AC session-cleanup
Session cleanup skill for Claw-family agents (OpenClaw, WorkBuddy, QClaw, etc.). This skill should be used when the user wants to track and clean up temporary files, scripts, installed skills, libraries, and software generated during a conversation session. Trigger phrases include: "开启清理追踪", "session cleanup", "会话清理", "清理垃圾文件", "清理对话文件", "清理临时文件", "结束清理", "列出临时文件", "清理 Skill", "卸载多余库", "clean up session", "cleanup now", "帮我清理".
As a process C 63/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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: 8. 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 63/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (session-cleanup) differs from the folder (super-session-cleanup)
- 60Tools and files. Uses tools (python, node) that frontmatter does not declare
- 100Steps. 74 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 8 branches, has a failure section
- 100Execution cost. Instruction body is 3256 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (18 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- -33 of 4 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +3Description length 431: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 74 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.