Skip to content

aiskillstore/marketplace / skills/2389-research/cookoff

cookoff

Verified

This skill should be used when moving from design to implementation. Triggers on "let's build", "implement this", "looks good let's code", "ready to implement". Presents options for parallel agent competition (cookoff), single subagent, or local implementation. Each agent creates own plan from shared design for genuine variation.

FileKindSize
SKILL.mdskill md13.3 KB
skill-report.jsonconfig59.8 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-09T11:12:58.518Z",
    "slug": "2389-research-cookoff",
    "source_url": "https://github.com/2389-research/claude-plugins/tree/main/test-kitchen/skills/cookoff",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "a366bed94cdbcac0de66543e7c347ac56c58a8ff25b13efaf627ed6dae0520a8",
    "tree_hash": "0663722073da2b1e65b5211d47d5dfc3e701e8dc1493949b5deb9cbc1a9b2d44",
    "provenance": {
      "model_requested": "gpt-5.5:high",
      "model_effective": "codex:gpt-5.5:high",
      "fallback_chain": [
        {
          "agent": "codex",
          "model": "gpt-5.5",
          "effort": "high",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "cookoff",
    "description": "Coordinates a design-to-implementation cookoff where multiple agents create independent plans, implement in worktrees, compare results, and select a winner.",
    "summary": "Run parallel implementation cookoffs from a shared design and select the strongest result.",
    "icon": "📦",
    "version": "1.0.0",
    "author": "2389-research",
    "license": "MIT",
    "tags": [
      "implementation-planning",
      "parallel-agents",
      "git-worktrees",
      "code-review",
      "quality-assurance"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands",
      "filesystem"
    ],
    "category": "coding"
  },
  "security_audit": {
    "risk_level": "medium",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "Most static findings are false positives caused by Markdown backticks and fenced examples, not Ruby shell execution. No prompt injection, network reconnaissance, or system reconnaissance evidence was found. The main risk is the cleanup workflow, which can delete worktrees and branches without explicit confirmation.",
    "remediation": [
      {
        "issue": "Destructive cleanup commands",
        "suggestion": "Require user confirmation and show a dry-run list before removing worktrees or deleting branches. Preserve loser branches unless the user approves deletion.",
        "severity": "medium"
      },
      {
        "issue": "Templated shell paths and branch names",
        "suggestion": "Validate and quote feature names before using them in filesystem or git commands. Avoid passing raw user text into shell commands.",
        "severity": "low"
      },
      {
        "issue": "Companion skill dependency trust",
        "suggestion": "State that companion skills should be installed from trusted sources and reviewed before use in the cookoff workflow.",
        "severity": "low"
      }
    ],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 11,
            "line_end": 11
          },
          {
            "file": "SKILL.md",
            "line_start": 12,
            "line_end": 12
          },
          {
            "file": "SKILL.md",
            "line_start": 18,
            "line_end": 29
          },
          {
            "file": "SKILL.md",
            "line_start": 29,
            "line_end": 35
          },
          {
            "file": "SKILL.md",
            "line_start": 35,
            "line_end": 35
          },
          {
            "file": "SKILL.md",
            "line_start": 36,
            "line_end": 36
          },
          {
            "file": "SKILL.md",
            "line_start": 37,
            "line_end": 37
          },
          {
            "file": "SKILL.md",
            "line_start": 38,
            "line_end": 38
          },
          {
            "file": "SKILL.md",
            "line_start": 39,
            "line_end": 39
          },
          {
            "file": "SKILL.md",
            "line_start": 40,
            "line_end": 40
          },
          {
            "file": "SKILL.md",
            "line_start": 41,
            "line_end": 41
          },
          {
            "file": "SKILL.md",
            "line_start": 42,
            "line_end": 42
          },
          {
            "file": "SKILL.md",
            "line_start": 43,
            "line_end": 43
          },
          {
            "file": "SKILL.md",
            "line_start": 44,
            "line_end": 44
          },
          {
            "file": "SKILL.md",
            "line_start": 45,
            "line_end": 45
          },
          {
            "file": "SKILL.md",
            "line_start": 70,
            "line_end": 78
          },
          {
            "file": "SKILL.md",
            "line_start": 78,
            "line_end": 91
          },
          {
            "file": "SKILL.md",
            "line_start": 91,
            "line_end": 101
          },
          {
            "file": "SKILL.md",
            "line_start": 101,
            "line_end": 125
          },
          {
            "file": "SKILL.md",
            "line_start": 125,
            "line_end": 127
          },
          {
            "file": "SKILL.md",
            "line_start": 127,
            "line_end": 130
          },
          {
            "file": "SKILL.md",
            "line_start": 130,
            "line_end": 134
          },
          {
            "file": "SKILL.md",
            "line_start": 134,
            "line_end": 139
          },
          {
            "file": "SKILL.md",
            "line_start": 139,
            "line_end": 148
          },
          {
            "file": "SKILL.md",
            "line_start": 148,
            "line_end": 152
          },
          {
            "file": "SKILL.md",
            "line_start": 152,
            "line_end": 154
          },
          {
            "file": "SKILL.md",
            "line_start": 154,
            "line_end": 160
          },
          {
            "file": "SKILL.md",
            "line_start": 160,
            "line_end": 166
          },
          {
            "file": "SKILL.md",
            "line_start": 166,
            "line_end": 193
          },
          {
            "file": "SKILL.md",
            "line_start": 193,
            "line_end": 196
          },
          {
            "file": "SKILL.md",
            "line_start": 196,
            "line_end": 201
          },
          {
            "file": "SKILL.md",
            "line_start": 201,
            "line_end": 212
          },
          {
            "file": "SKILL.md",
            "line_start": 212,
            "line_end": 214
          },
          {
            "file": "SKILL.md",
            "line_start": 214,
            "line_end": 219
          },
          {
            "file": "SKILL.md",
            "line_start": 219,
            "line_end": 223
          },
          {
            "file": "SKILL.md",
            "line_start": 223,
            "line_end": 227
          },
          {
            "file": "SKILL.md",
            "line_start": 227,
            "line_end": 231
          },
          {
            "file": "SKILL.md",
            "line_start": 231,
            "line_end": 240
          },
          {
            "file": "SKILL.md",
            "line_start": 240,
            "line_end": 255
          },
          {
            "file": "SKILL.md",
            "line_start": 255,
            "line_end": 262
          },
          {
            "file": "SKILL.md",
            "line_start": 262,
            "line_end": 264
          },
          {
            "file": "SKILL.md",
            "line_start": 264,
            "line_end": 268
          },
          {
            "file": "SKILL.md",
            "line_start": 268,
            "line_end": 274
          },
          {
            "file": "SKILL.md",
            "line_start": 274,
            "line_end": 277
          },
          {
            "file": "SKILL.md",
            "line_start": 277,
            "line_end": 302
          },
          {
            "file": "SKILL.md",
            "line_start": 302,
            "line_end": 304
          },
          {
            "file": "SKILL.md",
            "line_start": 304,
            "line_end": 310
          },
          {
            "file": "SKILL.md",
            "line_start": 310,
            "line_end": 311
          },
          {
            "file": "SKILL.md",
            "line_start": 311,
            "line_end": 312
          },
          {
            "file": "SKILL.md",
            "line_start": 312,
            "line_end": 313
          }
        ]
      },
      {
        "factor": "filesystem",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 171,
            "line_end": 171
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:11:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 11,
        "line_end": 11,
        "snippet": "- `omakase-off` - Chef's choice exploration (different approaches/designs)"
      },
      {
        "id": "external_commands:SKILL.md:12:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 12,
        "line_end": 12,
        "snippet": "- `cookoff` - Same design, multiple cooks compete (each creates own plan + implements)"
      },
      {
        "id": "external_commands:SKILL.md:18:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 18,
        "line_end": 29,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:29:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 29,
        "line_end": 35,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:35:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 35,
        "line_end": 35,
        "snippet": "| `writing-plans` | `superpowers:writing-plans` | Each agent writes their own implementation plan |"
      },
      {
        "id": "external_commands:SKILL.md:36:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 36,
        "line_end": 36,
        "snippet": "| `executing-plans` | `superpowers:executing-plans` | Execute plan tasks sequentially with verificat"
      },
      {
        "id": "external_commands:SKILL.md:37:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 37,
        "line_end": 37,
        "snippet": "| `parallel-agents` | `superpowers:dispatching-parallel-agents` | Dispatch multiple Task tools in si"
      },
      {
        "id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 38,
        "line_end": 38,
        "snippet": "| `git-worktrees` | `superpowers:using-git-worktrees` | `git worktree add .worktrees/<name> -b <bran"
      },
      {
        "id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 39,
        "line_end": 39,
        "snippet": "| `tdd` | `superpowers:test-driven-development` | RED-GREEN-REFACTOR cycle |"
      },
      {
        "id": "external_commands:SKILL.md:40:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 40,
        "line_end": 40,
        "snippet": "| `verification` | `superpowers:verification-before-completion` | Run command, read output, THEN cla"
      },
      {
        "id": "external_commands:SKILL.md:41:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 41,
        "line_end": 41,
        "snippet": "| `fresh-eyes` | `fresh-eyes-review:skills` (2389) | 2-5 min review for security, logic, edge cases "
      },
      {
        "id": "external_commands:SKILL.md:42:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 42,
        "line_end": 42,
        "snippet": "| `judge` | `test-kitchen:judge` | Scoring framework with checklists (MUST invoke at Phase 4) |"
      },
      {
        "id": "external_commands:SKILL.md:43:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 43,
        "line_end": 43,
        "snippet": "| `code-review` | `superpowers:requesting-code-review` | Dispatch code-reviewer subagent |"
      },
      {
        "id": "external_commands:SKILL.md:44:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 44,
        "line_end": 44,
        "snippet": "| `scenario-testing` | `scenario-testing:skills` (2389) | `.scratch/` E2E scripts, real dependencies"
      },
      {
        "id": "external_commands:SKILL.md:45:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 45,
        "line_end": 45,
        "snippet": "| `finish-branch` | `superpowers:finishing-a-development-branch` | Verify tests, present options, cl"
      },
      {
        "id": "external_commands:SKILL.md:70:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 70,
        "line_end": 78,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:78:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 78,
        "line_end": 91,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:91:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 91,
        "line_end": 101,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:101:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 101,
        "line_end": 125,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:125:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 125,
        "line_end": 127,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:127:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 127,
        "line_end": 130,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:130:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 130,
        "line_end": 134,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:134:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 134,
        "line_end": 139,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:139:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 139,
        "line_end": 148,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:148:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 148,
        "line_end": 152,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:152:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 152,
        "line_end": 154,
        "snippet": "Use `parallel-agents` pattern. Send ONE message with multiple Task tool calls:"
      },
      {
        "id": "external_commands:SKILL.md:154:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 154,
        "line_end": 160,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:160:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 160,
        "line_end": 166,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:166:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 166,
        "line_end": 193,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:193:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 193,
        "line_end": 196,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:196:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 196,
        "line_end": 201,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:201:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 201,
        "line_end": 212,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:212:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 212,
        "line_end": 214,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:214:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 214,
        "line_end": 219,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:219:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 219,
        "line_end": 223,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:223:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 223,
        "line_end": 227,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:227:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 227,
        "line_end": 231,
        "snippet": "**CRITICAL: Invoke `test-kitchen:judge` now.**"
      },
      {
        "id": "external_commands:SKILL.md:231:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 231,
        "line_end": 240,
        "snippet": "```text"
      },
      {
        "id": "external_commands:SKILL.md:240:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 240,
        "line_end": 255,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:255:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 255,
        "line_end": 262,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:262:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 262,
        "line_end": 264,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:264:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 264,
        "line_end": 268,
        "snippet": "**Winner:** Use `finish-branch`"
      },
      {
        "id": "external_commands:SKILL.md:268:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 268,
        "line_end": 274,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:274:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 274,
        "line_end": 277,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:277:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 277,
        "line_end": 302,
        "snippet": "```markdown"
      },
      {
        "id": "external_commands:SKILL.md:302:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 302,
        "line_end": 304,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:304:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 304,
        "line_end": 310,
        "snippet": "Save to: `docs/plans/<feature>/cookoff/result.md`"
      },
      {
        "id": "external_commands:SKILL.md:310:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 310,
        "line_end": 311,
        "snippet": "| `writing-plans` | 3 | Each subagent creates their own implementation plan |"
      },
      {
        "id": "external_commands:SKILL.md:311:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 311,
        "line_end": 312,
        "snippet": "| `executing-plans` | 3 | Each subagent implements their plan |"
      },
      {
        "id": "external_commands:SKILL.md:312:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 312,
        "line_end": 313,
        "snippet": "| `parallel-agents` | 3 | Dispatch ALL subagents in SINGLE message |"
      },
      {
        "id": "external_commands:SKILL.md:313:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 313,
        "line_end": 314,
        "snippet": "| `git-worktrees` | 3 | Create worktree per implementation |"
      },
      {
        "id": "external_commands:SKILL.md:314:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 314,
        "line_end": 315,
        "snippet": "| `tdd` | 3 | Subagents follow RED-GREEN-REFACTOR |"
      },
      {
        "id": "external_commands:SKILL.md:315:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 315,
        "line_end": 316,
        "snippet": "| `verification` | 3, 5 | Before claiming done; before declaring winner |"
      },
      {
        "id": "external_commands:SKILL.md:316:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 316,
        "line_end": 317,
        "snippet": "| `code-review` | 3 | Review each impl after completion |"
      },
      {
        "id": "external_commands:SKILL.md:317:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 317,
        "line_end": 318,
        "snippet": "| `fresh-eyes` | 4 | Quality review → judge input |"
      },
      {
        "id": "external_commands:SKILL.md:318:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 318,
        "line_end": 319,
        "snippet": "| `judge` | 4 | **INVOKE** for scoring framework (loads fresh, ensures format compliance) |"
      },
      {
        "id": "external_commands:SKILL.md:319:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 319,
        "line_end": 320,
        "snippet": "| `scenario-testing` | 4 | Validate if scenarios defined |"
      },
      {
        "id": "external_commands:SKILL.md:320:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 320,
        "line_end": 350,
        "snippet": "| `finish-branch` | 5 | Handle winner, cleanup losers |"
      },
      {
        "id": "external_commands:SKILL.md:350:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 350,
        "line_end": 395,
        "snippet": "```"
      },
      {
        "id": "filesystem:SKILL.md:171:hidden-file-access",
        "category": "filesystem",
        "severity": "medium",
        "pattern": "Hidden file access",
        "file": "SKILL.md",
        "line_start": 171,
        "line_end": 171,
        "snippet": "**Your working directory:** /path/to/.worktrees/cookoff-impl-N"
      },
      {
        "id": "blocker:SKILL.md:296:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 296,
        "line_end": 296,
        "snippet": "Reason: Clean fresh-eyes review, solid data-layer-first architecture"
      },
      {
        "id": "blocker:SKILL.md:206:network-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "Network reconnaissance",
        "file": "SKILL.md",
        "line_start": 206,
        "line_end": 207,
        "snippet": "- All tests pass"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:11:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:12:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:18:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:29:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:35:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:36:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:37:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.84,
        "reason": "The git worktree command appears as an inline documentation example. It is not executable code and is part of an expected user-approved development workflow."
      },
      {
        "id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:40:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:41:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:42:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:43:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:44:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:45:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:70:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:78:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:91:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:101:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:125:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.85,
        "reason": "The fenced bash example creates a planned project directory. It is not Ruby backtick execution and does not execute user-controlled shell code."
      },
      {
        "id": "external_commands:SKILL.md:127:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:130:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:134:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:139:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:148:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:152:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:154:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:160:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:166:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:193:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:196:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:201:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:212:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.86,
        "reason": "The fenced bash example compares known worktree directories with diff. It is not hidden execution, data exfiltration, or dynamic command construction."
      },
      {
        "id": "external_commands:SKILL.md:214:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:219:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:223:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:227:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:231:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:240:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:255:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:262:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:264:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:268:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.78,
        "reason": "The referenced block includes git worktree removal and forced branch deletion commands. These commands can delete local work if run on incorrect branch names or without user confirmation.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:274:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:277:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:302:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:304:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:310:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:311:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:312:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:313:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:314:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:315:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:316:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:317:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:318:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:319:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:320:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "external_commands:SKILL.md:350:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The match is Markdown inline code or a fenced block delimiter in documentation, not Ruby shell backtick execution. No automatic command execution is present at this location."
      },
      {
        "id": "filesystem:SKILL.md:171:hidden-file-access",
        "verdict": "false_positive",
        "confidence": 0.88,
        "reason": "The hidden path is a documented git worktree working directory, not covert access to hidden files. It supports isolated implementations and does not read secrets or persistence files."
      },
      {
        "id": "blocker:SKILL.md:296:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The matched line is prose explaining a sample winner selection reason. It contains no host inspection, system enumeration, or reconnaissance instruction."
      },
      {
        "id": "blocker:SKILL.md:206:network-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The matched text is a checklist item stating that tests pass. It contains no network scanning, remote probing, or external connection instruction."
      }
    ],
    "semantic_findings": [
      {
        "title": "Destructive Cleanup Commands Need Confirmation",
        "description": "The cleanup workflow tells the agent to remove loser worktrees and force-delete branches. This can cause local data loss if branch names or worktree paths are wrong.",
        "severity": "medium",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 267,
            "line_end": 273
          }
        ],
        "confidence": 0.86,
        "confidence_reasoning": "The commands shown in the cleanup block directly remove worktrees and delete branches with force. The risk is contextual data loss, not hidden malware."
      }
    ],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 268,
            "line_end": 274
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.78,
        "confidence_reasoning": "The referenced block includes git worktree removal and forced branch deletion commands. These commands can delete local work if run on incorrect branch names or without user confirmation."
      },
      {
        "title": "Destructive Cleanup Commands Need Confirmation",
        "description": "The cleanup workflow tells the agent to remove loser worktrees and force-delete branches. This can cause local data loss if branch names or worktree paths are wrong.",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 267,
            "line_end": 273
          }
        ],
        "review_kind": "security",
        "source_category": "semantic",
        "source_severity": "medium",
        "confidence": 0.86,
        "confidence_reasoning": "The commands shown in the cleanup block directly remove worktrees and delete branches with force. The risk is contextual data loss, not hidden malware."
      }
    ],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 1,
    "total_lines": 396,
    "audit_model": "codex",
    "audited_at": "2026-07-09T11:12:58.518Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Compare Parallel Implementations",
    "value_statement": "Complex features often have several valid implementation paths. This skill runs independent agent implementations, reviews them, and helps select the strongest result.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "parallel coding agents",
      "implementation planning",
      "git worktrees",
      "code review workflow",
      "TDD workflow",
      "AI development automation",
      "software quality assurance"
    ],
    "actual_capabilities": [
      "Offers implementation choices when a design is ready to build.",
      "Assesses feature complexity and recommends two to five implementations.",
      "Defines plan folders and worktrees for independent agent attempts.",
      "Coordinates parallel agents that plan, implement, test, and report results.",
      "Guides judging with tests, review findings, scorecards, and winner selection.",
      "Records results and cleanup steps after a winner is chosen."
    ],
    "limitations": [
      "Requires a design document or clear shared implementation target.",
      "Depends on companion skills when they are available.",
      "Uses more time and compute than a single implementation path.",
      "Cleanup commands need review because they can remove local branches."
    ],
    "use_cases": [
      {
        "title": "Evaluate Competing Feature Builds",
        "description": "Run several independent implementations of a feature and compare quality before choosing one.",
        "target_user": "Engineering lead"
      },
      {
        "title": "Reduce Design Bias",
        "description": "Let agents create separate plans from the same design instead of sharing one implementation plan.",
        "target_user": "Senior developer"
      },
      {
        "title": "Document Build Decisions",
        "description": "Capture plans, test results, review notes, and winner rationale for later team review.",
        "target_user": "Technical project manager"
      }
    ],
    "prompt_templates": [
      {
        "title": "Start a Simple Cookoff",
        "scenario": "Beginner prompt after a design is approved.",
        "prompt": "Use cookoff for this approved design. Recommend the number of implementations and show the options before starting."
      },
      {
        "title": "Compare Three Implementations",
        "scenario": "Intermediate prompt for a medium feature.",
        "prompt": "Run a three-agent cookoff from the design document. Each agent should write its own plan, implement, test, and report results."
      },
      {
        "title": "Judge With Review Signals",
        "scenario": "Advanced prompt for final selection.",
        "prompt": "Judge the cookoff results using tests, fresh review findings, design adherence, and maintainability. Explain the winner and rejected options."
      },
      {
        "title": "Manage Full Cookoff Lifecycle",
        "scenario": "Advanced prompt for end-to-end workflow control.",
        "prompt": "Run the full cookoff lifecycle. Create worktrees, coordinate agents, compare outputs, request approval before cleanup, and write the result summary."
      }
    ],
    "output_examples": [
      {
        "input": "Use cookoff for the approved authentication design.",
        "output": "The skill recommends three implementations because the feature touches authentication, data flow, and tests. It presents options before dispatching agents."
      },
      {
        "input": "Pick the winner from these cookoff results.",
        "output": "The skill compares test status, review findings, design adherence, and maintainability. It recommends the strongest implementation with a short rationale."
      },
      {
        "input": "Finish the cookoff and clean up safely.",
        "output": "The skill verifies the winning implementation, records the result summary, lists branches for cleanup, and asks before destructive deletion."
      }
    ],
    "best_practices": [
      "Start from a stable design document so every agent has the same target.",
      "Ask agents to create independent plans before writing implementation code.",
      "Review tests, design adherence, and maintainability before selecting a winner."
    ],
    "anti_patterns": [
      "Do not give every agent the same detailed implementation plan.",
      "Do not dispatch agents one at a time when the goal is parallel comparison.",
      "Do not delete worktrees or branches before reviewing the cleanup list."
    ],
    "faq": [
      {
        "question": "When should I use this skill?",
        "answer": "Use it after design approval, when you want several independent implementation options before choosing one."
      },
      {
        "question": "Does it write the design document?",
        "answer": "No. It expects a design document or a clear design agreement before implementation starts."
      },
      {
        "question": "How many agents does it use?",
        "answer": "It recommends two to five implementations based on feature complexity and risk."
      },
      {
        "question": "Does it require git worktrees?",
        "answer": "The workflow is built around separate worktrees so each implementation stays isolated."
      },
      {
        "question": "Can it work without companion skills?",
        "answer": "Yes, but companion skills provide stronger planning, execution, review, and finishing workflows."
      },
      {
        "question": "What should I verify before cleanup?",
        "answer": "Check the winning branch, loser branches, worktree paths, and user approval before deleting anything."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 396
    }
  ]
}
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 322kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall