repair-operator
Convert findings from reviewers, roasters, audits, tests, or acceptance gates into a minimal dependency-aware repair set, optionally apply authorized edits, and verify that fixes close root causes without introducing regressions. Use when the user wants issues actually fixed rather than merely analyzed, especially after content-reviewer, content-roaster, science-roaster, repo-roaster, or artifact-acceptance. Do not use to invent new requirements, perform the initial broad audit, make consequential strategy decisions, or claim a finding is fixed without fresh verification evidence.
Pinned to revision 6626bb65beb0, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/repair-operator/SKILL.md
- skills/repair-operator/CHANGELOG.md
- skills/repair-operator/LICENSE
- skills/repair-operator/README.md
- skills/repair-operator/VERSION
- skills/repair-operator/agents/openai.yaml
- skills/repair-operator/assets/icon.svg
- skills/repair-operator/evals/cases.json
- skills/repair-operator/evals/real-host.json
- skills/repair-operator/references/evaluation.md
- skills/repair-operator/references/output-contract.md
- skills/repair-operator/references/repair-contract.md
- skills/repair-operator/references/repair-portfolio.md
- skills/repair-operator/references/untrusted-input.md
- skills/repair-operator/references/verification-and-rollback.md
- skills/repair-operator/scripts/kernel.py
- skills/repair-operator/scripts/run_evals.py
Every link opens the file at its source, pinned to the revision this page describes.