agentleFS
Cassandra-CollectiveCassandra-Collective/Ephesus/.claude/skills/build-package/SKILL.md

build-package

Skill2 starsChanged 3 months agoMITView on GitHub

Execute the next Ephesus work package from BUILD-PROMPT.md — resume from docs/PROGRESS.md, run the READ→PLAN→BUILD→TEST→PROVE→COMMIT→REPORT loop, and never proceed on red checks. Use when asked to continue building Ephesus, implement a milestone/package, or "keep going".

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. mertefesensoy/Ephesus★ 2100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Read BUILD-PROMPT.md in full.

    line 8
  2. Distinctive:

    Read only the docs BUILD-PROMPT §2 maps to this package.

    line 15

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Build the next work package

  1. Read BUILD-PROMPT.md in full. It is the contract for this session; its §3 invariants and §7 prohibitions override any instinct you have.
  2. Open docs/PROGRESS.md and read its Resume here block: the package to build is the one it names, and where it says the build waits on the Architect, ask him first (AskUserQuestion) and stop on anything but a yes. If the milestone has no package list yet, derive one from its section of docs/IMPLEMENTATION.md and write it into PROGRESS.md before coding.
  3. Read only the docs BUILD-PROMPT §2 maps to this package.
  4. Execute the working loop (BUILD-PROMPT §4). Hard rules:
    • npm run typecheck && npm run lint && node scripts/check-invariants.cjs && npm run test:coverage && node scripts/check-coverage.cjs green before any commit — BUILD-PROMPT §4's TEST line (since M8.0 the suite runs once, under coverage, and the seam rule's two checks run with it).
    • Tests owed by the package (TEST-STRATEGY §2 mapping) are part of the package.
    • Evidence (command + observed result) goes in the commit description.
    • 3 failed distinct attempts on a blocker → stop, record it, report (don't hack around).
  5. Tick the package in docs/PROGRESS.md with a one-line evidence note and update the Resume here block in the same commit; log any minor choices in docs/DECISIONS-LOG.md; queue must-ask questions for the Architect.
  6. End with the session report format from BUILD-PROMPT §9.

Package too big mid-flight (> ~10 files)? Split it in PROGRESS.md and do the first half properly rather than all of it loosely.

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.