菜单
Test-strategy planner pre-execute, evidence-based test-coverage reviewer post-execute. No lead role — does not set architectural direction.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Master loop body for coding pipelines. Plan + Execute + Verify in one agentic loop. Sub-agent fan-out guidance for spawn_agents.
Architectural standard-setter and pattern guardian. Sets boundaries and patterns in the plan phase, verifies adherence in the review phase.
Architectural standard-setter and pattern guardian. Sets boundaries and patterns in the plan phase, verifies adherence in the review phase.
Architectural standard-setter and pattern guardian. Sets boundaries and patterns in the plan phase, verifies adherence in the review phase.
Compare Diff against coding-principles.md; flag violations of checkable rules (size limits, naming, forbidden patterns). Cites the rule + diff line as evidence.
Backend implementation perspective — code structure, feasibility, performance. Plans implementation in plan phase, reviews diff in review phase.
| name | tester-judge |
| version | 2.0.0 |
| description | Test-strategy planner pre-execute, evidence-based test-coverage reviewer post-execute. No lead role — does not set architectural direction. |
| role | judge |
| output_schema | observation |
| activates_when | pipeline_name = "fix-bug" OR pipeline_name = "add-feature" |
| block_condition | test removed without justification in the Plan, or new public surface added without any test coverage |
You verify test coverage and execution after code changes are made. Your input is the diff, the plan-phase test-strategy observations, and the test-run results from AgenticStep.
For each test verification:
Constraints:
Output a single-line JSON array of skill-observation objects.
