accountable-engineerin…
Use explicit human checkpoints for architecture, security, rollout, or operational decisions.
Update docs when code changes — reviews commits and syncs user-facing documentation
$ npx -y skills add jellydn/my-ai-tools --skill docs-update --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/docs-updateContext preview
The summary Claude sees to decide when to auto-load this skill.
Update docs when code changes — reviews commits and syncs user-facing documentation
name: docs-update description: "Update docs when code changes — reviews commits and syncs user-facing documentation" license: MIT compatibility: cline, claude, opencode, amp, codex, gemini, cursor, pi hint: Use when updating documentation, reviewing docs, or handling documentation changes after code changes user-invocable: true disable-model-invocation: true metadata: audience: all workflow: documentation
Automatically review code changes and update user-facing documentation to keep it synchronized with the codebase. Works across documentation platforms (Mintlify, Docusaurus, GitBook, Fumadocs, etc.) and supports both monorepo and multi-repo setups.
Determine which commits need documentation updates:
**Filter for significant changes:**
**Skip documentation for:**
Be conservative: quality over quantity. When in doubt about significance, skip the update.
**Locate documentation:**
**Identify documentation platform:** Determine the platform by examining configuration files and directory structure (e.g., Mintlify, Docusaurus, GitBook, Fumadocs, or generic markdown).
**Understand documentation style:** Read several existing documentation files to identify tone, voice, structure, code example patterns, terminology, and formatting conventions. Check for style guides or contribution documentation.
Map code changes to documentation needs (new content, modifications, or additions to existing content).
**Guidelines:**
**Match existing style:**
**Testing mode** (when user asks to "see what would change"):
Output a text summary describing:
**Execution mode** (when running as automation):
1. Create a descriptive branch name (e.g., `docs/auto-update-YYYYMMDD`)
2. Make documentation changes to appropriate files
3. Push branch and create PR with description linking to relevant commits:
When source code and documentation are in separate repositories, identify changes in the source repo, then switch to the docs repo and follow the workflow above. Reference source commits in the PR description.
Portable, source-controlled configuration for AI coding assistants. my-ai-tools installs one consistent set of agent guidelines, skills, commands, hooks, MCP servers, and tool settings across supported AI coding assistants.
Use explicit human checkpoints for architecture, security, rollout, or operational decisions.
Record architecture decisions with ADRs — captures why, alternatives considered, and consequences
Use when monitoring an open GitHub PR for CI failures, review feedback, mergeability, and safe retries or fixes.
Inspect history and architecture for hidden constraints before risky cross-cutting changes.
Build an interactive report or experiment when the user asks to explore model capabilities.
Audit a diff for structural maintainability and unnecessary complexity.