quality-gate
Production quality gate for agent sessions. Activates on session stop to evaluate work quality using 4-dimension weighted scoring (completeness, honesty, deferral ratio, work evidence). Catches rationalization patterns, verifies test claims, and generates handoff artifacts for session continuity. Use sprint contracts to define done-criteria before building.
ソース情報
- リポジトリ
- 0xNyk/lacp
- ソースの最終更新活動
- 2026年4月9日 15:16
- 検出された SKILL.md の言語
- 英語
- スター
- 305
- フォーク
- 2
インストール方法
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
ソースファイルを確認
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
SKILL.md を表示中
SKILL.md
ソースの指示 · 読み取り専用プレビュー- name
- quality-gate
- description
- Production quality gate for agent sessions. Activates on session stop to evaluate work quality using 4-dimension weighted scoring (completeness, honesty, deferral ratio, work evidence). Catches rationalization patterns, verifies test claims, and generates handoff artifacts for session continuity. Use sprint contracts to define done-criteria before building.
# Quality Gate
This plugin evaluates your work at session end using criteria-based scoring:
- **Completeness** (35%): Did you finish what you committed to?
- **Honesty** (30%): Are claims about tests/status verified?
- **Deferral ratio** (20%): How much was pushed to "later"?
- **Work evidence** (15%): Files changed relative to scope claimed
## Sprint Contracts
Before implementing, state your sprint contract:
- What files will be modified
- What tests will pass
- What the acceptance criteria are
The quality gate evaluates against these criteria at session end.
## Handoff Artifacts
On every non-trivial stop, a handoff artifact is generated with:
- Task summary, files modified, test status
- Git branch and diff summary
- Next steps for the following session
The next session automatically receives the handoff.
## Configuration
| Env Var | Default | Purpose |
|---------|---------|---------|
| `LACP_QUALITY_GATE_THRESHOLD` | `2.5` | Minimum weighted score (1-5) |
| `LACP_QUALITY_GATE_MODEL` | `llama3.1:8b` | Ollama model for scoring |
| `LACP_BLIND_SPOT_ENABLED` | `0` | Enable blind spot reflection |
GitHubで見る