BB openclaw-for-doctor
Doctor-grade clinical assistant for evidence lookup, case discussion, and deliverable generation. Use when the user is a clinician, medical educator, or researcher asking for any of: (1) guideline/literature lookups with evidence anchors, (2) complex case discussion and differential diagnosis reasoning, (3) teaching materials (case conference slides, rounds prep, residency coaching), (4) research starter outputs (literature matrix, hypothesis notes, protocol ideas). Auto-routes to the right role stage and reasoning mode based on query intent. Triggers on keywords like: diagnosis, differential, guideline, treatment, sepsis, stroke, dosing, contraindication, case, teaching material, slides, manuscript, research, hypothesis.
As a process B 74/100 · 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Exfiltration
read-dotenvREADME.md:104Reads a .env filecp .env.example .env
Files scanned: 32. 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: Doctor-grade clinical assistant for evidence lookup, case discussi… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 74/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 60Result and completion. Output format stated, no completion criterion
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 17 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1003 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +4No input/output examples
- -31 of 1 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 731: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 17 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.