AC error-recovery
Agent 错误恢复与容错。当 session 遇到限速、crash 或模型失败时使用。不适用于工具重试死循环（用 tool-governance）或 agent 提前停止（用 execution-loop）。参见 tool-governance（错误追踪数据）。
As a process C 54/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, consistency
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: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "triggers"
Process rating: all ten parameters 54/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 5 mutating operations with no state check
- 40Consistency. Frontmatter name (error-recovery) differs from the folder (eh-error-recovery)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 31 steps
- 100Execution cost. Instruction body is 1819 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (7 tags): a typed call is more reliable
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)
- +2Single-language instructions
- +3Description length 132: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 31 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (7 of 8)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.
External checks
ClawHub: suspicious
This is a legitimate error-recovery skill, but some automatic recovery steps can press keys, delete lock files, and persist session content without enough scoping or safeguards.
LLM: suspicious (high) · VirusTotal: · 29 May 2026