AC safety-kb-import
安全生产法规标准导入工具。当用户需要导入新法规或标准到知识库、PDF文本提取、条款拆分、批量导入、数据质量验证时使用。触发词：导入法规、添加标准、入库、导入知识库、补充标准、PDF提取文本、拆分条款、KB导入、safety-review import
As a process C 61/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice
How to improve
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: 3. 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 61/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 9 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 45 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2630 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -213 emoji in the instructions: noise for the model
- +2Single-language instructions
- +3Description length 125: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 45 items
- +4Has examples (10 code blocks)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.
External checks
ClawHub: suspicious
This is a legitimate safety knowledge-base import tool, but it can overwrite and delete local database content and its activation scope is broader than the import-only workflow needs.
LLM: suspicious (high) · VirusTotal: · 29 May 2026