AC defect-prevention-expert
全生命周期质量保障专家，覆盖需求、设计、编码、测试、上线、运维全阶段的质量保障活动。 融合缺陷预防（逆向操作、依赖踏空、并发冲突、新旧兼容、状态迁移、因果判定）与质量度量、持续改进三大支柱， 帮助团队建立「预防-评审-度量-改进」的质量闭环，实现软件质量的持续提升。 Use when: - 需求/设计/编码/测试/上线/运维任一阶段，需要质量保障支持 - 需要识别潜在缺陷和风险点（预防阶段） - 需要评审已有产出的质量（评审阶段） - 需要量化评估质量水平（度量阶段） - 需要制定改进方案并跟踪效果（改进阶段） - Keywords: "缺陷预防", "质量保障", "全生命周期", "评审", "风险识别", "测试策略", "质量提升", "逆向操作", "依赖踏空", "并发冲突", "新旧兼容", "状态迁移", "因果图", "质量度量", "持续改进" Output: 根据阶段输出对应的分析报告（需求风险清单/设计缺陷报告/代码审查意见/测试场景补充建议/质量度量报告/改进方案等） Not for: 具体的代码修复（用 bug-fixing），性能优化（用 performance-optimization），纯代码重构（用 refactoring）
全生命周期质量保障专家，覆盖需求、设计、编码、测试、上线、运维全阶段的质量保障活动。 融合缺陷预防（逆向操作、依赖踏空、并发冲突、新旧兼容、状态迁移、因果判定）与质量度量、持续改进三大支柱， 帮助团队建立「预防-评审-度量-改进」的质量闭环，实现软件质量的持续提升。 Use when: -…
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6452 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 70Execution cost. Instruction body is 6452 tokens
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 200 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- low 22 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- -233 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 540: enough signal without eating the budget
- +4Structure: 107 headings
- +3Step-by-step instructions: 200 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.