opensea-api
Query OpenSea marketplace data via the official CLI, MCP server, or shell scripts. Get floor prices, collection stats, NFT details, token data, trending collections, drops, events, and search across Ethereum, Base, Arbitrum, Polygon, and more. Read-only operations; for trading use opensea-marketplace, for token swaps use opensea-swaps.
65
80%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./opensea-api/SKILL.mdQuality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description with excellent specificity, rich trigger terms, and outstanding distinctiveness through explicit disambiguation from related skills. The main weakness is the absence of an explicit 'Use when...' clause, which would elevate completeness. The description effectively communicates scope and boundaries but could benefit from a brief trigger guidance sentence.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about NFT prices, collection data, OpenSea marketplace stats, or wants to look up NFT/token information without executing trades.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Get floor prices, collection stats, NFT details, token data, trending collections, drops, events, and search' across named blockchains. Very detailed enumeration of capabilities. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with detailed capabilities, but lacks an explicit 'Use when...' clause. The description implies when to use it but never states it explicitly, and the rubric guidelines cap completeness at 2 when a 'Use when' clause is missing. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'OpenSea', 'floor prices', 'collection stats', 'NFT details', 'trending collections', 'drops', 'events', plus specific chain names like 'Ethereum', 'Base', 'Arbitrum', 'Polygon'. These are all terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit boundary-setting: 'Read-only operations; for trading use opensea-marketplace, for token swaps use opensea-swaps.' This directly disambiguates from related skills and creates a clear niche. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable and well-structured API reference skill with excellent concrete guidance, clear error handling workflows, and strong security considerations. Its main weakness is token efficiency — the document is very long due to exhaustive inline reference tables for three different interfaces (CLI, MCP, shell scripts) that cover overlapping functionality, much of which could be offloaded to separate reference files. The workflow clarity is strong, particularly the pre-bulk-operation checklist and error handling guidance.
Suggestions
Move the exhaustive shell scripts reference tables and MCP tool parameter details into separate reference files (e.g., `references/shell-scripts.md`, `references/mcp-tools.md`) and link to them from the main SKILL.md to reduce token count by ~50%.
Consolidate the three parallel interface tables (CLI, MCP, shell scripts) into a single task-oriented table with columns for each interface, eliminating the repetition of listing the same operations three times in different sections.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but quite long (~400+ lines). Many tables are thorough reference material, but there's significant repetition between CLI commands, MCP tools, and shell scripts that cover the same operations. The MCP tool parameter tables are detailed but could be in a separate reference file. Some sections like the shell scripts reference are exhaustive listings that inflate the token count. | 2 / 3 |
Actionability | Excellent actionability throughout — the quick start section has copy-paste ready commands, every task has concrete CLI commands with exact syntax, shell script paths are specified, MCP tool names are given, and code examples (TypeScript SDK, bash) are executable. The trait filtering example and MCP server setup JSON are particularly well done. | 3 / 3 |
Workflow Clarity | The pre-bulk-operation checklist is an excellent validation workflow with explicit sequential steps and verification checkpoints. Error handling is well-documented with specific HTTP codes and recommended actions. The security section provides clear boundaries for handling untrusted data. The scope_in/scope_out table with handoff guidance is a strong workflow decision aid. | 3 / 3 |
Progressive Disclosure | The skill references external files (`references/rest-api.md`, `references/stream-api.md`) appropriately, but the SKILL.md itself is monolithic — the exhaustive shell scripts reference tables, full MCP tool parameter documentation, and SDK examples could be split into separate reference files. The content that's inline would benefit from being organized into referenced sub-documents to keep the main skill leaner. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (558 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- ProjectOpenSea/opensea-skill
- Commit
10f23f8
- Reviewed
Table of Contents
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.