Skip to content

Gentleman-Programming/gentle-shell / skills/rdd-defect-workflow

gentle-ai-rdd-defect-workflow

Verified

Trigger: fixing RDD defects (review authority, receipts/lineage, correction/recovery, delivery gate). Not for using or toggling RDD.

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.
  • Follow the target repository's issue policy: require an approved issue (status:approved) only where it uses one; reproduce on a clean current default branch 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 Split independent causes; never merge a superseded or conflicting authority line.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. Above about 400 additions plus deletions (a planning heuristic, not a hard limit), record the slice boundary in the feature document; the delivery shape and the target repository's size policy apply only when publishing.
  • 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.

Decision Gates

ConditionAction
Any RDD modeReview evidence remains review-only; ordinary commit, push, PR, and release follow repository policy with no Pi delivery authority.
Issue gate or reproduction failsWait, stop, or narrow with evidence.
Invariant or rollback is independentSeparate issue and authoritative PR line.
Core bench fits / does not fitBench journey / actual runtime E2E; never proxy.
Forecast exceeds about 400 linesRecord the slice boundary; choose the delivery shape and apply the target size policy only when publishing; never a hard stop.

Execution Steps

  1. Check mode, the repository's issue policy, PR conflicts, and default-branch reproduction.
  2. Name invariant and rollback; isolate the worktree; CodeGraph-map code, tests, evidence, docs, distribution, and registration.
  3. Inventory flows and controls; add failing tests and the smallest correction.
  4. Normalize, record slice boundaries past about 400 changed lines, run tests, and record each flow's exact candidate, command, scenario, and result.
  5. Freeze, validate read-only, and give the verdict, evidence, and one humane next action.

Output Contract

Return rdd_mode, issue_pr, causal_invariant, operator_flows, journey_runtime_evidence, changed_line_budget, tests, rollback, and unresolved_authority_decisions.

Identify approved and superseded/conflicting authority lines; every flow, negative control, and candidate-bound proof; additions plus deletions and chain/exception; test results; independent rollback; and unresolved maintainer decisions.

References

No supporting files. Current repository policy remains authoritative.

planning-and-task-breakdownaddyosmani/agent-skillsBreaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
screenpipethedotmack/claude-memSearch screen and audio history recorded by Screenpipe and optionally save selected context into claude-mem. Use when the user asks to recall desktop activity, a meeting, or something seen in another app through Screenpipe.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
contact-widgetnexu-io/open-designSelf-contained floating chat widget with welcome screen, social links, meeting button, and message input. Single HTML file, zero dependencies.Stars: 108kUpdated Claude CodeCodexVerifiedInstall
meeting-notesnexu-io/open-designMeeting notes page — title bar with attendees, agenda checklist, decisions block, action items table with owners + dates, and a "next meeting" footer. Use when the brief mentions "meeting notes", "minutes", "1:1 notes", "all-hands recap", or "会议纪要".Stars: 108kUpdated Claude CodeCodexVerifiedInstall