Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Docs Drift

ASecurity

Use when code changes may have made documentation stale, or the user asks to check/update docs after editing source. Triggers: "docs out of date", "stale docs", "update the README", "docs drift", "did I miss a doc", "keep docs in sync", "changelog", "document this change". Not for writing new docs from scratch — for detecting and fixing drift caused by code changes.

2 stars
0 votes
0 copies
0 views
Added 10/1/2026
ai-agentsgitapidocumentation

Works with

cliapi

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 10/1/2026

$npx -y skills add matthews-wong/claude-code-plugins --skill docs-drift --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Docs Drift?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Docs Drift
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/matthews-wong-docs-drift/badge)](https://www.skillsdirectory.com/skills/matthews-wong-docs-drift)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: docs-drift
description: >
  Use when code changes may have made documentation stale, or the user asks to
  check/update docs after editing source. Triggers: "docs out of date", "stale
  docs", "update the README", "docs drift", "did I miss a doc", "keep docs in
  sync", "changelog", "document this change". Not for writing new docs from
  scratch — for detecting and fixing drift caused by code changes.
---

# Docs Drift Detection

Find documentation that code changes have quietly invalidated, then propose the
minimal edits to make it true again. A stale doc is worse than no doc — it
misleads with authority.

## Workflow

1. Get the changed source files (git diff / status).
2. Run `sh "${CLAUDE_PLUGIN_ROOT}/scripts/docs-scan.sh"` for leads.
3. For each change, map it to the docs it affects (signals below).
4. Grep the docs for the changed symbols/flags/values; confirm real mismatches.
5. Report stale docs with reasons + concrete edits; note what you verified as
   still correct.

## Drift signal catalog

Map a code change to the docs it likely breaks:

- **Public signature change** (function/method/class/endpoint params, return
  type) -> API reference, usage examples, docstrings, type stubs.
- **CLI change** (added/removed/renamed flag or subcommand) -> README usage,
  quickstart, embedded `--help` output, man pages.
- **Config change** (env var, config key, default) -> configuration docs,
  `.env.example`, Helm/compose samples, settings reference.
- **Dependency/version change** -> install instructions, requirements,
  compatibility matrix, badges.
- **Behavior/default change** -> any prose describing that behavior; tutorials.
- **New feature/module** -> README feature list, docs nav/index, CHANGELOG,
  migration notes.
- **Removed/deprecated code** -> remove or mark deprecated in docs; add to
  CHANGELOG and migration guide.

The full checklist per doc type (README, API ref, CHANGELOG, tutorials,
architecture docs) is in `./reference/doc-map.md`.

## Judgment rules

- Flag only genuine mismatches you can point to. No speculative "you might want
  to mention this."
- Match the project's existing doc style and structure; do not impose new
  conventions.
- Prefer surgical edits over rewrites. Keep the author's voice.
- CHANGELOG entries follow the project's format (e.g. Keep a Changelog) — see
  the reference.
- If nothing is stale, say so; a clean bill is a valid, useful result.

Attribution

matthews-wongmatthews-wong
View sourceSee grades on GitHubMore from matthews-wong →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →