BD servicegraph
The branded entry point to ServiceGraph — use whenever the user explicitly names **ServiceGraph** — "use ServiceGraph to…", "what datasets does ServiceGraph have", "search ServiceGraph for…", "look this up in ServiceGraph", "pull contacts from ServiceGraph for these domains", "how many credits do I have on ServiceGraph". ServiceGraph is a multi-dataset platform of metrics-enriched business data for founders — where to launch, who to email, who to hire. This skill explains how to drive the API (api.servicegraph.co / mcp.servicegraph.co) against ANY dataset — discover what datasets exist, discover a dataset's schema and filters, search free brief rows, and unlock contact + metric detail with credits. Dataset-agnostic by design — it discovers everything through the API and never assumes which datasets or fields exist. When the user describes an intent WITHOUT naming ServiceGraph (e.g. "find a PR agency in NY"), defer to the matching specific skill (find-pr-agency, find-marketing-agency, find-law-firm, …); this skill is for explicit ServiceGraph requests and for datasets no specific skill covers yet. Skip non-US firms, consumer/personal services, and individual freelancers.
The branded entry point to ServiceGraph — use whenever the user explicitly names ServiceGraph — "use ServiceGraph to…", "what datasets does ServiceGraph…
As a process D 47/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- Shorten the description to 1024 characters.
- 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
- error
description-longdescription is 1188 chars, limit 1024
Process rating: all ten parameters 47/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50Steps. 2 steps
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 834 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1188: 120–800 characters recommended
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Structure: 5 headings
Quality base 70; lint remarks subtract, signals add up to 100. Result: 54.