agentleFS
preetamnathpreetamnath/agent-skills/skills/triage/SKILL.md

triage

Skill4 starsChanged 7 months agoMITView on GitHub

Verify a panel's findings against their artifact: each gets a consider / skip verdict and a confidence. TRIGGER when: a fan-out skill needs its findings verified before walking them with the user; user says 'triage these findings', 'verify which of these are real', 'which are worth acting on'.

189 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use writing-beats, setup-matt-pocock-skills and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • LesaniSkill

    writing-beats

    Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.

    Also in 66 projects that use this

  • GoogleSkill

    setup-matt-pocock-skills

    Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

    Also in 167 projects that use this

  • liufeng1976Skill

    setup-ts-deep-modules

    Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

    Also in 42 projects that use this

  • SethGammonSkill

    ascii-diagram

    Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.

    Also in 4 projects that use this

  • simo97Skill

    migrate-to-shoehorn

    Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.

    Also in 68 projects that use this

  • LesaniSkill

    writing-shape

    Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.

    Also in 63 projects that use this

  • +1 more from Lesani

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 176 edited versions we read keep these.

  • 1

    Distinctive

    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:

    Verify a list of findings: fan out independent checkers, each judging whether a finding is real and worth acting on, and returning a …

    line 8
  2. Very specific:

    not real, or real but trivial → skip

    line 27

“Common” is measured: kept by at least 6 in 10 of the 176 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

Triage

Verify a list of findings: fan out independent checkers, each judging whether a finding is real and worth acting on, and returning a per-finding verdict and a confidence. The caller decides what to do with them.

Instructions

Step 1 — Receive the inputs

The caller passes: the findings (each with an id and its claim) and the artifact path(s). If the findings or the artifact are missing, ask before proceeding.

Step 2 — Batch the findings and fan out

  • Batch: 1–3 findings per checker, sized by complexity (more than 3 degrades independence and quality) — a finding needing deep ground-truth checking goes alone; simple or closely-related ones can share.
  • Dispatch: one general-purpose subagent per batch, in parallel — cap ~6 concurrent and wave the rest.
  • Each checker gets only: its finding(s), the artifact path(s), the return contract below, and the instruction not to fan out checkers of its own.

For each finding it holds, the checker reads the artifact fresh and:

  • real? — is the finding correct, or a misread? Ground it in the artifact.
  • material? — does it warrant the user's attention?
  • maps the two axes to one verdict:
    • real AND material → consider
    • not real, or real but trivial → skip
    • can't be checked against the given artifact (claim rests on runtime behavior or files outside it) → skip with reason unverifiable
  • returns: verdict, adjusted_confidence (0.00–1.00, the checker's fresh score), one-line reason — on a skip, say which: false positive, real-but-trivial, or unverifiable.

Step 3 — Return output conforming to the Output Schema below.

Collect the checkers' results verbatim — don't re-judge or override a verdict.

Rules

  • Clean room. A checker didn't produce the finding it judges — don't pass it the panel's reasoning, prior score, or your expected verdict.
  • Score from the read, don't re-rank by fiat. Verdict and confidence come from the checker's read, not the caller's preference.
  • Bar-free. Judge consider/skip on the finding's own merits; the caller owns any confidence bar and applies it after.

Output Schema

TriageResult {
  verdicts: [
    {
      finding_id: string,
      verdict: "consider" | "skip",
      adjusted_confidence: number,   // 0.00–1.00, the checker's fresh score
      reason: string                 // one line; on skip: false positive, real-but-trivial, or unverifiable
    }
  ]
}

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.