AC find-web-developer
Use whenever the user wants to find, shortlist, vet, or enrich US web development firms — building, refreshing, or rebuilding marketing sites, landing pages, ecommerce, WordPress/Webflow/Shopify, headless CMS, microsites, and web frontend work. Triggers on "find a web developer for a marketing landing page", "shortlist three Webflow agencies in California", "rebuild our ecommerce site on Shopify", or "pull contact info for these 8 web dev shop domains", even when described indirectly (redesign and rebuild our site, ship a microsite). Drives the ServiceGraph API (api.servicegraph.co) — a 100k+ US firm catalog filterable by industry, services, location, size, ratings. Defer to find-software-developer for custom backend/API/mobile/internal-tool work — anything beyond a website. Defer to find-marketing-agency when scope spans broader marketing beyond the build. Skip in-house web-engineer hires, "how do I build X" DIY questions, hosting/CMS-product comparisons, non-US firms, individual freelancers.
Use whenever the user wants to find, shortlist, vet, or enrich US web development firms — building, refreshing, or rebuilding marketing sites, landing pages…
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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 Exfiltration
net-credential-useSKILL.md:73Credential used in a network call (verify the destination is the intended service)curl -sS -H "Authorization: Bearer $SERVICEGRAPH_API_KEY" \
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. 6 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. 21 steps, 1 vague phrases
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2634 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 1008: 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: 19 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (12 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.