agentleFS
nearmapnearmap/shipyard/skills/help/SKILL.md

help

Skill1 starsChanged 21 days agoMITView on GitHub

Answer questions about Shipyard itself — commands, SY_*/ACLI_* config knobs, which model an agent uses, workflow behavior, diagnosis recipes — by reading the plugin's own docs and citing the source. Never reads the tracker or the target repo's code.

76 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use create-stories, story-done and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • lilangMaxSkill

    create-stories

    Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.

    Also in 9 projects that use this

  • lilangMaxSkill

    story-done

    End-of-story completion review. Reads the story file, verifies each acceptance criterion against the implementation, checks for GDD/ADR deviations, prompts code review, updates story status to Complete, and surfaces the next ready story from the sprint.

    Also in 9 projects that use this

  • +10 more from lilangMax

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 57 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:

    Every read and grep target below is rooted at ${CLAUDE_PLUGIN_ROOT} — a normal (non---plugin-dir) install runs commands with the *user's …

    line 16
  2. Very specific:

    If none of the above cover it, grep ${CLAUDE_PLUGIN_ROOT}/skills/ and ${CLAUDE_PLUGIN_ROOT}/agents/ for the topic before giving up.

    line 24
  3. Distinctive:

    If nothing in the plugin's files answers it, say so plainly and point at the nearest real doc — never infer or fabricate a variable name, …

    line 30

“Common” is measured: kept by at least 6 in 10 of the 57 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

Answer a question about how Shipyard (this plugin) works. $ARGUMENTS is the question; if empty, say what this can answer and give two or three example questions instead of guessing at intent.

This skill inherits caller model/effort. It only reads the plugin's own bundled files below — never the tracker, never the target repo's code or its board. A question about the target codebase or a ticket belongs to /sy:explain or the tracker skill, not this one.

Sources, read only what the question needs

Every read and grep target below is rooted at ${CLAUDE_PLUGIN_ROOT} — a normal (non---plugin-dir) install runs commands with the user's repo as cwd, so a bare relative path silently reads nothing or the wrong file.

  1. ${CLAUDE_PLUGIN_ROOT}/docs/configuration.md — every setting: layer, default, required?, meaning. Authoritative for "where do I configure X" / "what setting controls Y". For what a given repo actually resolves to, call the show_config tool rather than quoting a default.
  2. ${CLAUDE_PLUGIN_ROOT}/agent-guide.md — concepts, install/config walkthrough, Diagnosis recipes (symptom → cause → fix).
  3. ${CLAUDE_PLUGIN_ROOT}/README.md, ${CLAUDE_PLUGIN_ROOT}/docs/usage.md, ${CLAUDE_PLUGIN_ROOT}/docs/installation.md, ${CLAUDE_PLUGIN_ROOT}/docs/github-setup.md — the loop, day-to-day usage, one-time setup.
  4. ${CLAUDE_PLUGIN_ROOT}/.out-of-scope/ — ideas Shipyard deliberately declined, one file per concept with its reason. Check it for any "why doesn't Shipyard do X" or "can it do X" question before answering that X is missing.
  5. The specific ${CLAUDE_PLUGIN_ROOT}/skills/<name>/SKILL.md or ${CLAUDE_PLUGIN_ROOT}/agents/<name>.md the question names or implies — read it directly rather than guessing at its behavior.

If none of the above cover it, grep ${CLAUDE_PLUGIN_ROOT}/skills/ and ${CLAUDE_PLUGIN_ROOT}/agents/ for the topic before giving up.

Answer

State the answer first, then cite it as a repo-relative file:line (e.g. docs/configuration.md:12) — that's what the user can actually open, even though the read above went through ${CLAUDE_PLUGIN_ROOT}. If the question spans a setting and where it's consumed — "what model does gate use" — give both: the setting (models.agents.gate.model, docs/configuration.md) and the consumer (skills/ship/references/immutable-gate.md), reading the actual current line rather than assuming one — the file shifts over time and a pinned line number is a snapshot, not ground truth. For a "what is my config actually set to" question, prefer calling the show_config tool, which reports each value with the layer it came from, over quoting a default from the docs.

If nothing in the plugin's files answers it, say so plainly and point at the nearest real doc — never infer or fabricate a variable name, default, or behavior.

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.