AC find-seo-agency
Use whenever the user wants to find, shortlist, vet, or enrich US SEO agencies — technical SEO, on-page/off-page, link-building, content-led SEO, local SEO, ecommerce SEO, B2B SEO, and SEO audits. Triggers on "find me an SEO agency in Texas", "shortlist three technical SEO consultancies for SaaS", "link-building and on-page for our ecommerce store", or "pull contact info for these 8 SEO firm domains", even when described indirectly (organic traffic flat, improve Google rankings, search visibility). Drives the ServiceGraph API (api.servicegraph.co) — a 100k+ US firm catalog filterable by industry, services, location, size, ratings, third-party listings. Defer to find-marketing-agency when scope spans multiple marketing services beyond SEO. Skip SEM/PPC/paid-search asks, web-dev asks (use find-web-developer), "how do I rank" DIY questions, SEO tool recommendations (Ahrefs, Semrush), in-house SEO hires, non-US firms, individual freelancers.
Use whenever the user wants to find, shortlist, vet, or enrich US SEO agencies — technical SEO, on-page/off-page, link-building, content-led SEO, local SEO…
As a process C 57/100 · 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:72Credential 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 57/100
- 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. 7 mutating operations with no state check
- 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. 17 steps, 1 vague phrases
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2628 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 951: 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: 17 items
- +4Has examples (12 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.