AB pharma-intelligence
In-depth, multi-region pharmaceutical intelligence search and synthesis, plus drug repurposing, target discovery, clinical evidence review, and bioactivity analysis. Use this skill whenever the user asks about drug approvals, clinical trials, regulatory submissions, pipeline assets, patent landscapes, competitive intelligence, scientific evidence, disease targets, genetic associations, or compound bioactivity for any drug, target, indication, or company — especially when coverage of China, US, Europe, Japan, South Korea, or Australia is needed. Trigger even for casual queries like "what's the approval status of X in China", "find trials for Y in Japan", "compare pipeline coverage across regions", "find drugs for disease Z", or "what targets are associated with condition W". Always consult this skill before answering any pharma or biomedical research question that requires source-grounded data.
As a process B 73/100 · Nearly there — weak spots: inputs and preconditions, running it twice, 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: 7. 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 73/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 85Steps. 88 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3876 tokens
- low 10 top-level sections: this looks like several domains in one skill
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)
- +3Description length 906: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Structure: 23 headings
- +3Step-by-step instructions: 88 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.