AC evidence-cleaner
LLM通用证据清洗技能。将原始搜索结果、网页片段、OCR残片等原始材料清洗为可用证据，减少脏输入、伪实体、重复片段和错域材料对后续判断的污染。在搜索结果返回后、进入freshness判定或叙事生成前使用。触发条件：搜索结果质量差、证据量大但信噪比低、需要标准化证据格式。
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
- 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 51/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 8 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 47 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 987 tokens
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 135: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 47 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.
External checks
ClawHub: suspicious
The skills are mostly coherent maintenance guidance, but one bundled review helper defaults to running a nested reviewer with full sandbox bypass, which deserves user review before installation.
LLM: suspicious (medium) · VirusTotal: · 29 May 2026