Keeps project documentation in sync with codebase changes by running incremental updates.

Install

mkdir -p .claude/skills/are-update && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11976" && unzip -o skill.zip -d .claude/skills/are-update && rm skill.zip

Installs to .claude/skills/are-update

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.

Incrementally update documentation for changed files
52 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Read the current version of agents-reverse-engineer
  • Run the update command in the background
  • Monitor progress by polling log files
  • Summarize updated, unchanged, and orphaned files
  • Include staged but uncommitted changes with `--uncommitted`
  • Show what would be updated without writing with `--dry-run`

How it works

The skill reads the current version of agents-reverse-engineer, runs the update command in the background, and monitors its progress by polling log files until completion, then summarizes the changes.

Inputs & outputs

You give it
Changed files in the project
You get back
Updated documentation and a summary of changes

When to use are-update

  • Updating docs after a feature merge
  • Running documentation sync in a CI pipeline
  • Identifying orphaned documentation

About this skill

Update documentation for files that changed since last run.

<execution> Run the update command in the background and monitor progress in real time.

Steps

  1. Read version: Read .claude/ARE-VERSION → store as $VERSION. Show the user: agents-reverse-engineer v$VERSION

  2. Run the update command in the background using run_in_background: true:

    npx agents-reverse-engineer@$VERSION update --backend claude $ARGUMENTS
    
  3. Monitor progress by polling the latest progress log:

    • Wait ~15 seconds (use sleep 15 in Bash), then use Glob to find the latest .agents-reverse-engineer/progress-*.log file, and Read it (use the offset parameter to read only the last ~20 lines for long files)
    • Show the user a brief progress update (e.g. "12/30 files updated, ~5m remaining")
    • Check whether the background task has completed using TaskOutput with block: false
    • Repeat until the background task finishes
    • Important: Keep polling even if no progress log exists yet (the command takes a few seconds to start writing)
  4. On completion, read the full background task output and summarize:

    • Files updated
    • Files unchanged
    • Any orphaned docs cleaned up

Options:

  • --uncommitted: Include staged but uncommitted changes
  • --dry-run: Show what would be updated without writing
  • --eval: Namespace output by backend.model for side-by-side comparison
  • --concurrency N: Control number of parallel AI calls (default: auto)
  • --fail-fast: Stop on first file analysis failure
  • --debug: Show AI prompts and backend details
  • --trace: Enable concurrency tracing to .agents-reverse-engineer/traces/
</execution>

When not to use it

  • When a full, non-incremental documentation update is desired
  • When real-time progress monitoring is not needed
  • When the update command should not run in the background

Limitations

  • Requires `npx agents-reverse-engineer` to be available
  • Progress monitoring relies on polling log files
  • Output is summarized after background task completion

How it compares

This skill incrementally updates documentation for changed files in the background with real-time progress monitoring, unlike a manual or full documentation regeneration.

Compared to similar skills

are-update side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
are-update (this skill)05moReviewIntermediate
architecture-decision-records545moReviewBeginner
meeting-minutes416moNo flagsBeginner
docs-write226moNo flagsBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry