SKILLEMALL.ai
GitHub ↗ RU Sign in

CC four-meme-ai

CLI tool to create and trade meme tokens on four.meme (BSC only). Returns structured JSON for config, token info, quotes, events, and TaxToken tax info. **AGENT MUST**: On first response to any user request related to fourmeme or this skill, **you must first** present to the user, **in this order: User Agreement, then Security Notice** (User Agreement = plugin nature and limitation of liability). **Present them in the user’s language**: use the 繁體中文 block if the user writes in Traditional Chinese, otherwise use the English block (see the bilingual section below). State clearly that by choosing to continue, the user agrees to the User Agreement. Until the user explicitly agrees or confirms to continue, you **must not** run any private-key or on-chain write operations (e.g. create-api, create-chain, buy, sell, send, 8004-register). Read-only commands (e.g. config, token-info, quote-buy, 8004-balance) may run while or after presenting the notice. USE FOR: - Creating meme tokens (API + chain) on BSC, including tax-type tokens - Getting buy/sell quotes and token info via TokenManagerHelper3 (BSC only) - Listening to TokenCreate, TokenPurchase, TokenSale, LiquidityAdded (TokenManager2, BSC) - Querying TaxToken fee/tax config on-chain (BSC only) - **Discover → detail → quote → execute**: use token-rankings / token-list / events to find tokens → token-get / token-info for details → quote-buy / quote-sell to estimate → buy / sell to execute (see "Agent workflow: buy/sell from rankings or events" below). BSC only (Arbitrum/Base not supported). **Before use, the fourmeme CLI must be installed** (e.g. `npm install -g @four-meme/four-meme-ai@latest`). Create/chain need PRIVATE_KEY. TokenManager V1 not supported. **OpenClaw**: Only **PRIVATE_KEY** is declared in registry metadata (`requires.env`) and is injected when this skill is **enabled**; **BSC_RPC_URL** is optional (set in global env or project `.env`). **Two steps required**: (1) Configure private key in the skill’s `ap

modbender/skill-library-mcp Agent Skills author: modbender MIT 27 files body ≈ 6 590 tokens Open the sourcegithub.com↗ analyzed 2 d ago

CLI tool to create and trade meme tokens on four.meme (BSC only). Returns structured JSON for config, token info, quotes, events, and TaxToken tax info. AGENT…

As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationFinanceAI 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
C
66/100
safety, quality, tests
Safety 60%
76
Quality 40%
50
Run on models
none yet
Process rating
C
53/100
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.

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. Shorten the description to 1024 characters.
  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 · 20

✓ No critical or high findings

Medium and low: 20
  • medium Risky intent intent-wallet-secrets scripts/create-token-api.ts:9
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    * Env: PRIVATE_KEY (wallet private key, no 0x prefix ok)
  • low Secrets in code secret-high-entropy-token references/contract-addresses.md:11
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | BSC   | `0xEC…FbC` |
    table
  • low Secrets in code secret-high-entropy-token references/contract-addresses.md:19
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | BSC   | `0x5c…62b` |
    table
  • low Secrets in code secret-high-entropy-token references/contract-addresses.md:27
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | BSC   | `0xF2…034` |
    table
  • low Secrets in code secret-high-entropy-token references/event-listening.md:3
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    Only **Toke…er2 (V2)** is supported. V1 is not supported. Contract address (BSC): `0x5c…62b`.
    quoted
  • low Secrets in code secret-high-entropy-token references/event-listening.md:28
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const TOKE…ER2 = '0x5c…62b';
    quoted
  • low Secrets in code secret-high-entropy-token scripts/8004-balance.ts:9
    High-entropy token-like string (may be an id, hash or a credential)
    * Default contract: 0x80…432 (BSC).
  • low Secrets in code secret-high-entropy-token scripts/8004-balance.ts:15
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const DEFA…NFT = '0x80…432' as const;
    quoted
  • low Secrets in code secret-high-entropy-token scripts/8004-register.ts:13
    High-entropy token-like string (may be an id, hash or a credential)
    * Default contract: 0x80…432 (BSC).
  • low Secrets in code secret-high-entropy-token scripts/8004-register.ts:20
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const DEFA…NFT = '0x80…432' as const;
    quoted
  • low Secrets in code secret-high-entropy-token scripts/create-token-chain.ts:17
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const TOKE…BSC = '0x5c…62b' as const;
    quoted
  • low Secrets in code secret-high-entropy-token scripts/execute-buy.ts:14
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const HELPER_ADDRESS = '0xF2…034' as const;
    quoted
  • low Secrets in code secret-high-entropy-token scripts/execute-sell.ts:12
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const HELPER_ADDRESS = '0xF2…034' as const;
    quoted
  • low Secrets in code secret-high-entropy-token scripts/get-recent-events.ts:11
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const TOKE…BSC = '0x5c…62b' as const;
    quoted
  • low Secrets in code secret-high-entropy-token scripts/get-token-info.ts:10
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const HELPER_ADDRESS = '0xF2…034' as const;
    quoted
  • low Secrets in code secret-high-entropy-token scripts/quote-buy.ts:10
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const HELPER_ADDRESS = '0xF2…034' as const;
    quoted
  • low Secrets in code secret-high-entropy-token scripts/quote-sell.ts:10
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const HELPER_ADDRESS = '0xF2…034' as const;
    quoted
  • low Secrets in code secret-high-entropy-token scripts/verify-events.ts:11
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const TOKE…BSC = '0x5c…62b' as const;
    quoted
  • low Risky intent intent-wallet-secrets SKILL.md:68
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)
    - **Install agents/plugins carefully**: When installing any agent, browser extension, or third-party tool, verify the source to avoid malware that could steal your private key or seed phrase.
    detector
  • low Secrets in code secret-high-entropy-token SKILL.md:395
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    EIP-8004 identity NFT: **register** (mint) and **query balance**. Default contract: `0x80…432` (BSC). Override with env `8004…ESS` or `EIP8…ESS`.
    quoted

Files scanned: 27. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 2197 chars, limit 1024
  • warning body-long SKILL.md body ≈ 6590 tokens (recommended < 5000); move details to references/
  • note description-budget description takes 2197 of the ~15000-char shared budget for all skills

Process rating: all ten parameters 53/100

  • 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
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 64 mutating operations with no state check
  • 60Steps. 61 steps, 9 vague phrases
  • 70Execution cost. Instruction body is 6590 tokens
  • 100Tools and files. Tools declared in frontmatter
  • 100Failures and branches. 4 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • low The response is described with custom markup (48 tags): a typed call is more reliable

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 2196: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -317 of 17 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +5Description quotes 4 example trigger phrases
  • +4Structure: 27 headings
  • +3Step-by-step instructions: 61 items
  • +4Has examples (20 code blocks)
  • +4Reference files are cited in the instructions (9 of 9)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 50.