triage

Move GitHub issues and external PRs through a triage state machine with agent-ready briefs.

1|Updated Jun 2, 2026
One-click install
npx skills add https://github.com/SevWren/Daily-Motivation-Brain-Helper --skill triage-sevwren
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: triage
Source: https://github.com/SevWren/Daily-Motivation-Brain-Helper/tree/main/CLAUDE/skills/engineering/triage
Command: npx skills add https://github.com/SevWren/Daily-Motivation-Brain-Helper --skill triage-sevwren

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Maintainers drown in unlabeled issues and half-specified feature requests, and handing work to autonomous agents requires durable, well-scoped specifications that most issues lack. This Skill runs a structured triage workflow that categorizes issues, verifies claims against the codebase, grills reporters for missing detail, and produces agent-ready briefs. ## Core Features & Use Cases - State machine triage: Move issues and external PRs through category roles (bug, enhancement) and state roles (needs-triage, needs-info, ready-for-agent, ready-for-human, wontfix) with conflict detection. - Codebase verification: Reproduce reported bugs, check PR diffs against their claims, and detect already-implemented features or previously rejected concepts via the .out-of-scope/ knowledge base. - Agent brief authoring: Write durable, behavioral specifications with acceptance criteria and explicit scope boundaries that survive codebase refactors. - Use Case: A maintainer says "Let's look at #42" — the Skill reads the issue, checks the codebase for existing implementations and prior rejections, verifies the claim, grills the reporter if needed, and posts a complete agent brief so an AFK agent can implement it. ## Quick Start Ask the assistant to triage issue #42 and recommend a category and state with reasoning.

Frequently Asked Questions about triage

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I triage GitHub issues with an AI assistant?▼

Invoke the triage workflow in natural language, such as "show me anything that needs my attention" or "let's look at #42". The Skill reads the full issue, checks the codebase for existing implementations, recommends a category and state, and waits for your direction before applying labels or comments.

What makes a good agent brief for autonomous coding agents?▼

A good agent brief describes behavioral contracts and acceptance criteria rather than file paths or line numbers, which go stale. It states current versus desired behavior, names key types and interfaces, lists independently testable criteria, and declares explicit out-of-scope boundaries.

Does this triage workflow handle pull requests as well as issues?▼

Yes, external pull requests are treated as issues with attached code and move through the same state machine. For PRs, the Skill additionally checks out the diff, runs relevant tests to verify claims, and writes briefs describing what remains to finish the existing change.

How do I track rejected feature requests so they don't come back?▼

Rejected enhancements are recorded in a `.out-of-scope/` directory with one markdown file per concept, capturing the decision, reasoning, and links to prior requests. During triage, new issues are matched against these files so prior rejections are surfaced instead of re-litigated.

When should an issue go to ready-for-human instead of ready-for-agent?▼

Use ready-for-human when the work requires judgment calls, external access, design decisions, or manual testing that an autonomous agent cannot perform. The brief follows the same structure but notes why delegation is not possible.