AC pharmaceuticals-exploration
Used for answering drug-related questions. For early-stage drugs, search and summarize related patents, academic literature, database records, clinical trials, patents, and licensing transaction documents to answer questions. Activate when users explicitly mention specific drugs or when calling disease_investigation_skill or target_intelligence_skill for assistance - Specify output of a drug's characteristics or other records - Search for drugs related to a specific disease - Search for drugs targeting a specific target Typical queries - Please tell me about semaglutide targeting GLP-1R for diabetes treatment - What drug is remdesivir? - Drugs used to treat hepatitis B - ALN-F12
Used for answering drug-related questions.
As a process C 56/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, running it twice
The same skill appears in 1 more place: ClawHub
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5341 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 56/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Steps. 63 steps, 10 vague phrases
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 5341 tokens
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- low The response is described with custom markup (10 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 687: enough signal without eating the budget
- +4Structure: 30 headings
- +3Step-by-step instructions: 63 items
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.