Triage GitHub issues and PRs — cross-link, flag stale items, recommend actions. Use when grooming the backlog, pre-release cleanup, or asked to triage issues/PRs.
Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
Quelldateien prüfen
Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
Triage GitHub issues and PRs — cross-link, flag stale items, recommend actions. Use when grooming the backlog, pre-release cleanup, or asked to triage issues/PRs.
Writes are disabled by default. --auto-close and --auto-merge still require a per-batch AskUserQuestion confirmation before any gh issue close or gh pr merge.
Execution
Execute this triage workflow:
Step 1: Resolve target repo and gather batches
Run the data-gathering script. It fetches issue/PR batches, computes age in days
per item, categorizes each PR via the pure first-match table (over isDraft,
mergeable, mergeStateStatus, reviewDecision, and statusCheckRollup[].conclusion),
flags stale-candidate issues, and extracts each PR's closing keywords:
Parse STATUS= and ISSUES: from the output. Per item it emits
ISSUE_<n>_AGE_DAYS / ISSUE_<n>_REFS / ISSUE_<n>_STALE_CANDIDATE and
PR_<n>_CATEGORY / PR_<n>_AGE_DAYS / PR_<n>_CLOSES (plus the underlying
enum fields). It also rolls up SYSTEMATIC_FAILURE_* groups (see Step 4).
If --repo was provided, pass it through; the script reads the
current repo from origin otherwise. Sort each set by age (oldest first if
--oldest-first) and build a TodoWrite list with one entry per item.
Step 2: Investigate each issue (skip if --type prs)
For each open issue in parallel (batch reads), gather evidence:
Extract referenced PR numbers from title, body, and comments (regex #(\d+)).
Search the codebase for concrete nouns in the issue (file paths, function names, resource names, command names) using Grep. Evidence that described artefacts exist (or no longer exist) feeds the categorization.
Compute age in days from updatedAt.
Step 3: Categorize each issue
Category
Criteria
implemented
A referenced PR is merged AND codebase shows the promised artefacts
outdated
Referenced files/resources no longer exist; issue predates current structure
stale
age > --days-stale-issue AND no recent comments AND not implemented
still-valid
None of the above — work remains
Record the winning PR number (if any) with each implemented entry.
Step 4: Read each PR's category (skip if --type issues)
The script already categorized every PR in Step 1 — read PR_<n>_CATEGORY
straight from its output. The category is a pure first-match over the enum
fields (the script owns this deterministic table, top to bottom):
Category
Criteria
draft
isDraft is true
needs-fix
Any check in statusCheckRollup has conclusion: FAILURE
needs-rebase
mergeStateStatus in BEHIND, DIRTY; OR mergeable is CONFLICTING
changes-requested
reviewDecision is CHANGES_REQUESTED
ready-to-merge
mergeable: MERGEABLE AND mergeStateStatus in CLEAN/HAS_HOOKS/UNSTABLE AND reviewDecision: APPROVED AND not draft
awaiting-review
reviewDecision is REVIEW_REQUIRED or null AND no failing check
stale
age > --days-stale-pr AND none of the above trigger
If a PR comes back as uncategorized (e.g. mergeStateStatus/mergeable
both UNKNOWN), trigger a fresh view and re-run the script, or inspect:
Systematic failures. When ≥2 bot-authored needs-fix PRs share an
identical failing-check signature, the script groups them under
SYSTEMATIC_FAILURE_<k>_SIGNATURE (the sorted |-joined failed check names)
and SYSTEMATIC_FAILURE_<k>_PRS (the PR list); SYSTEMATIC_FAILURE_COUNT
holds the number of groups. These almost always have one shared root
cause — e.g. Dependabot can't update bun.lock, so every npm-bump PR fails
the bun install --frozen-lockfile step before lint/typecheck/tests run, and
"Lint FAILURE / Type Check FAILURE" is misleading (nothing was linted). For
each group, read the install step's log once before assuming code defects:
If --auto-close was set and any issue is implemented or stale, ask before acting:
AskUserQuestion("Close N issues?", options=[
"Yes — close all implemented + stale",
"Implemented only",
"Stale only",
"No, report only"
])
For each selected issue:
gh issue close <n> --repo $REPO --comment "Closing as <category>.
Evidence: <short summary + cross-link PR>
Triaged by /git:triage on <date>."
If --auto-merge was set and any PR is ready-to-merge, ask similarly. Merge with:
gh pr merge <n> --repo $REPO --squash --auto
(--squash is the repo default for this project; for other repos, read gh repo view --json squashMergeAllowed,mergeCommitAllowed,rebaseMergeAllowed and pick the first allowed strategy.)
Step 8: Synthesize the backlog report
After per-item actions, emit a structured summary:
Actions taken — count of issues closed, PRs merged, with numbers.
Quick wins — still-valid issues whose body suggests <30 min of work (single file, doc edit, config tweak).
Blockers — changes-requested PRs and issues blocked on external factors. For each SYSTEMATIC_FAILURE_* group, emit one "systematic failure — likely shared root cause" line naming the PRs and the shared check signature, rather than N independent needs-fix entries.
Decisions needed — still-valid issues whose body ends in a question or "how should we…".
Handoff recommendations per category:
Category
Recommended next skill
needs-fix
/git:fix-pr <n>
changes-requested
/git:pr-feedback <n>
needs-rebase
/git:conflicts <n> or gh pr merge --update-branch
still-valid (actionable)
/git:issue <n>
still-valid (admin only)
/git:issue-manage
implemented (not auto-closed)
manual gh issue close <n>
Post-actions
Print a one-line summary: Triaged N issues (X closed), M PRs (Y merged). See report above.
If any writes were gated behind confirmation that the user declined, leave the items open and note "no writes — report only".
Remind the user they can re-run with --type prs or --type issues to focus the sweep.
Agentic Optimizations
Context
Command
Minimal issue list
gh issue list --repo $REPO --state open --limit $BATCH --json number,title,updatedAt,labels
Full PR status
gh pr list --repo $REPO --state open --limit $BATCH --json number,title,updatedAt,mergeable,mergeStateStatus,reviewDecision,statusCheckRollup,isDraft
