documentation-maintenance
Ensures project documentation stays aligned with actual implementation and validated behavior.
Install
mkdir -p .claude/skills/documentation-maintenance && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14768" && unzip -o skill.zip -d .claude/skills/documentation-maintenance && rm skill.zipInstalls to .claude/skills/documentation-maintenance
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Keep repository-visible docs current, concise, and aligned with implementation and validation evidence.Key capabilities
- →Update documentation when implementation or contract changes
- →Keep documentation concise and factual
- →Match terminology across documentation and implementation
- →Remove stale references and duplicate explanations
- →Preserve authority boundaries between documentation and runtime code
How it works
The skill reads project grounding files, design documents, and implementation evidence to identify discrepancies and then updates documentation to reflect validated behavior and consistent terminology.
Inputs & outputs
When to use documentation-maintenance
- →Update stale documentation
- →Sync docs with implementation changes
- →Remove duplicate or speculative info
- →Standardize technical terminology
About this skill
Documentation Maintenance
Purpose
Keep docs accurate without turning them into a parallel source of truth.
Read
AGENTS.md- project grounding file
- relevant design docs
- relevant implementation and validation evidence
Do
- Update docs only where the implementation or contract changed.
- Keep wording concise and factual.
- Preserve authority boundaries between docs and runtime code.
- Match terminology across docs and implementation.
- Remove stale references and duplicate explanations.
Outputs
- Doc deltas tied to behavior changes
- Stale references removed
- Consistency gaps called out
Rules
- Do not pad docs with speculative detail.
- Do not let docs drift from validated behavior.
When not to use it
- →When adding speculative details to documentation
- →When documentation drifts from validated behavior
Limitations
- →Cannot add speculative detail to documentation
- →Cannot let documentation drift from validated behavior
How it compares
This skill ensures documentation reflects actual implementation and validated behavior, unlike manual updates that can introduce inconsistencies or speculative content.
Compared to similar skills
documentation-maintenance side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| documentation-maintenance (this skill) | 0 | 3mo | No flags | Beginner |
| documentation-review | 11 | 5mo | No flags | Beginner |
| docs-review | 10 | 8mo | No flags | Beginner |
| workthrough | 10 | 9mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by chethanp11
View all by chethanp11 →You might also like
documentation-review
stacklok
Reviews documentation for factual accuracy
docs-review
metabase
Review documentation changes for compliance with the Metabase writing style guide. Use when reviewing pull requests, files, or diffs containing documentation markdown files.
workthrough
bear2u
Automatically document all development work and code modifications in a structured workthrough format. Use this skill after completing any development task, bug fix, feature implementation, or code refactoring to create comprehensive documentation.
claude-md-improver
anthropics
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project memory optimization".
anti-slop
rand
Comprehensive toolkit for detecting and eliminating "AI slop" - generic, low-quality AI-generated patterns in natural language, code, and design. Use when reviewing or improving content quality, preventing generic AI patterns, cleaning up existing content, or enforcing quality standards in writing, code, or design work.
agent-md-refactor
davila7
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.