agentleFS
Sign inStart free
kvantatechkvantatech/RedLine/.github/skills/func-verdict/SKILL.md

func-verdict

Skill1 starsChanged 3 months agoMITView on GitHub

Type: skill (deterministic, no model call — thin wrapper over verdict.mjs) · Used by: func-run-one, corroborate-2-sources · Status: LIVE (2026-07-08) Run the script — no judgment: Verdict rule (hard rule 6, functional edition): green requires failed == 0 and passed == tests_total — every test actually passed. Anything else → red: a real failure (failed > 0), or an incomplete run where tests were skipped (passed < tests_total, e.g. a beforeAll error). A suite where nothing failed but nothing passed…

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. Distinctive:

    Run the script — no judgment:

    line 10
  2. Very specific:

    No baselines for functional suites — by design (see baselines/README.md).

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

func-verdict

Map a functional contract to green | red — the two-verdict rule, pass/fail edition.

Type: skill (deterministic, no model call — thin wrapper over verdict.mjs) · Used by: func-run-one, corroborate-2-sources · Status: LIVE (2026-07-08)

Prompt

Run the script — no judgment:

node .github/skills/func-verdict/verdict.mjs reports/<run_id>/contract.json <team> reports/<run_id>/verdict.json
  • Exit 0 → verdict written (both green and red exit 0 — branch on overall_verdict in the file).
  • Exit 1 → FAILED (malformed or zero-test contract). Report FAILED — <reason>, STOP.

Verdict rule (hard rule 6, functional edition): green requires failed == 0 and passed == tests_total — every test actually passed. Anything else → red: a real failure (failed > 0), or an incomplete run where tests were skipped (passed < tests_total, e.g. a beforeAll error). A suite where nothing failed but nothing passed is NOT an all-clear. There is no amber, no threshold, no baseline file — k6 owns performance numbers.

Tools

Bash (node), Read — no MCP, no model calls.

Data

  • Reads: reports/<run_id>/contract.json
  • Writes: reports/<run_id>/verdict.json

Hard rules

  1. No baselines for functional suites — by design (see baselines/README.md).
  2. Fails closed on malformed/zero-test contracts.
  3. Behavior check: powershell -File tests/func-contract-check.ps1.

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