Skip to content

aiskillstore/marketplace / skills/92bilal26/session-intelligence-harvester

session-intelligence-harvester

Verified

This skill should be used after productive sessions to extract learnings and route them to appropriate Reusable Intelligence Infrastructure (RII) components. Use when corrections were made, format drift was fixed, new patterns emerged, or the user explicitly asks to "harvest learnings" or "capture session intelligence". Transforms one-time fixes into permanent organizational knowledge by implementing updates across multiple files.

FileKindSize
SKILL.mdskill md11.1 KB
skill-report.jsonconfig28.5 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-05T16:07:19.623Z",
    "slug": "92bilal26-session-intelligence-harvester",
    "source_url": "https://github.com/92Bilal26/TaskPilotAI/tree/main/.claude/skills/session-intelligence-harvester",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "fb29637813d191a511d209ddf8b3984d8a002b5c14d35685de6caf1dde160fef",
    "tree_hash": "2ad8e19449aa6339b9bdd7ed9bf4a03e78c5e19386fdabfa2cf6f6858c7c1d2c",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "session-intelligence-harvester",
    "description": "Extracts session corrections and reusable patterns, routes them to RII components, and guides updates to project knowledge files.",
    "summary": "Capture session learnings and convert them into reusable project intelligence.",
    "icon": "📦",
    "version": "1.0.1",
    "author": "92Bilal26",
    "license": "MIT",
    "tags": [
      "session-review",
      "knowledge-management",
      "process-improvement",
      "documentation"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands"
    ],
    "category": "productivity"
  },
  "security_audit": {
    "risk_level": "medium",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "The static external-command findings are false positives caused by Markdown code fences and inline code formatting. The system-reconnaissance findings are reflective checklist text, not host inspection. A medium semantic risk remains because the skill asks agents to edit files and commit changes by default.",
    "remediation": [
      {
        "issue": "Default file edits and commits",
        "suggestion": "Add mandatory user confirmation before file writes and a separate confirmation before commits.",
        "severity": "medium"
      },
      {
        "issue": "Broad target file scope",
        "suggestion": "Require a user-approved target file list or restrict edits to documented RII paths.",
        "severity": "medium"
      },
      {
        "issue": "Pre-commit review gap",
        "suggestion": "Require a changed-file list and diff summary before finalizing the harvest.",
        "severity": "low"
      }
    ],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 37,
            "line_end": 66
          },
          {
            "file": "SKILL.md",
            "line_start": 66,
            "line_end": 84
          },
          {
            "file": "SKILL.md",
            "line_start": 84,
            "line_end": 84
          },
          {
            "file": "SKILL.md",
            "line_start": 94,
            "line_end": 115
          },
          {
            "file": "SKILL.md",
            "line_start": 115,
            "line_end": 128
          },
          {
            "file": "SKILL.md",
            "line_start": 128,
            "line_end": 134
          },
          {
            "file": "SKILL.md",
            "line_start": 134,
            "line_end": 140
          },
          {
            "file": "SKILL.md",
            "line_start": 140,
            "line_end": 149
          },
          {
            "file": "SKILL.md",
            "line_start": 149,
            "line_end": 159
          },
          {
            "file": "SKILL.md",
            "line_start": 159,
            "line_end": 167
          },
          {
            "file": "SKILL.md",
            "line_start": 167,
            "line_end": 173
          },
          {
            "file": "SKILL.md",
            "line_start": 173,
            "line_end": 184
          },
          {
            "file": "SKILL.md",
            "line_start": 184,
            "line_end": 188
          },
          {
            "file": "SKILL.md",
            "line_start": 188,
            "line_end": 205
          },
          {
            "file": "SKILL.md",
            "line_start": 205,
            "line_end": 209
          },
          {
            "file": "SKILL.md",
            "line_start": 209,
            "line_end": 219
          },
          {
            "file": "SKILL.md",
            "line_start": 219,
            "line_end": 225
          },
          {
            "file": "SKILL.md",
            "line_start": 225,
            "line_end": 254
          },
          {
            "file": "SKILL.md",
            "line_start": 254,
            "line_end": 263
          },
          {
            "file": "SKILL.md",
            "line_start": 263,
            "line_end": 278
          },
          {
            "file": "SKILL.md",
            "line_start": 278,
            "line_end": 292
          },
          {
            "file": "SKILL.md",
            "line_start": 292,
            "line_end": 300
          }
        ]
      }
    ],
    "static_findings": [
      {
        "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": 66,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:66:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 66,
        "line_end": 84,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:84:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 84,
        "line_end": 84,
        "snippet": "**WHY ROUTING MATTERS**: Learnings placed in the wrong component don't prevent recurrence. A check i"
      },
      {
        "id": "external_commands:SKILL.md:94:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 94,
        "line_end": 115,
        "snippet": "```markdown"
      },
      {
        "id": "external_commands:SKILL.md:115:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 115,
        "line_end": 128,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:128:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 128,
        "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": 140,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:140:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 140,
        "line_end": 149,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:149:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 149,
        "line_end": 159,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:159:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 159,
        "line_end": 167,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:167:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 167,
        "line_end": 173,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:173:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 173,
        "line_end": 184,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:184:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 184,
        "line_end": 188,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:188:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 188,
        "line_end": 205,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:205:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 205,
        "line_end": 209,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:209:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 209,
        "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": 225,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:225:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 225,
        "line_end": 254,
        "snippet": "```markdown"
      },
      {
        "id": "external_commands:SKILL.md:254:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 254,
        "line_end": 263,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:263:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 263,
        "line_end": 278,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:278:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 278,
        "line_end": 292,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:292:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 292,
        "line_end": 300,
        "snippet": "```"
      },
      {
        "id": "blocker:SKILL.md:41:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 41,
        "line_end": 41,
        "snippet": "- Why did the error occur? (missing check, format drift, etc.)"
      },
      {
        "id": "blocker:SKILL.md:181:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 181,
        "line_end": 181,
        "snippet": "- \"What I did wrong\" list"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:37:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The detected backticks are Markdown code fences around templates, examples, or checklists. They are not Ruby or shell execution and do not process user input."
      },
      {
        "id": "external_commands:SKILL.md:66:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The detected backticks are Markdown code fences around templates, examples, or checklists. They are not Ruby or shell execution and do not process user input."
      },
      {
        "id": "external_commands:SKILL.md:84:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "This line is prose with inline Markdown formatting around file names, not Ruby or shell backtick execution. No command is formed or executed."
      },
      {
        "id": "external_commands:SKILL.md:94:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The detected backticks are Markdown code fences around templates, examples, or checklists. They are not Ruby or shell execution and do not process user input."
      },
      {
        "id": "external_commands:SKILL.md:115:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The detected backticks are Markdown code fences around templates, examples, or checklists. They are not Ruby or shell execution and do not process user input."
      },
      {
        "id": "external_commands:SKILL.md:128:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The detected backticks are Markdown code fences around templates, examples, or checklists. They are not Ruby or shell execution and do not process user input."
      },
      {
        "id": "external_commands:SKILL.md:134:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The detected backticks are Markdown code fences around templates, examples, or checklists. They are not Ruby or shell execution and do not process user input."
      },
      {
        "id": "external_commands:SKILL.md:140:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The detected backticks are Markdown code fences around templates, examples, or checklists. They are not Ruby or shell execution and do not process user input."
      },
      {
        "id": "external_commands:SKILL.md:149:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The detected backticks are Markdown code fences around templates, examples, or checklists. They are not Ruby or shell execution and do not process user input."
      },
      {
        "id": "external_commands:SKILL.md:159:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The detected backticks are Markdown code fences around templates, examples, or checklists. They are not Ruby or shell execution and do not process user input."
      },
      {
        "id": "external_commands:SKILL.md:167:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The detected backticks are Markdown code fences around templates, examples, or checklists. They are not Ruby or shell execution and do not process user input."
      },
      {
        "id": "external_commands:SKILL.md:173:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The detected backticks are Markdown code fences around templates, examples, or checklists. They are not Ruby or shell execution and do not process user input."
      },
      {
        "id": "external_commands:SKILL.md:184:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The detected backticks are Markdown code fences around templates, examples, or checklists. They are not Ruby or shell execution and do not process user input."
      },
      {
        "id": "external_commands:SKILL.md:188:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The detected backticks are Markdown code fences around templates, examples, or checklists. They are not Ruby or shell execution and do not process user input."
      },
      {
        "id": "external_commands:SKILL.md:205:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The detected backticks are Markdown code fences around templates, examples, or checklists. They are not Ruby or shell execution and do not process user input."
      },
      {
        "id": "external_commands:SKILL.md:209:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The detected backticks are Markdown code fences around templates, examples, or checklists. They are not Ruby or shell execution and do not process user input."
      },
      {
        "id": "external_commands:SKILL.md:219:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The detected backticks are Markdown code fences around templates, examples, or checklists. They are not Ruby or shell execution and do not process user input."
      },
      {
        "id": "external_commands:SKILL.md:225:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The detected backticks are Markdown code fences around templates, examples, or checklists. They are not Ruby or shell execution and do not process user input."
      },
      {
        "id": "external_commands:SKILL.md:254:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The detected backticks are Markdown code fences around templates, examples, or checklists. They are not Ruby or shell execution and do not process user input."
      },
      {
        "id": "external_commands:SKILL.md:263:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The detected backticks are Markdown code fences around templates, examples, or checklists. They are not Ruby or shell execution and do not process user input."
      },
      {
        "id": "external_commands:SKILL.md:278:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The detected backticks are Markdown code fences around templates, examples, or checklists. They are not Ruby or shell execution and do not process user input."
      },
      {
        "id": "external_commands:SKILL.md:292:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The detected backticks are Markdown code fences around templates, examples, or checklists. They are not Ruby or shell execution and do not process user input."
      },
      {
        "id": "blocker:SKILL.md:41:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The line asks why a workflow error happened during session review. It does not inspect the host system or enumerate system information."
      },
      {
        "id": "blocker:SKILL.md:181:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The phrase appears in a reflective failure-mode template for documentation. It is not system reconnaissance or host inspection."
      }
    ],
    "semantic_findings": [
      {
        "title": "Automatic Repository Modification and Commit Workflow",
        "description": "The skill directs the agent to implement updates by default, edit each target file, create a PHR, and commit changes. This can persist broad repository changes without explicit confirmation for each write or commit.",
        "severity": "medium",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 31,
            "line_end": 31
          },
          {
            "file": "SKILL.md",
            "line_start": 119,
            "line_end": 125
          },
          {
            "file": "SKILL.md",
            "line_start": 151,
            "line_end": 158
          }
        ],
        "confidence": 0.88,
        "confidence_reasoning": "The workflow explicitly tells the agent to make edits and commit changes by default. The risk is procedural and intent-level, not a static command-execution pattern."
      }
    ],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [
      {
        "title": "Automatic Repository Modification and Commit Workflow",
        "description": "The skill directs the agent to implement updates by default, edit each target file, create a PHR, and commit changes. This can persist broad repository changes without explicit confirmation for each write or commit.",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 31,
            "line_end": 31
          },
          {
            "file": "SKILL.md",
            "line_start": 119,
            "line_end": 125
          },
          {
            "file": "SKILL.md",
            "line_start": 151,
            "line_end": 158
          }
        ],
        "review_kind": "security",
        "source_category": "semantic",
        "source_severity": "medium",
        "confidence": 0.88,
        "confidence_reasoning": "The workflow explicitly tells the agent to make edits and commit changes by default. The risk is procedural and intent-level, not a static command-execution pattern."
      }
    ],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 1,
    "total_lines": 317,
    "audit_model": "codex",
    "audited_at": "2026-07-05T16:07:19.623Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Capture Session Learnings for Future Work",
    "value_statement": "Important session lessons are often lost after a task ends. This skill turns corrections and patterns into reusable project knowledge.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "session intelligence",
      "knowledge harvesting",
      "RII workflow",
      "process documentation",
      "agent guidance",
      "project memory",
      "workflow improvement"
    ],
    "actual_capabilities": [
      "Identifies corrections, format drift, and repeated failure modes from a session.",
      "Classifies learnings by target RII component, such as commands, agents, skills, or project guidance.",
      "Provides structured templates for documenting each learning, placement, rationale, and source.",
      "Guides agents through reading target files before preparing precise updates.",
      "Defines validation checks for routing, duplicate detection, style matching, and final harvest summaries."
    ],
    "limitations": [
      "The skill depends on accurate session context from the user or agent.",
      "It does not validate whether the target project uses the same RII structure.",
      "It can propose broad edits unless users define boundaries first.",
      "It requires human review before commits in sensitive repositories."
    ],
    "use_cases": [
      {
        "title": "Standardize Post-Session Learning Capture",
        "description": "Turn corrections from a productive session into durable project guidance.",
        "target_user": "Engineering leads"
      },
      {
        "title": "Update Agent and Skill Instructions",
        "description": "Route repeated agent mistakes to the right reusable instruction file.",
        "target_user": "Claude Code users"
      },
      {
        "title": "Keep Process Documentation Current",
        "description": "Record new workflow rules where future sessions will find them.",
        "target_user": "Documentation owners"
      }
    ],
    "prompt_templates": [
      {
        "title": "Harvest a Session",
        "scenario": "Beginner session review",
        "prompt": "Harvest learnings from this session. Identify corrections, classify each learning, and propose the target RII component before editing."
      },
      {
        "title": "Capture a Correction",
        "scenario": "Single recurring issue",
        "prompt": "We corrected a recurring format issue. Use the skill to document the root cause and show where the fix belongs."
      },
      {
        "title": "Update Reusable Guidance",
        "scenario": "Multiple related learnings",
        "prompt": "Review this session for reusable workflow patterns. Read the likely target files and prepare precise updates with rationale."
      },
      {
        "title": "Run a Controlled Full Harvest",
        "scenario": "Advanced repository update",
        "prompt": "Perform a full session intelligence harvest. Before edits or commits, show the target files, proposed changes, validation checks, and confirmation points."
      }
    ],
    "output_examples": [
      {
        "input": "A session fixed skill format drift across several instruction files.",
        "output": "A harvest summary listing each learning, its target component, the applied update, and the validation result."
      },
      {
        "input": "A user asks what should be encoded after a workflow failure.",
        "output": "A routed learning plan that names the root cause, target file, exact placement, and review steps."
      },
      {
        "input": "A team wants to preserve a new planning rule for future agents.",
        "output": "A concise update proposal for the relevant agent or command guidance, with rationale and confirmation checkpoints."
      }
    ],
    "best_practices": [
      "Ask for a dry-run summary before applying edits.",
      "Review target files and diffs before any commit.",
      "Use precise learning titles, root causes, and target components."
    ],
    "anti_patterns": [
      "Running harvests on vague or unresolved sessions.",
      "Committing updates before reviewing the changed files.",
      "Adding the same guidance to unrelated components."
    ],
    "faq": [
      {
        "question": "When should I use this skill?",
        "answer": "Use it after a session that corrected errors, found repeated patterns, or produced guidance worth reusing."
      },
      {
        "question": "Does it edit files automatically?",
        "answer": "The source workflow encourages edits by default. Ask for confirmation gates before using it in important repositories."
      },
      {
        "question": "What are RII components?",
        "answer": "They are reusable project knowledge files, such as agent instructions, commands, skills, and core guidance."
      },
      {
        "question": "Can I use it with Codex?",
        "answer": "Yes. The report lists support for Claude, Codex, and Claude Code workflows."
      },
      {
        "question": "What context should I provide?",
        "answer": "Provide the correction made, the original mistake, likely root cause, and files or workflows affected."
      },
      {
        "question": "How do I reduce risk?",
        "answer": "Request a dry run, approve target files, inspect diffs, and confirm separately before any commit."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 317
    }
  ]
}
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall