agentleFS
Sign inStart free
agoopintsaiagoopintsai/shipright/skills/where/SKILL.md

where

Skill2 starsChanged 16 days agoApache-2.0View on GitHub

One sentence on where you are: step, gates, brain, whose move

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. ARCASSystems/FounderOS★ 7same name
    2. ARYN26/you-are-here★ 1same name
    3. bingelp/skills★ 0same name
    4. Emin4ik/StateNest★ 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 repository7 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Run python3 "${CLAUDE_PLUGIN_ROOT}/scripts/shipright_hooks.py" status and read shipright.yaml in the project root.

    line 12
  2. Very specific:

    not configured: no valid shipright.yaml.

    line 20
  3. Distinctive:

    If evidence is mixed, pick the earliest plausible step and say what you could not verify.

    line 27

“Common” is measured: kept by at least 6 in 10 of the 4 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

/shipright:where

Answer "where am I?" from evidence, not memory. Do not ask the user anything and do not change anything.

Gather (read-only)

  1. Run python3 "${CLAUDE_PLUGIN_ROOT}/scripts/shipright_hooks.py" status and read shipright.yaml in the project root. Missing file means "not configured". Unparsable file or missing brain path means broken: treat as "not configured" and say run /shipright:setup.
  2. Current branch: git branch --show-current.
  3. Consensus doc: any file under <brain>/products/<product>/decisions/ or <brain>/shared/decisions/ whose frontmatter branches: lists the current branch (the same scan the red-zone gate uses). Note its path, or none.
  4. Pull request: if gh is available, run gh pr view --json state,reviewDecision,url,isDraft. If gh is missing or fails, skip and report "none".
  5. Last line of <brain>/products/<product>/log.md (the last non-empty line), or "nothing yet".

Pick the step by evidence

  • not configured: no valid shipright.yaml.
  • planning (no consensus yet): configured, no consensus doc covers the branch, no PR.
  • spec review (PR open, awaiting approval): PR open, not approved, and the PR contains only the consensus doc or spec (no implementation yet).
  • implementing: consensus doc covers the branch; no PR, or the PR is a draft.
  • code review (PR open after implementation): PR open, not approved, and it contains implementation changes.
  • ready to ship (approved): PR open and reviewDecision is APPROVED.

If evidence is mixed, pick the earliest plausible step and say what you could not verify.

Answer in exactly this shape, nothing else

You are at <step>: <state>.
- Gates: <on|off> (<mode, or "no mode">), tier <file|commit> (from `gate:` in shipright.yaml, default commit)
- Consensus: <doc path or none>
- PR: <url + review state, or none>
- Brain last recorded: <log line or "nothing yet">
Next move: <whose> - <what>

<state> is one short clause (for example "branch feat/x has a signed decision, no PR yet"). Gates are "on" when the config is valid, "off" otherwise. "Next move" names the human or the AI and one action, for example "Human - run /shipright:grill" or "Human - approve the PR on GitHub".

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