Use this skill when running or interpreting VCSDD adversarial reviews. Provides calibration guidance for the Adversary agent, finding severity classification, and anti-leniency enforcement patterns.
中文简介正在准备中。当前显示原文说明。
Use this skill when writing sprint contracts in VCSDD strict mode. Provides grading criteria patterns, dimension weight guidelines, and pass threshold formulation for the 5 review dimensions.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
| Dimension | Focus | Typical Weight |
|---|---|---|
| spec_fidelity | Do tests and code match the spec? | 0.30 |
| edge_case_coverage | Are edge cases from spec tested? | 0.25 |
| implementation_correctness | Is logic correct? | 0.25 |
| structural_integrity | Is code organized well? | 0.10 |
| verification_readiness | Is pure core isolatable? | 0.10 |
Pass thresholds MUST be binary-evaluable (yes/no), NOT numeric:
Good (binary):
Bad (subjective):
status: draft/vcsdd-contract-review → adversary reviews criteria against spec/tests/sourcenegotiationRound field)status: approved---
sprintNumber: 1
feature: my-feature
scope: "Core parsing logic with error handling"
negotiationRound: 0
status: draft
criteria:
- id: CRIT-001
dimension: spec_fidelity
description: All REQ-XXX items have corresponding test cases
weight: 0.30
passThreshold: Every requirement ID (REQ-NNN) in behavioral-spec.md appears in at least one test function name or test docstring
beadId: BEAD-001
- id: CRIT-002
dimension: edge_case_coverage
description: Critical edge cases from the spec are tested
weight: 0.25
passThreshold: Every critical edge case section in behavioral-spec.md has an explicit test
---
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Use this skill when running or interpreting VCSDD adversarial reviews. Provides calibration guidance for the Adversary agent, finding severity classification, and anti-leniency enforcement patterns.
中文简介正在准备中。当前显示原文说明。
Run Phase 3 (adversarial review) for the active VCSDD feature. Spawns a fresh vcsdd-adversary agent with zero Builder context to review implementation against spec. Produces binary PASS/FAIL verdict per dimension.
中文简介正在准备中。当前显示原文说明。
Create a git commit for the current VCSDD phase. Auto-generates a conventional commit message from state.json including phase, sprint, gate verdict, and affected bead IDs. Tags with vcsdd/<feature>/phase-<id>.
中文简介正在准备中。当前显示原文说明。
Run the strict-mode sprint contract review after Phase 2c. Spawns a fresh vcsdd-adversary instance to review `contracts/sprint-N.md` and writes a PASS/FAIL verdict under `reviews/contracts/sprint-N/output/`.
中文简介正在准备中。当前显示原文说明。
Run Phase 6 (convergence check) for the active VCSDD feature. Validates four-dimensional convergence: finding diminishment, finding specificity, criteria coverage, and duplicate detection.
中文简介正在准备中。当前显示原文说明。
Use this skill during Phase 6 convergence checks. Provides four-dimensional convergence analysis, hallucination detection, and duplicate finding identification.
中文简介正在准备中。当前显示原文说明。