菜单
Systematic documentation methodology for Claude Code projects using empirically validated templates, patterns, and automation. Provides structure for living documentation, doc health checks, gap analysis, and doc evolution workflows.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Autonomous unified B″ Worker for the backlog.md board. Drives BOTH lanes from one Monitor session: basic-ready events execute kind:basic tasks in isolated git worktrees that merge back on success; epic-ready events auto-decompose a kind:epic task (Epic: Ready → Decomposing → children at Basic: Backlog → Awaiting Children); child-done events reconcile the parent epic and, when all children are Basic: Done, run evaluate and write a FINISH/ITERATE recommendation for human confirmation. Invoke /loop-backlog once; it runs until the backlog/.loop-stop sentinel is written.
Interactive epic authoring for the B″ epic lane. Drives a brief multi-child epic idea through propose then plan, each gated by human-reviewed cycles, and parks it at Epic: Backlog. The plan enumerates intended child sub-tasks but creates none — the human promotes Epic: Backlog to Epic: Ready to authorize autonomous decomposition by the epic worker.
Drives the Proposal-to-Backlog pipeline for a software feature: two architect-reviewed cycles (one for Proposal, one for Plan), each converging on APPROVED within 8 rounds. Outputs a planSet entry ready for implementation; does not create branches or open PRs.
Schedules a non-coding work item — research inquiry, audit, survey, experiment, or written report — as a backlog entry. Single draft-and-critique cycle produces a phased execution checklist with shell-command gates. No compilation or test runner required.
One-time initializer for the backlog task board. Checks that the backlog CLI is installed, initializes a backlog project if none exists, and verifies that all columns required by loop-backlog and feature-to-backlog are present. Idempotent — safe to run multiple times.
Creates a Ready-status backlog task from a pre-approved template, bypassing the full review cycle. Performs a single LLM freshness check against recent git changes; if FRESH creates the task immediately, if STALE explains why and prompts the user to regenerate via task-to-backlog.
| name | documentation-management |
| description | Systematic documentation methodology for Claude Code projects using empirically validated templates, patterns, and automation. Provides structure for living documentation, doc health checks, gap analysis, and doc evolution workflows. |
| allowed-tools | Read, Write, Edit, Grep, Glob, Bash |
| contracts | [{"grep":"DocumentationArtifacts"},{"grep":"docs"},{"grep":"Markdown"},{"grep":"template"}] |
λ(project: ProjectContext) → DocumentationArtifacts
Systematic documentation methodology for Claude Code projects using empirically validated templates, patterns, and automation. All artifacts are written in Markdown.
name: documentation-management
version: 1.0.0
status: validated
domain: Documentation
tags: [documentation, writing, templates, automation, quality]
validated_on: meta-cc
convergence_iterations: 4
total_development_time: 20-22 hours
value_instance: 0.82
value_meta: 0.82
transferability: 93%
Validation Evidence:
Identify which documentation type you need:
templates/tutorial-structure.md)templates/concept-explanation.md)templates/example-walkthrough.md)templates/quick-reference.md)templates/troubleshooting-guide.md)# Copy the appropriate template
cp .claude/skills/documentation-management/templates/tutorial-structure.md docs/tutorials/my-guide.md
# Follow the template structure and guidelines
# Fill in sections with your content
Use these validated patterns while writing:
# Validate all links
python .claude/skills/documentation-management/tools/validate-links.py docs/
# Validate command syntax
python .claude/skills/documentation-management/tools/validate-commands.py docs/
Use the quality checklist in each template to self-assess:
This methodology follows a 4-phase lifecycle:
Phase 1: Needs Analysis
Phase 2: Strategy Formation
Phase 3: Writing/Execution
Phase 4: Validation
V_instance (Documentation Quality) = (Accuracy + Completeness + Usability + Maintainability) / 4
Component Definitions:
Target: V_instance ≥ 0.80 for production-ready documentation
Example Scoring:
This skill provides 5 empirically validated templates:
templates/tutorial-structure.md)templates/concept-explanation.md)templates/example-walkthrough.md)templates/quick-reference.md)templates/troubleshooting-guide.md)Retrospective Validation Results:
Problem: Users overwhelmed by complex topics presented all at once. Solution: Structure content from simple to complex, general to specific.
Implementation:
Validation: 4+ uses across BAIME guide, iteration docs, FAQ, examples
See: patterns/progressive-disclosure.md for comprehensive guide
Problem: Abstract concepts hard to understand without concrete examples. Solution: Pair every concept with concrete, realistic example.
Implementation:
Validation: 3+ uses across BAIME concepts, templates, examples
See: patterns/example-driven-explanation.md for comprehensive guide
Problem: Documentation organized around features, not user problems. Solution: Structure around problems users actually face.
Implementation:
Validation: 3+ uses across troubleshooting guides, error recovery
See: patterns/problem-solution-structure.md for comprehensive guide
tools/validate-links.py)Purpose: Detect broken internal/external links, missing files
Usage: python tools/validate-links.py docs/
Output: List of broken links with file locations
Speedup: 30x faster than manual checking
Tested: 13/15 links valid in meta-cc docs
tools/validate-commands.py)Purpose: Validate code blocks for correct syntax, detect typos
Usage: python tools/validate-commands.py docs/
Output: Invalid commands with line numbers
Speedup: 20x faster than manual testing
Tested: 20/20 commands valid in BAIME guide
Both tools are production-ready and integrate with CI/CD for automated quality gates.
Context: Create comprehensive guide for BAIME methodology Template Used: tutorial-structure.md Result: 1100-line tutorial with V_instance = 0.82
Key Decisions:
Lessons Learned:
Context: Document meta-cc CLI commands Template Used: quick-reference.md Result: Comprehensive command reference with 70% template match
Adaptations:
Lessons Learned:
Context: Test templates on existing meta-cc documentation Approach: Applied templates to 3 diverse docs (CLI, Installation, JSONL)
Results:
Insight: Templates extract genuine universal patterns (descriptive, not prescriptive)
Documentation is production-ready when:
Accuracy Assessment:
Completeness Assessment:
Usability Assessment:
Maintainability Assessment:
This methodology has been validated across:
Transferability Rate: 93% (empirically measured) Adaptation Effort: -3% (net time savings) Domain Independence: Universal (applies to all documentation types)
When adapting templates to your domain:
Keep Core Structure (90% match is ideal)
Adapt Content Depth (10-15% variation)
Customize Examples (domain-specific)
Follow Quality Checklist (from template)
Identify Documentation Type
Copy Template
cp templates/[template-name].md docs/[your-doc].md
Follow Template Structure
Apply Core Patterns
Validate Quality
python tools/validate-links.py docs/[your-doc].md
python tools/validate-commands.py docs/[your-doc].md
Self-Assess
Assess Current State
Select Improvement Strategy
Apply Template Incrementally
Validate Improvements
Empirical Validation Over Assumptions
Multiple Examples Demonstrate Universality
Progressive Disclosure Reduces Cognitive Load
Problem-Solution Matches User Mental Model
Automation Enables Scale
Template Creation Is Infrastructure
Deferring Quick Wins
Single Example Syndrome
Feature-Centric Structure
Abstract-Only Explanations
Manual Validation Only
This methodology was developed using BAIME and can be used to document other BAIME experiments:
Use Tutorial Structure for methodology guides
Use Example Walkthrough for domain examples
Use Troubleshooting Guide for common issues
Apply Progressive Disclosure
After BAIME experiment converges, extract documentation:
This skill itself was extracted from a BAIME experiment (Bootstrap-Documentation).
Version: 1.0.0 (validated and converged) Created: 2025-10-19 Last Updated: 2025-10-19 Status: Production-ready
Validated On:
Known Limitations:
Future Enhancements:
Changelog:
Source Experiment: /home/yale/work/meta-cc/experiments/documentation-methodology/
Convergence: 4 iterations, ~20-22 hours, V_instance=0.82, V_meta=0.82
Methodology: BAIME (Bootstrapped AI Methodology Engineering)
Related Skills:
testing-strategy: Systematic testing methodologyerror-recovery: Error handling patternsknowledge-transfer: Onboarding methodologiesExternal Resources: