gentle-ai-rdd-defect-workflow
Installation
SKILL.md
Activation Contract
Load when the frontmatter trigger terms apply to a defect workflow.
This skill guides public collaboration. It does not grant issue approval, label, review, exception, or merge authority.
Hard Rules
- Review and Judgment Day evidence is review-only. Pi never mints delivery authority: ordinary commit, push, PR, and release always follow repository policy, regardless of RDD mode.
- Require an approved issue (
status:approved) and clean currentmainreproduction before implementation. Audit existing PRs for supersession or conflict; stop or narrow stale claims. - Group by causal authority invariant. Use one issue and one PR or explicit chain per independent invariant and rollback boundary. Split independent causes; never merge a superseded or conflicting authority line.
- Inventory every operator flow claimed by the issue or PR, including entry, mode, environment, expectation, and negative controls. Require one truthful black-box bench journey per CLI or lifecycle flow, or actual runtime E2E proof when the core bench cannot represent it. Synthetic proxy coverage never proves another runtime.
- Use CodeGraph-first impact mapping, a dedicated worktree, and behavior-first tests. Run source-mutating normalization before candidate freeze.
- Forecast authored changes before edits. The hard limit is 400 additions plus deletions; above it, STOP for a chain or explicit maintainer-approved exception.
- When RDD is enabled, bind review receipts, lineage, correction, and recovery evidence to the exact candidate. Keep bounded review defects in one correction transaction; never treat that evidence as delivery authority.
- Require independent read-only candidate validation before publication. Validation cannot edit source or authority; findings require a new candidate.
- Keep communication humane and evidence-based. Repository labels and workflow metadata are maintainer-owned, never evidence of contributor blame.