github-triage/SKILL.md
Triage GitHub issues through a label-based state machine with interactive grilling sessions. Activate when the user says "triage issues", "review incoming issues", or "what needs triage". Not for creating issues, writing code, or PR reviews.
npx skillsauth add sanurb/skills github-triageInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Triage issues in the current repo using a label-based state machine. Infer the repo from git remote. Use gh for all GitHub operations.
Activation guard: Only run when the user explicitly requests issue triage. Do not activate on general issue discussion, code reviews, or implementation requests.
| Label | Type | Meaning |
|-------|------|---------|
| bug | Category | Something is broken |
| enhancement | Category | New feature or improvement |
| needs-triage | State | Maintainer must evaluate |
| needs-info | State | Waiting on reporter |
| ready-for-agent | State | Fully specified, ready for AFK agent |
| ready-for-human | State | Requires human implementation |
| wontfix | State | Will not be actioned |
Every issue must have exactly one state label and one category label. If conflicting state labels exist, flag the conflict and ask the maintainer before proceeding.
| From | To | Trigger | Action |
|------|----|---------|--------|
| unlabeled | needs-triage | Skill (first look) | Apply label after presenting recommendation |
| unlabeled | ready-for-agent | Maintainer | Write agent brief, apply label |
| unlabeled | ready-for-human | Maintainer | Write human brief, apply label |
| unlabeled | wontfix | Maintainer | Close with comment (+ .out-of-scope/ for enhancements) |
| needs-triage | needs-info | Maintainer | Post triage notes + questions for reporter |
| needs-triage | ready-for-agent | Maintainer | Write agent brief, apply label |
| needs-triage | ready-for-human | Maintainer | Write human brief, apply label |
| needs-triage | wontfix | Maintainer | Close with comment (+ .out-of-scope/) |
| needs-info | needs-triage | Skill (detects reply) | Surface to maintainer for re-evaluation |
An issue can only move along these transitions. Flag unusual overrides.
What does the maintainer want?
├─ "Show me what needs attention" → Overview (below)
├─ "Let's look at #N" → read references/triage-workflow.md
├─ "Move #N to <state>" → Quick Override (below)
└─ "What's ready for agents?" → Query: gh issue list --label ready-for-agent
Query GitHub and present a summary in three buckets:
needs-triage issues — maintainer must evaluate. Oldest first.needs-info with new activity — reporter replied since last triage notes.For each issue: number, title, age, one-line summary. Let the maintainer pick which to dive into.
When the maintainer explicitly says "move #N to <state>":
ready-for-agent without a prior grilling, ask if they want a brief agent brief.Read references/triage-workflow.md for the full step-by-step procedure.
Every triage action must satisfy ALL of these:
needs-info comments capture all grilling progress — no resolved question is lostwontfix enhancements produce a .out-of-scope/ file — see out-of-scope.md| File | One Job |
|------|---------|
| triage-workflow.md | Step-by-step for triaging a single issue |
| agent-brief.md | How to write durable agent briefs |
| out-of-scope.md | How the .out-of-scope/ knowledge base works |
| agent-brief-template.md | Copy-and-fill template for agent briefs |
| needs-info-template.md | Copy-and-fill template for needs-info comments |
development
Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub, GitLab, fp, or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `fp-plan`, `fp-implement`, `fp-review`, `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.
development
Build a throwaway prototype to flush out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".
tools
Control herdr (a terminal-native agent multiplexer) from inside it. Manage workspaces and tabs, split panes, spawn sibling agents, read pane output, and wait for state changes — all via CLI commands that talk to the running herdr instance over a local unix socket. Use when running inside herdr (HERDR_ENV=1). Do not use outside herdr.
documentation
Compact the current conversation into a handoff document for another agent to pick up.