BC agent-extract
将技能/功能从 main agent 剥离成独立 agent，实现 session 隔离和独立保活。Use when: (1) 用户想把某个功能独立成单独的 agent，(2) 需要隔离 session 避免污染，(3) 需要 agent 独立保活运行。触发词：剥离 agent、独立 agent、拆分 agent、创建独立 agent。
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: 将技能/功能从 main agent 剥离成独立 agent，实现 session 隔离和独立保活。Use when: (1) 用户… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
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. 1 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 34 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1555 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
- -31 of 1 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 169: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (12 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.
External checks
ClawHub: suspicious
This skill has a coherent agent-splitting purpose, but it gives broad local agent-management instructions that can duplicate sensitive context and alter existing heartbeat behavior too aggressively.
LLM: suspicious (medium) · VirusTotal: suspicious · 28 May 2026