agentleFS
Avarok-CybersecurityAvarok-Cybersecurity/atlas/.claude/skills/measurement-artifact-oracle/SKILL.md

measurement-artifact-oracle

Skill724 starsChanged 2 months agoAGPL-3.0View on GitHub

M.A.O. — the MEASUREMENT ARTIFACT ORACLE (Observation Reliability And Claim-Legitimacy Examiner). Adjudicate whether a benchmarked number is REAL or a MEASUREMENT ARTIFACT, before it is believed, quoted, ratcheted into a gate, put on a chart, or shown to anyone. Invoke whenever reading, comparing, or acting on measured values: tok/s, throughput, TTFT, TPOT, ITL, latency, wall time, J/token, tokens per watt, energy, power draw, watts, cost per token, accuracy, BFCL, acceptance rate, jitter, stability, p50/p90/p99. Invoke on any claim of the form faster, slower, cheaper, more efficient, regression, speedup, win, beats, N times better, no change, or inert. Invoke before setting a floor or ceiling from data, before comparing two engines or two commits, and whenever a number is surprising, too good, too flat, or the wrong sign. Takes JSONL of metrics with pointers to the code that measured them plus each metric's intent; returns an ARTIFACT / SOUND / UNDETERMINED verdict per metric with the failure class, the evidence, and the experiment that would settle it.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

Licensed with conditions — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.

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.