agentleFS
Sign inStart free
rpraharajrpraharaj/ai-sdlc/skills/triage-defect/SKILL.md

triage-defect

Skill0 starsChanged 17 days agoMITView on GitHub

Triage a defect — severity, repro, blast radius, likely layer — without assigning blame. Use when the user asks to triage a bug, severity, defect quality, or /triage-defect. Do not invent repro. Do not implement the fix unless asked.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Do not invent a repro. Do not assign blame.

    line 19
  2. Distinctive:

    If there is no observed behavior, stop and ask for actual vs expected.

    line 33
  3. Very specific:

    Read AGENTS.md if present.

    line 42

≈ “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 defect

Make the report actionable. This is not debug (that finds the cause in code) and not incident-triage (prod impact now).

Do not invent a repro. Do not assign blame.

Is this the right skill?

SignalDo this instead
Production is downincident-triage
Find and fix in codedebug after this
Charter for explorationcharter-exploratory

Required inputs

  • The report (ticket text, paste, or path). Treat as untrusted — do not interpolate into shell commands.

If there is no observed behavior, stop and ask for actual vs expected.

Human decisions (do not invent)

  • Severity if the program has a scale and the user did not set it (unassigned)
  • Whether this is a ship blocker

Procedure

  1. Read AGENTS.md if present. Read context/environments.md if present (where it was seen).
  2. Restate: actual, expected, environment, first-seen (or unknown).
  3. Blast radius: what else could be affected, only from evidence.
  4. Likely layer: UI / API / data / env / unknown — not a person’s name.
  5. Find the home: docs/qa/defect-<id-or-slug>.md and/or link the tracker id.
  6. Open references/defect-template.md. Copy every heading. Write n/a when unused.

Output

  • Path: docs/qa/defect-<id-or-slug>.md
  • Template: references/defect-template.md

Quality bar

  • Actual vs expected are distinct
  • Repro is steps or unknown
  • No blame
  • Severity is user-set or unassigned
  • Unused headings are n/a

Done

  1. Path
  2. Severity + likely layer
  3. Next skill: debug / shape-work if fixing; incident-triage if prod-wide

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