Menú
Discover, analyze, and draft high-signal issue-thread responses and follow-up actions.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Governed runtime for agent skills: discover and install portable skills, run bounded skill graphs with explicit authority, and inspect signed receipts for what happened.
Audit a sealed runx receipt for governance, comparing the authority a run exercised against what it was granted, and flag over-reach, ungated mutation, unrecorded refusals, or exposed secret material.
Verify the receipt ids behind a normalized authority-usage summary, compare that evidence with granted scopes, and propose the narrowest grant the evidence supports.
Answer a cross-run audit question against the receipt ledger, returning matched receipts and a chain-verification result.
Read durable reflect projections, group repeated signals by skill, and emit validated handoffs to skill-lab improve when the evidence clears configured floors.
Review receipts and harness failures to propose bounded skill improvements.
| name | issue-triage |
| description | Discover, analyze, and draft high-signal issue-thread responses and follow-up actions. |
| runx | {"category":"ops"} |
Turn noisy issue streams into bounded, evidence-backed action.
This skill is for issue selection and response drafting, not for silently mutating repositories. Use it to identify which threads are worth attention, understand the maintainer or contributor situation, and draft the next helpful response or remediation path.
Separate discovery from response. Discovery finds the thread worth engaging. Response drafting turns one chosen thread into a concrete answer, escalation, or change plan.
Ground selection and response in the actual thread, repository facts, receipts,
and maintainer context; do not infer intent beyond what is visible. Lead with
the decision, answer, or next action in the project's own voice. Return
needs_more_evidence or needs_human when the thread is ambiguous, hostile,
underspecified, unsafe, or outside the maintainer's declared posture.
Discovery runner:
issue_candidates: candidate issues or discussions worth attention.selection_rationale: why one candidate should be handled next.operator_notes: constraints, caveats, or escalation triggers.Response runner:
issue_profile: concise summary of the chosen thread.response_strategy: recommended response posture and next action.response_draft: post-ready draft or maintainer handoff.follow_up_actions: concrete next steps after the response.repository (optional): repository slug or workspace reference.query (optional): search or queue objective for discovery.issue_url (optional): canonical issue URL for response drafting.issue_snapshot (optional): structured issue data when already fetched.maintainer_context (optional): project norms, release posture, and
response constraints.operator_context (optional): operator-supplied context used by higher-level
triage graphs.objective (optional): what the operator wants from this pass.