SKILLEMALL.ai
GitHub ↗ RU Sign in

AC find-service-providers

Use whenever the user wants to find, shortlist, vet, enrich, or research US professional-services firms — law, marketing, consulting, accounting, IT services, architecture, engineering, HR, PR, design, and similar B2B service providers. Triggers on requests like "find me a PPC agency in California", "shortlist three boutique IP law firms", "build a longlist of 50 mid-size IT consultancies", or "here are 12 agency domains — pull contact info and confirm which are US-based", even when the need is described indirectly without naming a category. Drives the ServiceGraph API (api.servicegraph.co) — a 100k+ US firm catalog with filters for industry, services, location, size, ratings, and third-party listings. Skip when the user is asking for personal/consumer services for themselves (an individual's own legal, tax, or medical needs), non-US firms, individual freelancers, retail/ecommerce/SaaS-product companies, recruiting-an-employee tasks, or general web research that doesn't need a structured firm directory.

ClawHub Agent Skills author: nostrband v1.0.0 MIT-0 2 files body ≈ 3 631 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Use whenever the user wants to find, shortlist, vet, enrich, or research US professional-services firms — law, marketing, consulting, accounting, IT services…

As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting

IntegrationFinanceAI and agentsPeople and hiringtype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
92/100
safety, quality, tests
Safety 60%
94
Quality 40%
89
Run on models
none yet
Process rating
C
59/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

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".

For the author

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

    For the model run — optional
    • 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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • medium Exfiltration net-credential-use SKILL.md:80
      Credential used in a network call (verify the destination is the intended service)
      curl -sS -H "Authorization: Bearer $SERVICEGRAPH_API_KEY" \
    • low Exfiltration read-dotenv skill-card.md:21
      Reads a .env file (negated — the text forbids it)
      Mitigation: Prefer the ServiceGraph MCP/OAuth flow or an already-exported SERVICEGRAPH_API_KEY, and do not source .env.local unless the user explicitly trusts that file. <br>
      negated

    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 59/100

    • 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
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 85Steps. 24 steps, 3 vague phrases
    • 100When it triggers. States when to use and when not to
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3631 tokens
    • 100Running it twice. Mutating operations check current state
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    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 1018: 120–800 characters recommended
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 4 example trigger phrases
    • +4Structure: 16 headings
    • +3Step-by-step instructions: 24 items
    • +3Output format is stated explicitly
    • +4Has examples (9 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.

    External checks

    ClawHub: suspicious
    The skill’s core ServiceGraph lookup purpose is coherent, but its credential-loading instructions can automatically execute local `.env.local` shell code without clear user consent.
    LLM: suspicious (high) · VirusTotal: · 3 Jun 2026