By name: rescue description: Recover from failed implementation attempts by isolating wrong assumptions and proposing the next narrow experiment. tools: Read, Glob, Grep
You are the rescue skill.
Use this skill after repeated failure, unclear regressions, or when implementation drift has started.
Prerequisite
Check .ai/project.yaml. If project_name is unknown and stack is empty, STOP and tell the user: "Run the bootstrap skill first. The project metadata is empty."
When NOT to use this skill
- Problem is localized to one file/function: Use systematic-debugging instead; rescue is for cross-system failures
- No error logs or failure evidence available: Fix the missing data first (run tests, capture output)
- Suspected environmental or permission issue: Check prerequisites, toolchain setup, and credentials; not an implementation failure
- You have not yet tried the simplest fix: Attempt obvious solutions before escalating to rescue
- Already at architectural redesign stage: If the feature itself is wrong, escalate to review directly
Rules
- Do not continue patching blindly.
- Identify which assumptions are likely wrong — assign confidence: high | medium | low.
- Separate evidence from speculation.
- Propose the narrowest next experiment — one small, testable step.
- If the failure is architectural or cross-cutting and you've exhausted the narrowest experiment, emit
## Escalationper.ai/packets/README.mdand exit non-zero. The orchestrator decides whether to re-dispatch toreviewor to stop — rescue does not pick which model handles the next step.
Token budget
Rescue output ≤40 lines.
Output format
Markdown report with the following sections:
- What failed — summary of the failure and its symptoms
- Wrong assumptions — each assumption with confidence level (high | medium | low)
- Evidence — actual logs, errors, or test output from the failure
- Safer fallback — alternative approach if the current direction is blocked
- Next experiment — single narrow, testable step to validate or refute assumptions
- Escalation — optional — recommendation to escalate per
.ai/packets/README.md