SKILLEMALL.ai
GitHub ↗ RU Sign in

BB traderouter

Solana swap execution, MEV-protected transaction submission, wallet scanning, and market-cap-based limit/trailing orders via the TradeRouter API. Use when the user wants to: swap SPL tokens on Solana (buy or sell), check wallet token holdings, submit signed transactions through an MEV-protected priority lane, place limit orders (buy/sell at a target market cap), set trailing stop orders (trailing_sell/trailing_buy), manage existing orders (check, list, cancel, extend), or implement DCA strategies. No API key required — wallet address is the only identity. Supports REST endpoints POST /swap, POST /holdings, POST /protect, and WebSocket wss://api.traderouter.ai/ws for limit orders.

modbender/skill-library-mcp Agent Skills author: modbender MIT 1 file body ≈ 18 910 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Solana swap execution, MEV-protected transaction submission, wallet scanning, and market-cap-based limit/trailing orders via the TradeRouter API.

As a process B 73/100 · Nearly there — weak spots: inputs and preconditions, consistency, execution cost

IntegrationSoftware developmentInfrastructureAI 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
B
86/100
safety, quality, tests
Safety 60%
92
Quality 40%
77
Run on models
none yet
Process rating
B
73/100
Nearly there
Execution cost w 6
10
Inputs and preconditions w 11
30
Consistency w 8
40
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.

Risky intent 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 purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.

For the author

Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.

How to improve

  1. 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 · 4

✓ No critical or high findings

Medium and low: 4
  • medium Risky intent intent-wallet-secrets SKILL.md:231
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    5. **Sign** with wallet private key
  • low Secrets in code secret-high-entropy-token SKILL.md:148
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "mint": "FFKw…onk",
    quoted
  • low Risky intent intent-wallet-secrets SKILL.md:256
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    3. **Client:** Sign the **nonce** (UTF-8 bytes) with the **wallet's private key** (Ed25519). You **must** have the wallet private key to use the WebSocket for orders; without it you cannot register su
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:586
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    process.env.TRADEROUTER_SERVER_PUBKEY || 'EXX3…Jd4'
    quoted

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

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 18910 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 73/100

  • 10Execution cost. Instruction body is 18910 tokens: crowds the task out of the window
  • 30Inputs and preconditions. Does not say what the process needs to start
  • 40Consistency. Frontmatter name (traderouter) differs from the folder (trade-router)
  • 60Tools and files. Uses tools (web, python) that frontmatter does not declare
  • 85Steps. 83 steps, 1 vague phrases
  • 100Result and completion. Output format and completion criterion are stated
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 2 branches, has a failure section
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 25 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 688: enough signal without eating the budget
  • +4Structure: 56 headings
  • +3Step-by-step instructions: 83 items
  • +3Output format is stated explicitly
  • +4Has examples (25 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.