escalate
Reports stuck problems that need human help, showing what was tried and what's blocking progress.
Installation
Paste this into Claude Code, Cursor, or any agent that can run commands.
SKILL.mdShow the author's original SKILL.md
--- name: escalate description: 'Terminal escalation for do when unresolved blockers require outside intervention and no useful independent work remains. Reports the evidence, recovery attempts, completed work, and intervention needed.' user-invocable: false --- This is a terminal handoff, called only after useful independent work is exhausted. An earlier blocker notice belongs in the executor's progress report; it does not end the run. If useful independent work remains, return to the calling executor to continue it before escalating. Receive the Manifest path from `/do`, along with the affected gates and the actual evidence behind each. Relay that evidence as supplied, without inventing verification the run did not perform. Open the report with the intervention needed — unavailable knowledge or access, new authority, or a change to the Outcome or a hard requirement — and the resolution you recommend; report it without starting a question-and-wait loop. Surface it with the blocker evidence: the Outcome or criterion (OUTCOME, INV-G or AC ID) that can't be met, and the credible recovery paths investigated and why they failed. Name what independent work completed and why the remainder depends on that intervention. Name the execution log's path when `/do` kept one, so the run that resumes reads what this one tried. Also name material autonomous decisions and their rationale, including material working-claim and evidence revisions with their basis, and Appetite revisions and the benefit that justified their added complexity or maintenance; any Process Guidance departed from; any deviation from the Initial Approach or the Deliverable order; the issues fixed on the way; the debt `/do` hands over, which is only what the run could not fix, item by item as supplied, offering `ticket-up` for any the user wants worked, never a finding below a gate's bar or a pre-existing issue fixed on the way; and each offer flagged for a person rather than accepted — whether the run flagged it or the Manifest's `ASM-*` entries carry it — and each decision record written with an agent as its decider, with what accepting the offer or reviewing the record would change. Include these even when the execution log already holds them. Carry any drafted Taste entry `/do` supplies verbatim, with its question for the user's yes. **The user's call.** A decision is the user's call when two careful people with the same evidence could reasonably decide it differently, and the difference would matter to the user. Test each material decision against that sentence; your own confidence does not settle it. At a user's call, first honor any explicit retained decision or applicable delegation; then check the user's Taste entries — ratified preferences in a `## Taste` section of a loaded memory file. Follow an entry only where it clearly bears: it speaks to this kind of call, and following it would change the choice. A general lean that would tilt almost any call, such as less effort or lower cost, does not bear on its own. Otherwise decide on the evidence. Wherever decisions are reported, list first each decision record the run reopened, with the reason set aside and what reversing would cost, then the user's calls, each with the alternative not taken and what decided it — the entry followed, or that no entry applied. A false hard premise outside the caller's amendment authority can arrive here even when its gate passed. Quote the report or name what execution showed in place of attempts a passing gate does not have. A costly bar alone is not a blocker while repairs remain viable, and this skill never lowers a bar. A BLOCKED verifier verdict is not sufficient on its own: the executor first investigates what it can recover and completes useful independent work. Quote the remaining BLOCKED note and name the required outside action. A pure external wait reports as pending under a no-wait policy; otherwise the executor waits and re-verifies. A stalled wait with no viable recovery path names the intervention needed here. Pure user questions about the manifest or process are answered inline by the executor. **If the user later supplies a scope or requirement change**, invoke `define` with the Manifest path, then resume the executor on the Manifest with the log path this report named. If they clear the blocker or supply the missing context, resume it the same way. Their response is steering; resumed execution remains unattended.
Mirrored from the author's public source. Install counts from the open skills registry.