AC network-pharmacology
Build evidence-graded compound–target–disease network-pharmacology hypotheses for natural products, herbal medicines, formulae, and small molecules using live SciMiner tools plus public life-science evidence. Use when an agent must curate compounds, predict or verify targets, prioritize disease-relevant targets, assess ADMET or off-target risk, run docking as supporting evidence, create interactive network visualizations, or produce reproducible network-pharmacology reports without R.
Build evidence-graded compound–target–disease network-pharmacology hypotheses for natural products, herbal medicines, formulae, and small molecules using live…
As a process C 52/100 · Has gaps — weak spots: result and completion, failures and branches, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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
-
medium Broad scope
meta-requests-env-secretSKILL.md:1Skill asks the runtime to inject credential env vars into its sandbox: SCIMINER_API_KEY — verify each one is needed for the stated purposerequired_environment_variables: SCIMINER_API_KEY
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "required_environment_variables"
Process rating: all ten parameters 52/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 45 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2565 tokens
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 489: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 45 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.