菜单
This skill should be used when the user asks to 'verify tests', 'check coverage', 'detect phantom completions', 'check spec drift', or needs guidance on Phase 8 verification. Also trigger on 'sdd test', 'test traceability', 'verification report', or 'gate criteria'.
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
This skill should be used when the user asks to 'research codebase', 'scan tech stack', 'import documents', 'discovery questions', or needs guidance on Phase 1 research. Also trigger on 'sdd research', 'brownfield scan', 'import transcript', or 'check ecosystem'.
Use for Phase 2 (Specify): write SPECIFICATION.md with EARS, REQ-IDs, and acceptance criteria. Trigger on sdd_write_spec, sdd_turnkey_spec, sdd_validate_ears, or /specky-specify.
Use for Phase 4 (Design): produce DESIGN.md with architecture, API contracts, data model, and Mermaid diagrams. Trigger on sdd_write_design, sdd_generate_all_diagrams, or /specky-design.
Use for contracted implementation planning, executable TDD bindings, IaC, Docker, devcontainer, local environment, or Codespaces tools after an APPROVE analysis gate.
Use when starting or resuming Specky work, selecting lifecycle/workload/mode/capabilities, diagnosing config/state, or choosing an agent/tool.
This skill should be used when the user asks to 'orchestrate pipeline', 'run full pipeline', 'coordinate phases', 'advance phase', or needs guidance on end-to-end pipeline execution. Also trigger on 'specky orchestrate', 'phase transition', 'LGTM gate', 'pipeline status', or 'which agent for this phase'.
| name | specky-test-verifier |
| description | This skill should be used when the user asks to 'verify tests', 'check coverage', 'detect phantom completions', 'check spec drift', or needs guidance on Phase 8 verification. Also trigger on 'sdd test', 'test traceability', 'verification report', or 'gate criteria'. |
The feature must enable tdd. Read these persisted values before running anything:
Specky does not generate TODO tests or in-file fake system models. A binding must cover every requirement ID and contain executable, nontrivial assertions.
sdd_verify_tests with spec_dir, feature_number, and test_results_json.effectiveCoverage to the response’s contracted coverage_threshold and meets_threshold; do not assume 80%, 90%, or 100% globally.sdd_verify_tasks with explicit code_paths to identify task evidence and phantom completions.sdd_check_sync with explicit code paths to identify requirement drift.REQ-* IDs.expect(true), assert True, TODO bodies) are rejected by contract validation.Present coverage by requirement, failing and untested IDs, threshold result, task verification, and drift evidence. The server computes the gate; do not manufacture PASS/FAIL from prose.