SKILLEMALL.ai
GitHub ↗ RU Sign in

AC french-business-analyser

Verified French business data for autonomous B2B agents. Without this MCP, agents hallucinate financial data. With it, they get real-time signals from 9 official registries. 12 tools, pay-per-call.

ClawHub Agent Skills author: Vannelier v2.2.0 MIT-0 4 files body ≈ 3 868 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 61/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice

AnalyzerAI and agentstype 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
91/100
safety, quality, tests
Safety 60%
98
Quality 40%
80
Run on models
none yet
Process rating
C
61/100
Has gaps
Result and completion w 14
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

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
    • low Risky intent intent-wallet-secrets SKILL.md:78
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)
      **Server-side (self-hosters only):** see the `.env.example` in the repository. The service never signs blockchain transactions — it only verifies incoming x402 payment proofs — so no wallet private ke
      detector
    • low Exfiltration read-dotenv SKILL.md:86
      Reads a .env file
      cp .env.example .env  # fill in your credentials

    Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "docs"
    • note frontmatter-key unknown frontmatter key "sourceCode"

    Process rating: all ten parameters 61/100

    • 0Result and completion. Does not say what the result is
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 2 mutating operations with no state check
    • 60Tools and files. Uses tools (web) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 73 steps
    • 100Failures and branches. 1 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3868 tokens
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • 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

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • -2localhost URLs: will not work for another user
    • +1No license
    • +2Single-language instructions
    • +3Description length 197: enough signal without eating the budget
    • +4Structure: 26 headings
    • +3Step-by-step instructions: 73 items
    • +4Has examples (2 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.

    External checks

    ClawHub: clean
    This is a clearly disclosed French business lookup skill with paid remote checks, and its sensitive data flows and consent requirements are stated.
    LLM: benign (high) · VirusTotal: · 29 May 2026