ワンクリックで
sddp-implement-qc-loop
Run Implement → QC in a continuous loop until QC passes or the safety limit (10 iterations) is reached
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Run Implement → QC in a continuous loop until QC passes or the safety limit (10 iterations) is reached
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Perform non-destructive cross-artifact consistency and quality analysis across spec, plan, and tasks
Run the full SDD pipeline (Specify → Clarify → Plan → Checklist → Tasks → Analyze → Implement+QC) end-to-end without user interaction
Generate a custom requirements quality checklist for the current feature
Identify underspecified areas in a feature spec and resolve them through targeted clarification questions
Create or refine the canonical project-level deployment and operations context (`specs/dod.md`)
Analyzes the repository and guides the user through setting up their local development environment
| name | sddp-implement-qc-loop |
| description | Run Implement → QC in a continuous loop until QC passes or the safety limit (10 iterations) is reached |
You are starting an Implement + QC loop workflow. Your sole purpose is to repeatedly implement tasks and run quality control until QC passes or the safety limit is reached. Disregard any prior specification or planning discussion from this conversation. Focus exclusively on the implement → QC cycle.
Load and follow the workflow in .github/skills/implement-qc-loop/SKILL.md.
When either shared sub-skill requires user decisions and AUTOPILOT = false:
When AUTOPILOT = true, keep following the shared workflow's automatic decision rules unchanged.
The loop skill will instruct you to load and execute two sub-skills inline:
.github/skills/implement-tasks/SKILL.md.github/skills/quality-control/SKILL.mdWhen either sub-skill says Delegate, read the referenced sub-agent file at that point, not before — then perform the task yourself:
.github/agents/_context-gatherer.md.github/agents/_task-tracker.md.github/agents/_developer.md.github/agents/_checklist-reader.md (only during gates.md checklist gate).github/agents/_test-evaluator.md (only during gates.md checklist gate, when checklists FAIL).github/agents/_technical-researcher.md.github/agents/_qc-auditor.md.github/agents/_story-verifier.mdReport progress to the user at each iteration boundary — summarize what was fixed and what remains.