Triage
Skill tokyubevoxelverse/triage
Claude Code skill that clears your issue backlog β dedupes by symptom, finds bugs already fixed on main, drafts the replies, ranks the five worth fixing next. Never posts anything without your approval. π
npx -y skills add tokyubevoxelverse/triageAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 17 days oldThe repository was created 17 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Triage a repository's issue backlog β dedupe, label, flag missing repro info, draft replies, and rank what's worth fixing. Use when a maintainer faces a pile of open issues and wants order restored without closing things rudely or blindly.
SKILL.md
2.9 KB, 608 tokens by cl100k_base, as published. Nobody here has run it
Triage
An untriaged backlog punishes the reporters who did everything right. Your job is to restore signal: cluster the duplicates, name what each issue is, check it against the current code, and surface the handful actually worth fixing next. You draft; the maintainer sends. Never post, close, or label anything without explicit approval β every action ships as a draft.
Phase 1 β Inventory
Pull all open issues (forge CLI or API; if neither is authenticated, ask the user to export or paste). For each: number, title, age, last activity, labels, reporter, body gist. Note the shape of the backlog β a 40-issue backlog gets per-issue care; a 400-issue one gets clustering first and per-issue care for the survivors.
Phase 2 β Cluster
Group issues describing the same underlying thing: same error text or stack signature, same feature area + symptom, same request in different words. For each cluster, pick the canonical (best repro info wins, not oldest) and mark the rest as duplicates of it. Merge information: a duplicate often contains the repro detail the canonical lacks β move it before closing.
Phase 3 β Classify each survivor
- Kind: bug / feature request / question / docs / can't-tell.
- Repro status: has runnable repro / has partial info / vague. For bugs with repro, check it against current code β search for the error message, look at whether the involved path was since rewritten or the fix already landed (name the commit if so).
- Status verdict:
FIXED(by commit X),STALE(refers to code that no longer exists),NEEDS-INFO(can't act without repro),VALID(confirmed against current code),DISCUSS(needs a maintainer decision, not a fix).
Phase 4 β Deliverables
- The dedupe map β close X as duplicate of Y, with the info-merge notes.
- The label plan β using the repo's existing labels; propose new ones only if a real gap exists.
- Drafted replies β for every issue that needs one: needs-info requests that ask for specific missing details (not a generic template), fixed-in-commit closes that name the commit and version, gentle stale-closes that invite reopening with fresh info. Warm, brief, blameless β reporters are volunteers.
- The shortlist β the top ~5 issues worth fixing next, ranked by user impact Γ confirmation confidence Γ estimated effort, each with a one-line "why this one."
- Backlog health note β recurring themes the backlog reveals (one subsystem generating half the bugs, a missing doc that keeps causing the same question).
If approved to execute, apply exactly the approved subset β labels, closes, replies β and report what was done.
What ships with it: 2 files
3.0 KB alongside SKILL.md