agentleFS
Ahsan-ireAhsan-ire/rag-pipeline-v1/.claude/skills/phase-gate/SKILL.md

phase-gate

Skill0 starsChanged 36 days agoMITView on GitHub

End-of-phase quality gate for the RAG pipeline — full tests, pressure-test subagent, code review, git hygiene, decisions.md check. Produces a PASS/FAIL evidence report.

  • Reads credentials

5 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions5 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 5

    1. acprk/crypto-research-agents★ 15same name
    2. andreymudri/claude-teammates★ 3same name
    3. andreymudri/fleetmates★ 3same name
    4. acgs-ai/ACGS★ 2same name
    5. huguryildiz/ALETHEIA★ 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 repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 0

    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:

    Read IMPLEMENTATION_PLAN.md and extract Phase $ARGUMENTS's acceptance criteria verbatim.

    line 17
  2. Very specific:

    Run the full test suite: .venv/bin/python -m pytest tests/ -q (fall back to python -m pytest tests/ -q if no venv).

    line 18

“Common” is measured: kept by at least 6 in 10 of the 5 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

Current state

!git status --short

The gate

You are running the quality gate for Phase $ARGUMENTS of this repo. Collect evidence first; fix nothing during the gate.

  1. Read IMPLEMENTATION_PLAN.md and extract Phase $ARGUMENTS's acceptance criteria verbatim. Read the current-phase line at the top of docs/decisions.md.
  2. Run the full test suite: .venv/bin/python -m pytest tests/ -q (fall back to python -m pytest tests/ -q if no venv). The whole suite must pass. Paste the output.
  3. Spawn the pressure-tester subagent (Agent tool), passing: the phase number, the acceptance criteria verbatim, and a reminder to return the per-criterion table with pasted evidence.
  4. Invoke the built-in code-review skill (Skill tool) on the current diff at high effort. 4b. Off-limits for every step and every subagent (D72): .env, data/, chroma_db*/, held-out eval files, eval/private/sealed/, Tutorial_Docs_for_review/ and ~/.local/state/claudecode/sealed_sp/. Sealed criteria are evidenced by scripts/sealed_tool.py counts only.
  5. Git hygiene: confirm git status --porcelain shows nothing matching data/, *.pdf, .env, chroma_db/, chroma_db_arm_*/, eval/bakeoff/, or logs/ (their presence means .gitignore failed).
  6. Confirm docs/decisions.md contains entries covering this phase's design choices. If missing, draft the entry and ask the user before appending.
  7. Assemble the gate report:
    • Acceptance criterion table (criterion → PASS/FAIL → evidence)
    • Code-review findings
    • Pressure-tester defects
    • Hygiene result and decisions.md status
    • GATE: PASS or FAIL
    • On PASS: print a suggested commit message. On FAIL: a numbered fix list, then wait for user approval before fixing anything.

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.