SKILLEMALL.ai
GitHub ↗ RU Sign in

BD OpenSea API

Query NFT data, trade on the Seaport marketplace, and swap ERC20 tokens across Ethereum, Base, Arbitrum, Optimism, Polygon, and more.

modbender/skill-library-mcp Agent Skills author: modbender MIT 25 files · 19 scripts body ≈ 2 769 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Query NFT data, trade on the Seaport marketplace, and swap ERC20 tokens across Ethereum, Base, Arbitrum, Optimism, Polygon, and more.

As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, failures and branches

IntegrationCommerceAI and agentsInfrastructuretype 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
82/100
safety, quality, tests
Safety 60%
88
Quality 40%
74
Run on models
none yet
Process rating
D
49/100
Unfinished process
Result and completion w 14
0
Failures and branches w 10
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

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 8

✓ No critical or high findings

Medium and low: 8
  • medium Exfiltration net-credential-use scripts/opensea-get.sh:25
    Credential used in a network call (verify the destination is the intended service)
    curl -sS -H "x-api-key: $key" "$url"
  • low Secrets in code secret-high-entropy-token references/marketplace-api.md:360
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | All chains | `0x00…4dC` |
    table
  • low Secrets in code secret-high-entropy-token references/seaport.md:14
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | All EVM chains | `0x00…395` |
    table
  • low Secrets in code secret-high-entropy-token references/seaport.md:16
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    Legacy Seaport 1.4: `0x00…4dC`
    quoted
  • low Secrets in code secret-high-entropy-token references/seaport.md:56
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "protocol_address": "0x00…395"
    quoted
  • low Secrets in code secret-high-entropy-token references/seaport.md:102
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    name: 'fulf…6yc',
    quoted
  • low Secrets in code secret-high-entropy-token references/seaport.md:144
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    listing: { hash: orderHash, chain, protocol_address: '0x00…395' },
    quoted
  • low Secrets in code secret-high-entropy-token references/token-swaps.md:148
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | USDC | `0x83…913` |
    table

Files scanned: 25. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 49/100

  • 0Result and completion. Does not say what the result is
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (OpenSea API) differs from the folder (opensea-mcp)
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 29 steps
  • 100Execution cost. Instruction body is 2769 tokens
  • 100Running it twice. No mutating operations
  • low 10 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (32 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

  • +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
  • +1No license
  • +2Single-language instructions
  • +3Description length 133: enough signal without eating the budget
  • +4Structure: 33 headings
  • +3Step-by-step instructions: 29 items
  • +4Has examples (12 code blocks)
  • +4Reference files are cited in the instructions (5 of 5)
  • +3All 19 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.