agentleFS
Sign inStart free
iadr-deviadr-dev/greenlight/skills/approve/SKILL.md

approve

Skill2 starsChanged 5 days agoMITView on GitHub

Approve or reject the rules or the examples of a feature. Only the person can run this by typing /greenlight:approve FEAT-n rules|examples (add "reject <reason>" to reject); the AI never invokes it.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. drobins25/craft★ 73same name
    2. tornikebolokadze1-cyber/agent-foundation-kit★ 6same name
    3. synaptiai/bdsk★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository6 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Look for a line starting with greenlight approval: in the context of this prompt.

    line 15
  2. Distinctive:

    If it says the approval was recorded, run the check below and tell the person the result.

    line 16
  3. Very specific:

    If it says NOT recorded, repeat its reason and what has to happen first.

    line 17
  4. Distinctive:

    Check where the feature stands and show the output unchanged:

    line 18
  5. Very specific:

    If there is no greenlight approval: line at all, hooks are not active in this session.

    line 28

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

greenlight approve

The person typed /greenlight:approve $ARGUMENTS.

The approval itself is recorded by a hook before you see this prompt, from exactly what the person typed. You do not record it and you cannot: never run bdd approve ... --self-reported or --auto to stand in for the person when the hook has run.

  1. Look for a line starting with greenlight approval: in the context of this prompt.
    • If it says the approval was recorded, run the check below and tell the person the result.
    • If it says NOT recorded, repeat its reason and what has to happen first. Do not retry.

  2. Check where the feature stands and show the output unchanged:

    "${CLAUDE_PLUGIN_ROOT}/tools/bdd/bdd" approve <FEAT-n> --verify
"${CLAUDE_PLUGIN_ROOT}/tools/bdd/bdd" state show <FEAT-n>

    An approval shows pending until Claude Code has written the person's prompt to the session transcript; run the check again after the next turn if it does. An approval that is invalid or unverifiable does not count: tell the person to type the command again themselves.

  3. If there is no greenlight approval: line at all, hooks are not active in this session. Say so. In a project that allows it (enforcement = "soft", or hooks never having run), ask the person to confirm in plain words, and only then record their answer with bdd approve <FEAT-n> <gate> --self-reported. The command refuses when the project requires hard enforcement; relay that refusal and do not look for another way.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free