triage-init

One-time setup for the auto-triage pipeline on a project. Interviews you, detects the project's repo shape and issue tracker(s), builds the routing map, writes .claude/auto-triage.config.json, and creates the routing labels in the tracker. Use when onboarding a new project to auto-triage, or when asked to "set up triage", "configure auto-triage", or "add triage to this repo". After it finishes, run `/loop /triage` from the project root. Produces config only — it does not run triage itself.

Quality

97%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, highly actionable setup workflow with strong sequencing and validation checkpoints. The only weak spot is conciseness: a few embedded rationale sentences pad the guidance without adding executable value.

Suggestions

Trim justificatory asides that aren't instructions — e.g. the 'This is the piece that makes onboarding work...' sentence in step 3b and the parenthetical about the Mac-local runner; keep the detection rules, drop the motivation.

Move the sidecar recipe-catalog detail (the four grep → env mappings in step 3b) into a short referenced file if it grows, so SKILL.md stays a lean overview pointing at the recipe table.

Consider collapsing the Linear status-mapping prose in step 2 into a compact table (tracker → states → optional IN_REVIEW) to cut tokens while preserving the same actionable detail.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence, but a few rationale asides could be trimmed — e.g. 'This is the piece that makes "onboard a repo → it declares its own provisioning" work; skip it and the Mac-local runner is unaffected (it ignores sidecars).' is justification rather than instruction.	4 / 5
Actionability	Fully executable guidance throughout — concrete commands (`git -C . remote -v`, `gh api repos/<repo>/branches/<base>`, `gh label create`), specific MCP calls (`list_teams`, `create_issue_label`), grep patterns for testcontainers/DB/browser/DynamoDB, and explicit defaults (claimMarker, limits 3/3/2).	5 / 5
Workflow Clarity	Seven clearly sequenced steps with explicit validation checkpoints ('Read-only until step 4', 'Show the full JSON and get explicit approval', 'Show the labels to be created and where, then create them'), a feedback loop for sandbox write-block recovery, and a Guardrails section reinforcing confirm-before-mutate and idempotency.	5 / 5
Progressive Disclosure	Well-organized numbered sections serve as a clear overview, and the one external reference — 'Read first: ../triage/skill/references/config-schema.md' — is one level deep, clearly signaled at the top, and is the exact artifact being produced; no bundle files are present to mis-organize.	5 / 5
	Total	19 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, model description: concrete actions, natural quoted triggers, explicit what-and-when, and a clear boundary against the related triage skill. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Interviews you, detects the project's repo shape and issue tracker(s), builds the routing map, writes .claude/auto-triage.config.json, and creates the routing labels' — covering the full setup pipeline comprehensively; the leading verbs are third-person voice (Interviews/detects/builds/writes/creates), so no voice penalty applies.	5 / 5
Completeness	Explicitly answers both what (interview/detect/build/write/create-labels) and when ('Use when onboarding a new project to auto-triage, or when asked to...'), with concrete trigger phrases and an explicit post-run handoff.	5 / 5
Trigger Term Quality	Quoted natural trigger phrases a user would actually say — 'set up triage', 'configure auto-triage', 'add triage to this repo' — plus the onboarding scenario, giving comprehensive synonym coverage.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (one-time setup) and explicitly distinguishes itself from the sibling triage skill via 'Produces config only — it does not run triage itself', minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: MrToxy/claude-skills
Path: triage-init/SKILL.md
Commit: 66c7102

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.