agentleFS
kiku-jwkiku-jw/codex-skills/triage-finding/SKILL.md

triage-finding

Skill0 starsChanged 4 months agoMITView on GitHub

Triage an external finding such as a post, article, repo, screenshot, video, note, or link and decide whether it matters now. Use when the user wants a verdict, not just a summary.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not use when: the user only wants a raw summary and no verdict or routing decision.

    line 10
  2. Distinctive:

    Check for local duplicates or existing use before recommending action, then map the finding to current work, repos, or issue state.

    line 18
  3. Distinctive:

    Do not install tools or create files unless the user explicitly asked for that step.

    line 25

≈ “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

Triage Finding

Metadata

  • Trigger when: the input is an outside finding and the real question is whether it deserves action in the current context.
  • Do not use when: the user only wants a raw summary and no verdict or routing decision.

Skill Purpose

Inspect an external finding against the primary source, local reality, and current work so the result is a usable verdict instead of yet another pile of interesting links.

Instructions

  1. Inspect the primary source first and fact-check the main claim. Use ~/.codex/skills/triage-finding/references/source-handling.md when you need source-type handling rules.
  2. Check for local duplicates or existing use before recommending action, then map the finding to current work, repos, or issue state. If it is already installed or already in use, say that before anything else.
  3. Give exactly one primary verdict and the smallest useful next action. Use ~/.codex/skills/triage-finding/references/verdicts.md only when you need the verdict frame.

Non-Negotiable Acceptance Criteria

  • Primary source truth beats repost or commentary.
  • Weak findings do not get stretched into fake relevance.
  • The answer names whether the finding is already installed, duplicated, or already in use.
  • Do not install tools or create files unless the user explicitly asked for that step.

Output

  • A structured verdict with What is this, Fact-check notes, Duplicate check, Where it applies, Recommendation, and Smallest next step.
  • For multiple findings, a short summary table of verdicts.
  • One clear primary recommendation: apply now, save for later, or not relevant.
  • Next skill options (only if needed): $tool-scout — research the broader external landscape around the finding; $skill-creator — turn a reusable workflow insight into a skill; $product-council — stress-test a finding that could change direction; $adr-log — record a finding that has turned into a durable decision.

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.