agentleFS
matheusPavanelimatheusPavaneli/workbench/skills/triage-task/SKILL.md

triage-task

Skill1 starsChanged 44 days agoMITView on GitHub

Reads a ticket from Jira or Azure DevOps and writes .workflow/<KEY>/triage.json. Use when asked what to work on, to pick up a ticket by key, or to understand its description, comments and blocking links.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 2 are distinctive, and 5 are 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.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All tracker access goes through one command.

    line 8
  2. Very specific:

    No tracker in this repo? task new "title" --type bug|feature|chore|support records it in the local backlog and everything downstream works …

    line 24
  3. Very specific:

    Only local contexts accept it.

    line 26
  4. Very specific:

    Use --depth 0 when the ticket is self-contained and links do not matter.

    line 35
  5. Very specific:

    Use --depth 2 only when a blocker or a parent decides the approach.

    line 36
  6. Very specific:

    Check _unmapped and _truncated: if present. _unmapped means the tracker had a link type or field this version does not model — say so …

    line 51
  7. Distinctive:

    Report gaps before planning: If the ticket lacks acceptance criteria, a reproduction, or a decision someone else owns, list those questions …

    line 56

≈ “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-task

All tracker access goes through one command. Never construct JQL, WIQL, URLs or field lists — the provider builds them from the resolved context.

wb <args>    # wb not on PATH: python <this skill's directory>/../../lib/wb.py <args>

Steps

  1. Key given? Go straight to step 2: start <KEY> resumes as well as starts. With no key, status lists every ticket with work in flight and the one command that moves each on.
  2. No key given — task list. Four columns, newest first. Show them and ask which one, unless the request already names one.

    No tracker in this repo? task new "title" --type bug|feature|chore|support records it in the local backlog and everything downstream works unchanged. Only local contexts accept it; wb says so if the repo has a real tracker.

  3. Pick it up — start <KEY>. Reads the ticket into .workflow/<KEY>/triage.json and prints its text, puts the checkout on the ticket's branch, and ends with the route and the one next command. Rerun it any time: it is a no-op that says where the ticket stands. To read without branching, or deeper, use task get <KEY> — depth 1 by default: the task, plus one line per linked item.

    • Use --depth 0 when the ticket is self-contained and links do not matter.
    • Use --depth 2 only when a blocker or a parent decides the approach. It fetches bodies for blocking and hierarchy links, never for relates.

    Light path (the route says so): no plan, no other skill, no status. Make the change and a test that covers it, then finish <KEY> -m "<type>: <summary>" --commit. It runs the suite, the regression check and the message check itself, so do not run them first; on a pass it commits exactly the checked files. If it says the work outgrew the path, continue with plan-change.

  4. Go deeper only where it pays — the _expand list names what exists but was not included. Pass a handle back verbatim: task get <KEY> --expand comments:all. Do not compose handles; anything not in _expand is rejected.
  5. Check _unmapped and _truncated if present. _unmapped means the tracker had a link type or field this version does not model — say so rather than guessing what it meant. _truncated means content was capped, and names the handle that would retrieve it.
  6. Report gaps before planning. If the ticket lacks acceptance criteria, a reproduction, or a decision someone else owns, list those questions plainly. A blocked-by link that is not Done is a gap, not a detail. Write them to .workflow/<KEY>/questions.md and say the ticket is not ready to plan.

Rules

  • Report what the ticket says, not what it probably means. Missing information is a finding to report, never a blank to fill.
  • Quote the key in every claim so later steps can check it.
  • One tracker per context, resolved automatically. If wb reports no context, relay its fix lines — do not guess a project or a URL.

Next, on the standard route: plan-change reads the artifact this produced.

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.