AC improvement-learner
当需要检查 skill 质量评分、自动优化 SKILL.md 结构、追踪评估分数变化趋势、或「评分低了想知道哪里扣分」时使用。6维结构评估 + HOT/WARM/COLD 三层记忆 + Pareto front。不用于候选语义打分（用 improvement-discriminator）或全流程编排（用 improvement-orchestrator）。
As a process C 50/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches
The same skill appears in 1 more place: ClawHub
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: 5. 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 50/100
- 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
- 40Consistency. Frontmatter name (improvement-learner) differs from the folder (auto-improvement-learner)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 9 steps
- 100Execution cost. Instruction body is 712 tokens
- 100Running it twice. No mutating operations
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 179: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 9 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +3All 2 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.
External checks
ClawHub: suspicious
This skill is meant to improve other skills, but it can modify target directories, run target tests, call the local Claude CLI, and make git commits without clear opt-in boundaries.
LLM: suspicious (high) · VirusTotal: · 29 May 2026