AC architecture-consistency-guardian
Enforce system-wide consistency before code changes. Activate for any task involving: refactoring across files, unifying variable/field/parameter names, consolidating state machines, cleaning legacy paths or fallbacks, aligning configuration sources, unifying database schema, consolidating service entry points, aligning documentation with code, or preventing local-only fixes that ignore global architecture contracts. Trigger signals: "统一一下", "全局改", "别只修当前文件", "检查所有引用", "清理 legacy", "状态机不统一", "配置路径不一致", "多个模块都要改", "架构收口", "重构", "修复兼容层", "把新旧逻辑统一", "unify", "consolidate", "clean up legacy", "align across modules", "single source of truth", "remove fallback", "schema drift". Also activate when a reported bug may stem from contract drift (e.g., mismatched field names, stale fallback paths, dual write targets, or status values not in the canonical set). NOT for: pure greenfield feature development with no cross-file impact, cosmetic lint/format changes, or single-file typo fixes with zero external references.
As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 64/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 57 steps
- 100Failures and branches. 6 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1871 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +3Description length 1019: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 13 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 16 headings
- +3Step-by-step instructions: 57 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 97.