analyzing-nft-rarity

Calculate NFT rarity scores and rank tokens by trait uniqueness. Use when analyzing NFT collections, checking token rarity, or comparing NFTs. Trigger with phrases like "check NFT rarity", "analyze collection", "rank tokens", "compare NFTs".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

87%

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

A well-organized, actionable skill body with concrete commands, a concise algorithm table, and properly signaled one-level references to verified bundle files. The main weakness is workflow clarity: the skill is presented as independent subcommands with no validation checkpoints or sequencing between steps.

Suggestions

Add a brief validation/checkpoint step for operations that touch external state, e.g. confirm the OpenSea fetch returned tokens before computing rarity, and verify export files are non-empty after writing.

Either reframe the numbered sections as a sequenced workflow (fetch → parse → score → rank → export) or note explicitly that the subcommands are independent modes so the lack of inter-step sequencing is intentional.

Reference the existing references/implementation.md from the body (or remove it) so every bundle file is either linked or pruned.

Dimension	Reasoning	Score
Conciseness	The body is lean — Overview bullets, command blocks, an algorithm table, and pointer sections — without explaining concepts Claude already knows (e.g. what an NFT or entropy is); every section earns its place. The Overview bullets are mildly redundant with the Instructions but not enough to drop to a 2.	3 / 3
Actionability	Provides copy-paste-ready commands with real collection names ('python3 rarity_analyzer.py collection boredapeyachtclub', export/cache subcommands) and concrete option flags; not a 2 because guidance is fully executable rather than pseudocode or abstract.	3 / 3
Workflow Clarity	Sections are numbered and each subcommand is unambiguous, but the skill is a set of independent read-only CLI modes rather than a sequenced multi-step process, and no validation/verification checkpoints are given (e.g. confirm the API fetch succeeded before ranking). Not a 3 because there are no explicit validation steps; not a 1 because the per-mode instructions are clear.	2 / 3
Progressive Disclosure	Body is an overview that signals one-level-deep references ('See ${CLAUDE_SKILL_DIR}/references/errors.md for:' and 'examples.md for:') with bullet lists of their contents; both referenced files exist and are single-level, matching the well-signaled-reference anchor.	3 / 3
	Total	11 / 12 Passed

Description

100%

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, third-person description that states concrete capabilities, provides explicit 'Use when' triggers, and lists natural user phrases. It cleanly answers both what the skill does and when to invoke it with minimal fluff.

Dimension	Reasoning	Score
Specificity	Quotes 'Calculate NFT rarity scores and rank tokens by trait uniqueness' — two concrete, specific actions named, matching the multiple-concrete-actions anchor; not a 2 because actions are explicit and specific rather than a partial domain listing.	3 / 3
Completeness	Explicitly answers both 'what' (Calculate NFT rarity scores and rank tokens) and 'when' (Use when analyzing NFT collections…), with explicit trigger guidance; not a 2 because the 'when' is stated rather than merely implied.	3 / 3
Trigger Term Quality	Lists natural user phrasings — 'analyzing NFT collections, checking token rarity, or comparing NFTs' plus 'Trigger with phrases like "check NFT rarity", "analyze collection", "rank tokens", "compare NFTs"' — good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	'NFT rarity' is a clear niche with distinct triggers unlikely to fire for unrelated skills; not a 2 because the domain and triggers are specific rather than overlapping with broad categories.	3 / 3
	Total	12 / 12 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 6e3a65f

Reviewed: 4 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.