triage · Skill Details

Mechanism

When It Triggers · How It Works · What It Produces

Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.

Trigger: User-invoked when external bug reports or feature requests need processing. /ask-matt lists it as one of the on-ramps — "bugs and requests piling up → /triage."
Mechanism: Operates around a state machine of 2 category roles (bug/enhancement) + 5 state roles. Each issue/PR goes through: gather context (full body, diff, labels) → check redundancy and .out-of-scope/ rejection records → recommend to maintainer → verify the claim → grill if needed (using /grilling and /domain-modeling) → apply outcome (AGENT-BRIEF for ready-for-agent, wontfix split by reason, enhancement rejection recorded in .out-of-scope/). Every auto-generated comment starts with an AI-generated disclaimer.
Output: Each issue/PR is advanced to the correct state: ready-for-agent (with brief), ready-for-human (with explanation), needs-info (with template questions), or wontfix (with outcome-specific handling, enhancements logged in .out-of-scope/).

Use Cases

Two Typical Use Cases

Scenario 01

Batch processing a backlog of issues

A maintainer facing a backlog of hundreds of unclassified issues invokes `/triage` asking for attention-needed items. The skill queries the issue tracker and presents three buckets: "unlabeled" → "needs-triage" → "needs-info with reporter replies." When the maintainer picks an issue, the skill gathers context, checks for redundancy and prior rejection, recommends a classification, verifies the claim (repro for bugs, diff check for PRs), grills if needed, and publishes an agent brief.

Scenario 02

Quick state override

A maintainer, already well-informed about an issue from a grilling discussion, says "move #42 to ready-for-agent." `/triage` recognizes this as a quick state override pattern, skips re-grilling, and directly applies the role change. But before acting, it confirms the details (role changes, comment content, whether to close). If moving to ready-for-agent without a grilling session, it asks whether to write an agent brief.

Skill Relationships

Which Skills I Use · Which Skills Use Me

Dependency relationships read as "the upper tier points to the lower tier." The current Skill sits in the middle tier — above are Skills that depend on it, below are Skills it depends on.

Tier 1 · These Skills Use Me

ask-mattWorkflow

Tier 2 · Current Skill

triageWorkflow

Tier 3 · I Use These Skills

Full Relationship Graph

Browse this skill's relationships within its skillset. Click a node to switch the side panel; use the search box to jump to any skill.

Skill File

SKILL.md

Open in GitHub ↗

SKILL.mdLoading from GitHub…

Skill Composition

Open in GitHub ↗

SKILL.md25.0%
other75.0%

▸skills/triage/
▸triage
- ·AGENT-BRIEF.md
- ·OUT-OF-SCOPE.md
- ·SKILL.md
- ▸agents
  - ·openai.yaml

Per the Agent Skills spec, SKILL.md is the only required file. The colored bars classify the rest into the three spec-aligned optional directories (scripts / references / assets) and an 'other' bucket. The full directory tree is below.

Related in Skillset

You May Also Need These Skills

ask-matt

A router skill for the entire skillset: when the user can't remember which skill to use or which flow fits their situation, they invoke this to get a recommendation. It describes the main "idea → ship" flow (grill-with-docs → to-spec/to-tickets → implement), plus on-ramps (triage, diagnosing-bugs, wayfinder), codebase health (improve-codebase-architecture), vocabulary layers (domain-modeling, codebase-design), and standalone skills (grill-me, prototype, research, teach). Following its map leads users to the correct workflow entry point.

Workflow

code-review

A two-axis code review skill: reviews a diff (from a fixed point to HEAD) along both Standards (coding standards + Fowler smell baseline) and Spec (faithful implementation of the originating issue/PRD). Both axes run as parallel sub-agents to avoid context pollution. The report aggregates findings without merging conclusions, ensuring "passes standards but implements the wrong thing" and "implements the right thing but breaks conventions" are both surfaced independently.

Workflow

codebase-design

A shared vocabulary skill for deep module design: provides a precise set of design terms (Module, Interface, Depth, Seam, Adapter, Leverage, Locality) guiding agents and developers to design "deep modules" — a lot of behaviour behind a small interface. Includes design principles (the deletion test, the interface is the test surface) and testability guidelines. A reference skill consumed by other skills (e.g., improve-codebase-architecture, tdd) and invoked directly by engineers.

Style Guide

diagnosing-bugs

A disciplined diagnosis loop for hard bugs and performance regressions. The core idea is to first build a tight feedback loop — no hypothesis phase without one. Six phases: build feedback loop → reproduce + minimise → generate 3-5 falsifiable hypotheses → instrument by prediction → fix + regression test → cleanup + post-mortem. If the codebase architecture can't lock down the bug, it recommends handing off to the improve-codebase-architecture skill.

Workflow