Skip to content

aiskillstore/marketplace / skills/64andrewwalker/skill-template

skill-template

Verified

Template for production-grade DocEngineering skills

FileKindSize
SKILL.mdskill md917 B
scripts/run.pyexecutablescript550 B
skill-report.jsonconfig12.1 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-04T17:05:58.499Z",
    "slug": "64andrewwalker-skill-template",
    "source_url": "https://github.com/64andrewwalker/calvin/tree/main/.promptpack/skills/_template",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "bf42ffd946a05534ed0dfb0c9f98d24c5876e02fded812eaec15d0909e3184d4",
    "tree_hash": "f828b2829e157d81b432497e32bc93c0d15d7bc67b7426aa08cd123afc1aff4a",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "skill-template",
    "description": "Template for building production-grade DocEngineering skills with structured instructions, validation steps, and portable assets.",
    "summary": "Build consistent DocEngineering skills with a reusable workflow template.",
    "icon": "πŸ“¦",
    "version": "1.0.1",
    "author": "64andrewwalker",
    "license": "MIT",
    "tags": [
      "skill-template",
      "docengineering",
      "agent-workflow",
      "validation",
      "developer-tools"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands"
    ],
    "category": "documentation"
  },
  "security_audit": {
    "risk_level": "safe",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "All five static findings are false positives caused by Markdown inline code formatting, not executable shell calls. I found no prompt injection, data exfiltration, or hidden execution intent in SKILL.md or scripts/run.py. The template declares Python Bash access, but the reviewed content uses it only for a simple self-test entrypoint.",
    "remediation": [],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 20,
            "line_end": 20
          },
          {
            "file": "SKILL.md",
            "line_start": 24,
            "line_end": 24
          },
          {
            "file": "SKILL.md",
            "line_start": 26,
            "line_end": 26
          },
          {
            "file": "SKILL.md",
            "line_start": 31,
            "line_end": 31
          },
          {
            "file": "SKILL.md",
            "line_start": 36,
            "line_end": 36
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:20:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 20,
        "line_end": 20,
        "snippet": "- Prefer relative paths via `{baseDir}` for portability."
      },
      {
        "id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 24,
        "line_end": 24,
        "snippet": "1. **Scout**: Use `Grep`/`find` to locate only the relevant files."
      },
      {
        "id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 26,
        "line_end": 26,
        "snippet": "3. **Execute**: Prefer deterministic scripts under `{baseDir}/scripts/`."
      },
      {
        "id": "external_commands:SKILL.md:31:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 31,
        "line_end": 31,
        "snippet": "- Define a strict output format (Markdown template in `{baseDir}/assets/` and/or JSON schema)."
      },
      {
        "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": "- If any hard gate fails, return `EXIT_BLOCKED` and list blockers."
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:20:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Line 20 contains Markdown inline code around {baseDir}. It is documentation for relative paths, not Ruby backtick execution or a shell command."
      },
      {
        "id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "Line 24 uses Markdown inline code for tool names Grep and find in a workflow step. It does not execute a command or interpolate user input."
      },
      {
        "id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Line 26 uses Markdown inline code to reference the scripts directory. It recommends deterministic scripts but contains no executable backtick expression."
      },
      {
        "id": "external_commands:SKILL.md:31:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Line 31 formats a relative asset path as Markdown inline code. This is prose documentation and not shell execution."
      },
      {
        "id": "external_commands:SKILL.md:36:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Line 36 formats the EXIT_BLOCKED status token as Markdown inline code. It is an output convention, not a command execution pattern."
      }
    ],
    "semantic_findings": [],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 2,
    "total_lines": 61,
    "audit_model": "codex",
    "audited_at": "2026-07-04T17:05:58.499Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Create DocEngineering Skills From a Template",
    "value_statement": "Building a reusable AI skill can create inconsistent instructions and weak validation. This template gives Claude, Codex, and Claude Code a structured workflow for skill creation.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "AI skill template",
      "DocEngineering skill",
      "skill scaffolding",
      "validation workflow",
      "prompt template",
      "agent instructions",
      "developer productivity"
    ],
    "actual_capabilities": [
      "Defines a frontmatter manifest with name, description, and allowed tools.",
      "Guides agents through scout, analyze, execute, and verify steps.",
      "Encourages relative paths through {baseDir} for portable skill assets.",
      "Includes a Python entrypoint that supports a --test self-check.",
      "Documents error handling for missing inputs and hard gate failures."
    ],
    "limitations": [
      "It is a template, so it needs customization before production use.",
      "It does not include a finished output schema or assets directory.",
      "It depends on authors to add domain-specific tests and validation.",
      "It allows only Python Bash commands by default."
    ],
    "use_cases": [
      {
        "title": "Bootstrap a New Skill",
        "description": "Start from a documented folder structure before adding domain instructions, assets, and validation scripts.",
        "target_user": "Skill author"
      },
      {
        "title": "Standardize Agent Workflow",
        "description": "Give contributors a shared scout, analyze, execute, and verify process for Claude, Codex, and Claude Code.",
        "target_user": "AI platform team"
      },
      {
        "title": "Teach Skill Design",
        "description": "Use the template to explain manifests, allowed tools, output rules, and failure handling.",
        "target_user": "Technical enablement lead"
      }
    ],
    "prompt_templates": [
      {
        "title": "Create a Basic Skill",
        "scenario": "Beginner setup",
        "prompt": "Use this template to create a basic documentation skill. Ask for missing inputs before changing files."
      },
      {
        "title": "Customize the Workflow",
        "scenario": "Intermediate adaptation",
        "prompt": "Adapt this skill template for my workflow. Update the scout, analyze, execute, and verify steps for the domain."
      },
      {
        "title": "Add Validation Gates",
        "scenario": "Advanced quality control",
        "prompt": "Extend this template with validation gates, expected outputs, and failure handling for a production skill."
      },
      {
        "title": "Prepare for Marketplace Review",
        "scenario": "Advanced release review",
        "prompt": "Review this customized skill against marketplace expectations. Identify missing metadata, risky tools, and unclear instructions."
      }
    ],
    "output_examples": [
      {
        "input": "Create a skill for release note writing.",
        "output": "A skill outline with focused instructions, supported tools, verification steps, and release note output expectations."
      },
      {
        "input": "Check whether my customized skill is ready for review.",
        "output": [
          "A readiness summary covering metadata, allowed tools, workflow clarity, and validation coverage.",
          "A short blocker list for missing inputs or failed checks."
        ]
      },
      {
        "input": "Add a self-test to the template.",
        "output": "A simple validation plan that runs the existing entrypoint and reports pass or blocked status."
      }
    ],
    "best_practices": [
      "Replace placeholder instructions with a narrow workflow for one clear domain.",
      "Keep allowed tools limited to the commands needed by the finished skill.",
      "Run the self-test and domain validation before publishing the skill."
    ],
    "anti_patterns": [
      "Publishing the template unchanged as a finished user workflow.",
      "Adding broad shell access without a clear validation requirement.",
      "Skipping output rules and leaving users to infer the result format."
    ],
    "faq": [
      {
        "question": "What does this skill help me build?",
        "answer": "It helps authors create structured DocEngineering skills with clear instructions, validation steps, and failure handling."
      },
      {
        "question": "Is this a finished workflow?",
        "answer": "No. It is a starting template that needs domain instructions, assets, and tests before production use."
      },
      {
        "question": "Which AI tools does it support?",
        "answer": "The report lists support for Claude, Codex, and Claude Code."
      },
      {
        "question": "Does it run external commands?",
        "answer": "The skill declares Python Bash access, and the included script only provides a simple self-test entrypoint."
      },
      {
        "question": "What should I customize first?",
        "answer": "Start with the skill description, domain workflow, expected output format, and validation checks."
      },
      {
        "question": "Can teams use it for standards?",
        "answer": "Yes. Teams can use it to standardize manifests, allowed tools, workflow steps, and review expectations."
      }
    ]
  },
  "file_structure": [
    {
      "name": "scripts",
      "type": "dir",
      "path": "scripts",
      "children": [
        {
          "name": "run.py",
          "type": "file",
          "path": "scripts/run.py",
          "lines": 24
        }
      ]
    },
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 37
    }
  ]
}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why β€” repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" β€” or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself β€” your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall