agentleFS
Sign inStart free
aezizhuaezizhu/hyperworkflows/skills/tricolor-reporting/SKILL.md

tricolor-reporting

Skill0 starsChanged 4 months agoMITView on GitHub

Use when rendering any Hyperworkflows result to a human - the mandatory report format with verified/unverified/quarantined+grey buckets, coverage arithmetic, and evidence links.

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:

    Every Hyperworkflows deliverable is a tricolor report.

    line 8
  2. Distinctive:

    Every claim a human might act on carries its evidence path.

    line 18

≈ “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

Tricolor Reporting

Every Hyperworkflows deliverable is a tricolor report. No other final format exists.

The three buckets (constitution C4):

  1. VERIFIED — machine-adjudicated green. Each item links its verdicts/*.json (raw exit codes) and states its depth (D0 acceptance / D1 attack-survived / D2 mutation-hardened / D3 differential / D4 bench-clean).
  2. DONE-UNVERIFIED — produced but not machine-verified (no oracle reachable, verification skipped with a logged reason). Never counted as verified. Say why, per item.
  3. QUARANTINED + GREY — failed units with their failure signature and last failing command; grey units with their infeasible_reason.

Hard rules:

  • Coverage arithmetic is shown: verified / total, with grey and quarantined counted in total. A denominator that silently shrinks is lying.
  • A failed unit is NEVER aggregated into a success count. A red suite is never "mostly passing".
  • Every claim a human might act on carries its evidence path. The footer always includes the one-line recheck command and the model-family residual-risk note.
  • Plain language for failures: the concrete failing command and exit code, what it means, and what the human can do next — never internal jargon.
  • Timestamps in Asia/Singapore.

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