agentleFS
wonderslifewonderslife/pdd-skills/pdd-doc-gardener/SKILL.md

pdd-doc-gardener

Skill41 starsChanged 8 months agoMITView on GitHub

Document Gardener skill that periodically scans document directories in the codebase to identify outdated or deprecated documents. Automatically triggered when users need document consistency checks, document updates, or document cleanup.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Document Gardener is a key skill for implementing garbage collection, responsible for periodically scanning the docs/ directory in the …

    line 24
  2. Distinctive:

    Check if referenced code exists

    line 32
  3. Distinctive:

    Check if code behavior matches document description

    line 33
  4. Distinctive:

    Check if files exist

    line 59

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Document Gardener (pdd-doc-gardener)

Core Philosophy

"Documentation as code, keep synchronized. Outdated documentation is technical debt." —— PDD Golden Principle

Document Gardener is a key skill for implementing garbage collection, responsible for periodically scanning the docs/ directory in the codebase to identify outdated or deprecated documents that no longer reflect actual code behavior.

Detection Items

1. Code-Document Inconsistency

Detection Method:

  • Parse code references in documents (e.g., file paths, function names, API endpoints)
  • Check if referenced code exists
  • Check if code behavior matches document description

Example:

Document description: API /api/users returns user list
Actual code: API /api/users returns user details (including orders)
→ Detection result: Document outdated

2. Outdated Comments

Detection Method:

  • Scan TODO, FIXME, HACK comments in code
  • Check comment age
  • Mark comments older than N days as outdated

Example:

Code comment: // TODO: implement this later (created 30 days ago)
→ Detection result: Comment outdated, needs handling or deletion

3. Document References Deleted Code

Detection Method:

  • Parse file path references in documents
  • Check if files exist
  • Mark documents referencing deleted files

Example:

Document reference: See src/utils/helper.js
Actual status: File deleted
→ Detection result: Document reference invalid

4. API Documentation Mismatch with Implementation

Detection Method:

  • Parse endpoint definitions in API documentation
  • Scan actual API implementations in code
  • Compare parameters, return values, error codes

Example:

API documentation: POST /api/users, parameters { name, email }
Actual code: POST /api/users, parameters { name, email, phone }
→ Detection result: API documentation missing parameter description

Execution Flow

┌─────────────┐     ┌─────────────┐     ┌─────────────┐     ┌─────────────┐
│   Scan      │ ──→ │   Compare   │ ──→ │   Classify  │ ──→ │   Execute   │
│             │     │             │     │             │     │             │
│ • Doc dirs  │     │ • Code refs │     │ • Issue type│     │ • Update    │
│ • Code      │     │ • API defs  │     │ • Severity  │     │   docs      │
│   comments  │     │ • Behavior  │     │ • Priority  │     │ • Create PR │
│ • API docs  │     │   desc      │     │             │     │ • Delete    │
│             │     │             │     │             │     │   deprecated│
└─────────────┘     └─────────────┘     └─────────────┘     └─────────────┘

Output Format

Document Gardener Report

# Document Gardener Report - YYYY-MM-DD

## Scan Scope
- Document directory: docs/
- Code directory: src/
- Files scanned: XX

## Issues Found

### Critical (Must Fix)
| File | Issue | Suggestion |
|------|-------|------------|
| docs/api/users.md | API parameter missing | Add phone parameter description |

### Warning (Recommended Fix)
| File | Issue | Suggestion |
|------|-------|------------|
| docs/architecture.md | References deleted file | Update reference path |

### Info (Optional Fix)
| File | Issue | Suggestion |
|------|-------|------------|
| src/utils/helper.js | TODO exists for 30 days | Handle or delete |

## Execution Results
- Documents updated: X items
- PRs created: X items
- Skipped: X items

Usage Examples

Example 1: Comprehensive Document Check

User: Check all document consistency

AI:
1. Scan docs/ directory
2. Parse all code references in documents
3. Compare with code implementation
4. Generate report and create fix PR

Example 2: API Documentation Check

User: Check if API documentation matches code

AI:
1. Scan docs/api/ directory
2. Parse API endpoint definitions
3. Compare with API implementations in code
4. Generate difference report

Example 3: Clean Up Outdated Comments

User: Clean up outdated TODOs in code

AI:
1. Scan TODO/FIXME comments in code
2. Check comment age
3. Mark comments older than 30 days
4. Generate cleanup suggestions

Configuration Options

# doc-gardener-config.yaml
doc_gardener:
  # Scan configuration
  scan:
    docs_paths: ["docs/", "*.md"]
    code_paths: ["src/"]
    exclude: ["node_modules/", "dist/"]
  
  # Staleness detection
  staleness:
    todo_max_age_days: 30
    doc_max_age_days: 90
  
  # Execution configuration
  execution:
    auto_update: true      # Auto-update simple documents
    create_pr: true        # Create PR
    max_pr_per_run: 3      # Max PRs per run

Collaboration with Other Skills

  • pdd-entropy-reduction: Invoked as a sub-skill by the coordinator
  • pdd-doc-change: Calls this skill to create document change PRs
  • expert-entropy-auditor: Receives audit results, executes document fixes

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.