agentleFS
ai-analyst-labai-analyst-lab/ai-analyst/.claude/skills/score-analysis/SKILL.md

score-analysis

Skill304 starsChanged 2 months agoMITView on GitHub

Decide whether the evidence for one analysis supports acting, investigating, abstaining, or marking the review incomplete. Use after reliability, provenance, query, or triangulation checks.

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:

    Keep the evidence dimensions separate:

    line 8
  2. Very specific:

    Use helpers.evals.scorecard.decide.

    line 21

≈ “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

Decide whether to use one analysis

Keep the evidence dimensions separate:

  • task and metric meaning;
  • source and freshness;
  • execution and query checks;
  • repeated behavior;
  • independent analytical support;
  • interpretation;
  • safety and authorization; and
  • unresolved evidence.

Mark each criterion as pass, fail, flag, unknown, error, blocked, or not applicable. Mark it as blocking when failure makes the analysis unsafe to use for the stated decision. Otherwise mark it diagnostic.

Use helpers.evals.scorecard.decide. Never average the criteria into one confidence number. A clean receipt cannot cancel a wrong result. A stable result cannot substitute for ground truth.

Return one recommendation:

  • act when all required evidence passes for the stated consequence;
  • investigate when a specific unresolved issue could change the answer;
  • abstain when a blocking correctness or safety criterion fails; or
  • incomplete when too little evidence exists to decide.

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.