AB openclaw-user-profiler
Two things: (1) Build a user.md through conversation so your OpenClaw lobster knows who it's working with. (2) Recommend Claude Code Skills based on the user's role — 42 roles across 11 categories, three-level inheritance model. Profile mode: chat → user.md. Recommend mode: role → curated skill list. Use when a user wants their lobster to learn about them, update their profile, or discover which Skills fit their role. Not for: editing SOUL.md (use the forge) or general-purpose Q&A. Triggers: know me, get to know me, write user.md, update my profile, profile me, recommend skills, skills for my role, what skills should I use, I'm an engineer, I'm a PM, 了解我, 认识我, 推荐 skill, 用户画像。
As a process B 75/100 · Nearly there — weak spots: inputs and preconditions, progress reporting
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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 75/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 40 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1977 tokens
- 100Running it twice. Mutating operations check current state
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
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 684: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 40 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.