agentleFS
mauriciovieiramauriciovieira/groundwork/skills/triage/SKILL.md

triage

Skill0 starsChanged 4 months agoMITView on GitHub

Triage inbound issues through a state machine of triage roles, so they arrive at to-issues (or ready for an agent directly) already sorted. Use before to-issues when issues already exist in the tracker rather than being sliced fresh from a PRD.

189 other projects use a version of this, 75 of them edited.

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

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

  • 0

    Common

    Most of the 176 edited versions we read keep these.

  • 3

    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:

    Every comment or issue posted to the issue tracker during triage must start with this disclaimer:

    line 18
  2. Distinctive:

    Every triaged issue should carry exactly one category role and one state role.

    line 44
  3. Very specific:

    Interview (if needed): If the issue needs fleshing out, use the groundwork:interview-loop technique - ask detailed, one-at-a-time questions …

    line 77
  4. Distinctive:

    If prior triage notes exist on the issue, read them, check whether the reporter has answered any outstanding questions, and present an …

    line 113

“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

groundwork:triage

Move issues on the configured issue tracker through a small state machine of triage roles. This is the inbound front door: real bug reports and feature requests land here before a PRD or a tracer-bullet slice ever gets written for them.

0. Preconditions

Read docs/groundwork/config.json. If it doesn't exist, don't stop - bootstrap it per the "Lazy bootstrap" section of the groundwork setup skill: detect tracker and project type, write the config with defaults, state the assumptions in one line, and continue. Running setup explicitly is only for customizing.

This skill assumes an external tracker with real issues, labels, comments, and reporters (tracker: "github" or "linear"). If config.json's tracker is "local", tell the user triage doesn't apply - local mode has no inbound-issue concept to sort, only docs/groundwork/features/NNNN-slug/tasks.md entries that to-issues already created with a type and status - and stop.

Every comment or issue posted to the issue tracker during triage must start with this disclaimer:

> *This was generated by AI during triage.*

Reference docs

  • AGENT-BRIEF.md - how to write durable agent briefs
  • OUT-OF-SCOPE.md - how the .out-of-scope/ knowledge base works

Roles

Two category roles:

  • bug - something is broken
  • enhancement - new feature or improvement

Five state roles:

  • needs-triage - maintainer needs to evaluate
  • needs-info - waiting on reporter for more information
  • ready-for-agent - fully specified, ready for an agent to build directly (no PRD/slice needed)
  • ready-for-human - needs human implementation
  • wontfix - will not be actioned

Every triaged issue should carry exactly one category role and one state role. If state roles conflict, flag it and ask the maintainer before doing anything else.

These are canonical role names. Only the five state roles are configurable: their label strings come from docs/groundwork/config.json's triage_role_labels field (not triage_labels, which is a separate, unrelated list to-issues applies to every issue it creates). If a state role is missing from triage_role_labels (or the field is empty), that role's label string equals its own name; tell the user to run setup to override any of them. The two category roles (bug, enhancement) are fixed - always use those exact strings, no config override exists for them.

State transitions: an unlabeled issue normally goes to needs-triage first; from there it moves to needs-info, ready-for-agent, ready-for-human, or wontfix. needs-info returns to needs-triage once the reporter replies. The maintainer can override at any time - flag transitions that look unusual and ask before proceeding.

Invocation

The maintainer invokes triage and describes what they want in natural language. Interpret the request and act. Examples:

  • "Show me anything that needs my attention"
  • "Let's look at #42"
  • "Move #42 to ready-for-agent"
  • "What's ready for agents to pick up?"

Show what needs attention

Query the issue tracker and present three buckets, oldest first:

  1. Unlabeled - never triaged.
  2. needs-triage - evaluation in progress.
  3. needs-info with reporter activity since the last triage notes - needs re-evaluation.

Show counts and a one-line summary per issue. Let the maintainer pick.

Triage a specific issue

  1. Gather context. Read the full issue (body, comments, labels, reporter, dates). Parse any prior triage notes so you don't re-ask resolved questions. Explore the codebase using docs/groundwork/glossary.md, respecting any accepted ADRs in the area (docs/groundwork/adr/ for system-wide decisions, or the relevant feature's docs/groundwork/features/NNNN-slug/adr/ if the issue clearly belongs to work already in flight). Read .out-of-scope/*.md and surface any prior rejection that resembles this issue.
  2. Recommend. Tell the maintainer your category and state recommendation with reasoning, plus a brief codebase summary relevant to the issue. Wait for direction.
  3. Reproduce (bugs only). Before any interview, attempt reproduction: read the reporter's steps, trace the relevant code, run tests or commands. Report what happened - successful repro with code path, failed repro, or insufficient detail (a strong needs-info signal). A confirmed repro makes a much stronger agent brief.
  4. Interview (if needed). If the issue needs fleshing out, use the groundwork:interview-loop technique - ask detailed, one-at-a-time questions until every branch of the issue is resolved.
  5. Apply the outcome:
    • ready-for-agent - post an agent brief comment (AGENT-BRIEF.md). Give it **Type:** AFK in the brief so build can pick it up directly, exactly like a to-issues-created slice.
    • ready-for-human - same structure as an agent brief, but **Type:** HITL, and note why it can't be delegated (judgment calls, external access, design decisions, manual testing).
    • needs-info - post triage notes (template below).
    • wontfix (bug) - polite explanation, then close.
    • wontfix (enhancement) - write to .out-of-scope/, link to it from a comment, then close (OUT-OF-SCOPE.md).
    • needs-triage - apply the role. Optional comment if there's partial progress.

Quick state override

If the maintainer says "move #42 to ready-for-agent", trust them and apply the role directly. Confirm what you're about to do (role changes, comment, close), then act. Skip the interview - but never skip the Agent Brief: ready-for-agent/ready-for-human are only reachable with one posted (see the outcome rules above), since build depends on its Type field to treat the issue as workable. Draft it from the issue's existing content; if something the template needs (acceptance criteria, current/desired behavior) is genuinely missing, ask the maintainer that one thing rather than reopening a full interview session.

Needs-info template

> *This was generated by AI during triage.*

## Triage Notes

**What we've established so far:**

- point 1
- point 2

**What we still need from you (@reporter):**

- question 1
- question 2

Capture everything resolved during the interview under "established so far" so the work isn't lost. Questions must be specific and actionable, not "please provide more info".

Resuming a previous session

If prior triage notes exist on the issue, read them, check whether the reporter has answered any outstanding questions, and present an updated picture before continuing. Don't re-ask resolved questions.

Relationship to to-issues

to-issues slices a prd.md into tracer-bullet work; triage sorts issues that already exist and, for ready-for-agent/ready-for-human outcomes, makes them directly buildable without a PRD at all. If an issue turns out to need real design work during the interview, tell the maintainer it's grown past a quick triage and suggest survey or to-prd instead of forcing an agent brief onto something underspecified.

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.