AC find-law-firm
Use whenever the user wants to find, shortlist, vet, or enrich US B2B law firms — corporate, IP/patent, M&A and securities, employment, commercial litigation, regulatory/compliance, data privacy/cyber, real estate, and tax. Triggers on "find three boutique IP law firms in California", "shortlist M&A counsel for a Series-B fundraise", "patent prosecution for our hardware startup", or "pull contact info for these 10 law firm domains", even when described indirectly (outside counsel, cap-table review, GDPR/SOC2 oversight). Drives the ServiceGraph API (api.servicegraph.co) — a 100k+ US firm catalog filterable by industry, services, location, size, ratings. Skip personal/consumer legal services where the user is the end client (divorce, personal injury, criminal defense, family law, estate planning, wills) — the catalog is B2B-only. Also skip in-house GC hires, "is this NDA enforceable" DIY questions, non-US firms, individual freelancers.
Use whenever the user wants to find, shortlist, vet, or enrich US B2B law firms — corporate, IP/patent, M&A and securities, employment, commercial litigation…
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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
net-credential-useSKILL.md:80Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)curl -sS -H "Authorization: Bearer $SERVICEGRAPH_API_KEY" \
security skill
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 54/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 6 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 85Steps. 20 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2597 tokens
- 100Progress reporting. Reports progress
- 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 947: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Structure: 18 headings
- +3Step-by-step instructions: 20 items
- +4Has examples (11 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.