opensea

Query NFT and token data, trade NFTs on Seaport, swap ERC20 tokens via DEX aggregator, configure wallet signing providers, and build/register/gate AI agent tools on Base. Covers the full OpenSea developer surface across CLI, MCP server, shell scripts, and SDK. Pick the right sub-skill using the routing table below, then read that sub-skill's SKILL.md for operational detail.

2.06x

Quality

77%

Does it follow best practices?

Impact

91%

2.06x

2 of 3 eval scenarios. Add 1 more for a full score.

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./SKILL.md

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-designed router: lean, unambiguous about the read-the-sub-skill-first workflow, with clean one-level-deep navigation. Its weaknesses are duplicated routing information between the table and the quick decision guide, a minor wallet-routing ambiguity, and sub-skill references that do not resolve to real files in this bundle.

Suggestions

Ensure the referenced sub-skill files (opensea-api/SKILL.md, opensea-marketplace/SKILL.md, opensea-swaps/SKILL.md, opensea-wallet/SKILL.md, opensea-tool-sdk/SKILL.md) ship in the bundle, or state explicitly where they live relative to this router.

Drop either the routing table or the 'Quick decision guide' — they carry the same mapping twice and cost tokens without adding information.

Clarify the wallet boundary, e.g. 'Signing/transaction setup → opensea-wallet; session/API authentication after setup → opensea-api', to remove the ambiguity between the two wallet-related rows.

Dimension	Reasoning	Score
Conciseness	The body is a lean ~20-line router with no concept explanations Claude already knows ('This router intentionally has no operational detail'). It falls short of 5 only because the same task-to-sub-skill mapping is stated twice — the routing table and the 'Quick decision guide' bullet list repeat each other nearly verbatim.	4 / 5
Actionability	The guidance is concrete and executable: every task maps to an explicit path to read ('[`opensea-marketplace/SKILL.md`](opensea-marketplace/SKILL.md)'), and the instruction 'Always read the sub-skill SKILL.md before executing' is unambiguous. It is not 5 because there is a minor gap — wallet-related routing is ambiguous between 'Configure wallet signing → opensea-wallet' and 'Authenticate a wallet for scoped REST or MCP → opensea-api'.	4 / 5
Workflow Clarity	The sequence is clear and appropriate for a router skill: identify the task, read the sub-skill SKILL.md, then execute, with the explicit guard 'Always read the sub-skill SKILL.md before executing'. It is not 5 because the duplicated routing mechanisms (table plus quick guide) and the two wallet-related rows create minor ambiguity about which sub-skill applies to a given wallet task.	4 / 5
Progressive Disclosure	The structure is textbook router design — a concise overview with well-signaled, one-level-deep links to sub-skill SKILL.md files. However, none of the six referenced sub-skill files (opensea-api/, opensea-marketplace/, opensea-swaps/, opensea-wallet/, opensea-tool-sdk/) exist in the evaluated bundle, so the references point at files that cannot be read; that material gap keeps it at 3 rather than 4-5.	3 / 5
	Total	15 / 20 Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific, third-person description that concretely enumerates capabilities across the OpenSea surface with excellent distinctiveness. Its one real gap is the absence of an explicit 'when to use' trigger clause, which caps completeness at 3 despite an otherwise exemplary 'what'.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user mentions OpenSea, NFTs, Seaport, trading or buying NFTs, swapping tokens, or building AI agent tools on Base.'

Add common natural phrasings users would say — 'buy/sell NFTs', 'NFT marketplace', 'listing', 'offer' — to strengthen trigger coverage.

Trim the router mechanics ('Pick the right sub-skill using the routing table below, then read that sub-skill's SKILL.md') from the description; that is body content, not capability description.

Dimension	Reasoning	Score
Specificity	The description enumerates five concrete actions — 'Query NFT and token data, trade NFTs on Seaport, swap ERC20 tokens via DEX aggregator, configure wallet signing providers, and build/register/gate AI agent tools on Base' — plus delivery surfaces ('CLI, MCP server, shell scripts, and SDK'), in third person, comprehensively covering the skill's scope. It is not a 4 because coverage is broad and every action is concrete with a named mechanism, not just a domain mention.	5 / 5
Completeness	The 'what' is clearly and concretely answered, but there is no 'Use when...' clause or equivalent explicit trigger guidance — the closest is the router-style instruction 'Pick the right sub-skill using the routing table below', which describes mechanics, not when Claude should invoke the skill. Per the judging guidelines, a missing 'when' caps completeness at 3.	3 / 5
Trigger Term Quality	Natural user terms are well covered: 'NFT', 'token data', 'trade NFTs', 'swap ERC20 tokens', 'wallet', 'Seaport', 'Base', 'OpenSea'. It falls short of 5 because common variations users would say are missing — 'buy/sell NFTs', 'marketplace', 'listing', 'offer', 'floor price' — so a few natural triggers are absent.	4 / 5
Distinctiveness Conflict Risk	The description occupies a clear niche (OpenSea developer surface, Seaport, ERC-8257, Base) with distinct trigger terms that no generic skill would claim, so conflict risk is minimal. It is not lower because nothing in it overlaps meaningfully with generic wallet, token, or document skills.	5 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 6 missing	Warning

	Total	14 / 16 Passed

Repository: ProjectOpenSea/opensea-skill
Path: SKILL.md
Commit: b0fa63f

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.