Community寫作與編輯github.com

Akshaysanthosh/docs-drift-check

Codex skill and local plugin for spotting likely documentation drift.

docs-drift-check 是什麼?

docs-drift-check is a Codex agent skill that codex skill and local plugin for spotting likely documentation drift.

相容平台~Claude CodeCodex CLI~Cursor
npx skills add Akshaysanthosh/docs-drift-check

Installed? Explore more 寫作與編輯 skills: steipete/notion, affaan-m/seo, affaan-m/brand-voice · View all 6 →

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

Docs Drift Check

Determine whether a branch or diff likely created documentation drift, then point to the exact docs files and terms worth reviewing. This skill should bias toward concrete evidence from the diff, not broad speculation.

Use This Skill When

  • The user asks whether a branch, PR, or local change likely needs doc updates.
  • The diff changes public-facing behavior such as API routes, CLI flags, env vars, config keys, setup steps, or file/module names that docs may reference.
  • The task is to review README, docs/, examples/, onboarding, or setup documentation for drift.

Do not use this skill for pure styling changes, test-only changes, or clearly internal refactors with no visible behavior change.

Quick Start

  1. Run the helper: bash .agents/skills/docs-drift-check/scripts/docs_drift_check.sh [base-ref]
  2. Read the highest-signal sections first:
    • Potential renames
    • Likely env var changes
    • Likely CLI flag changes
    • Likely route or endpoint changes
    • Likely config changes
  3. Inspect the most likely docs targets:
    • README.md
    • docs/
    • examples/
    • setup or onboarding docs near the affected feature
  4. Return a short result with:
    • risk level: low, medium, or high
    • concrete evidence from the diff
    • likely impacted docs files
    • recommended edits or patch plan

Workflow

1. Establish the comparison

  • Prefer a user-provided base ref.
  • If none is provided, the helper defaults to main.
  • If the base ref is missing, say so clearly and ask for the correct branch or compare target.

2. Identify doc-sensitive changes

Focus on high-signal change types:

  • env vars
  • CLI flags and commands
  • API routes or endpoints
  • config keys
  • renamed files or modules
  • setup or onboarding steps

Use the helper script for a deterministic first pass, then inspect the diff manually if needed.

3. Compare the code changes against docs

  • Search docs for old and new names, paths, flags, routes, and config terms.
  • Prefer docs closest to the changed area before scanning the full repo.
  • Read references/heuristics.md when you need the signal rubric or output shape.

4. Classify the outcome

  • low: docs likely OK, or only weak signals with no stale references found
  • medium: possible drift, or strong public-surface changes without confirmed stale docs
  • high: likely or confirmed drift with specific stale terms, paths, or missing instructions

5. Keep the output concise

Use this shape:

  1. Risk level
  2. Why
  3. Impacted docs files
  4. Recommended edits

Rules

  • Prefer deterministic evidence from the diff before semantic guesses.
  • Do not claim confirmed drift unless you can point to a concrete stale reference, missing doc update, or renamed path.
  • If evidence is partial, say possible drift instead of overstating certainty.
  • Ignore formatting-only, comment-only, and test-only changes unless they alter user-facing behavior.
  • Keep the result short and actionable.

相關技能

steipete/notion

Notion CLI/API for pages, Markdown content, data sources, files, comments, search, Workers, and raw API calls.

community

affaan-m/seo

Audit, plan, and implement SEO improvements across technical SEO, on-page optimization, structured data, Core Web Vitals, and content strategy. Use when the user wants better search visibility, SEO remediation, schema markup, sitemap/robots work, or keyword mapping.

community

affaan-m/brand-voice

Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants voice consistency without generic AI writing tropes.

community

affaan-m/crosspost

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.

community

affaan-m/x-api

X/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.

community

affaan-m/content-engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

community