SKILLEMALL.ai
GitHub ↗ RU Sign in

BB metengine-data-agent

Real-time smart money analytics API for Polymarket prediction markets, Hyperliquid perpetual futures, and Meteora Solana LP/AMM pools. 63 endpoints. Pay-per-request via x402 on Solana Mainnet USDC. No API keys.

ClawHub Agent Skills author: Harsh Ghodkar v1.0.0 1 file body ≈ 18 350 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 66/100 · Nearly there — weak spots: when it triggers, execution cost, running it twice

IntegrationAI and agentsSoftware developmenttype 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
B
84/100
safety, quality, tests
Safety 60%
99
Quality 40%
62
Run on models
none yet
Process rating
B
66/100
Nearly there
Execution cost w 6
10
When it triggers w 12
20
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 1

✓ No critical or high findings

Medium and low: 1
  • low Dangerous commands cmd-cron-mention skill.md:55
    Mentions editing / listing crontab
    # Add to crontab: crontab -e

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 18350 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "base_url"
  • note frontmatter-key unknown frontmatter key "payment_protocol"
  • note frontmatter-key unknown frontmatter key "payment_network"
  • note frontmatter-key unknown frontmatter key "payment_currency"
  • note frontmatter-key unknown frontmatter key "auth"
  • note frontmatter-key unknown frontmatter key "free_endpoints"
  • note frontmatter-key unknown frontmatter key "health_check"
  • note frontmatter-key unknown frontmatter key "pricing_endpoint"
  • note frontmatter-key unknown frontmatter key "total_endpoints"

Process rating: all ten parameters 66/100

  • 10Execution cost. Instruction body is 18350 tokens: crowds the task out of the window
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 10 mutating operations with no state check
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 60 steps
  • 100Failures and branches. 3 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 16 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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 210: enough signal without eating the budget
  • +4Structure: 113 headings
  • +3Step-by-step instructions: 60 items
  • +3Output format is stated explicitly
  • +4Has examples (83 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.

External checks

ClawHub: suspicious
This market-data skill is mostly coherent, but it asks agents to auto-update themselves from a remote URL, persist wallet-related state, and handle payment signing material.
LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026