AC company-profiling
Accurately and efficiently extract and analyze intelligence based on massive pharmaceutical data to provide users with professional company profiles and investment/collaboration recommendations. Typical user behavior involves inquiring about a pharmaceutical company's situation. This skill should be invoked when user questions involve the following content 1、Company overview 2、Company financing history analysis 3、Company pipeline analysis 4、Company drug transaction analysis 5、Company's important patent layout in a specific field Typical queries - Give me an overview of Arrowhead Pharmaceuticals - What is BioNTech's R&D pipeline? - Analyze Roche's patent layout in small nucleic acid technologies - What BD deals has Pfizer made in the last two years? - Tell me about Moderna's financing history
Accurately and efficiently extract and analyze intelligence based on massive pharmaceutical data to provide users with professional company profiles and…
As a process C 58/100 · 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
- 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
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 58/100
- 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. 39 steps, 11 vague phrases
- 60Result and completion. Output format stated, no completion criterion
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3416 tokens
- 100Progress reporting. Reports progress
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)
- +3Description length 802: 120–800 characters recommended
- +2Single-language instructions
- +4Structure: 24 headings
- +3Step-by-step instructions: 39 items
- +3Output format is stated explicitly
- +4Has examples (6 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.