auditing-wallet-security

Audit wallet security by analyzing token approvals, permissions, and transaction patterns. Use when checking wallet security, reviewing approvals, or assessing risk exposure. Trigger with phrases like "audit wallet", "check approvals", "security scan", or "revoke tokens".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

72%

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

The content is highly actionable with concrete, executable commands and a clean progressive-disclosure structure backed by real reference files. Its main weaknesses are mild verbosity from decorative output mockups and a lack of explicit validation/sequencing checkpoints for the multi-step analysis workflow.

Suggestions

Remove or shrink the decorative ASCII score-box in the Output section and trim the illustrative Risk Factors/Recommendations block to keep the token budget lean.

Fix the numbered lists so each section restarts at 1 (the current 4-23 cross-section numbering is a markdown artifact that reads as noise).

Add a short explicit workflow with validation steps tying the subcommands together (e.g., run scan -> review flagged approvals in revoke-list -> confirm before reporting) and reference or remove the unreferenced, off-topic references/implementation.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of concept explanations Claude already knows, but a large decorative ASCII score-box and an illustrative Output/Risk-Factors section, plus a broken cross-section numbered list (4-23 continuing across unrelated sections), add tokens that could be trimmed — fitting 'mostly efficient but could be tightened'.	2 / 3
Actionability	It provides fully executable, copy-paste-ready commands for every subcommand (approvals, scan, score, history, revoke-list, report, chains) with concrete options and a real example address, matching the highest anchor.	3 / 3
Workflow Clarity	The seven subcommands are individually clear, but for a multi-step analysis flow (scan -> score -> revoke-list) there are no explicit sequencing or validation checkpoints; this matches 'steps listed but checkpoints missing or implicit'.	2 / 3
Progressive Disclosure	The overview points one level deep to real, well-signaled bundle files (references/errors.md and references/examples.md both exist) with concise inline summaries, and scripts are bundled under scripts/ — fitting the clear-overview one-level-deep anchor.	3 / 3
	Total	10 / 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.

The description is concise, specific, and complete: it states the concrete actions, gives an explicit 'Use when' trigger clause, and lists natural trigger phrases. It uses third-person voice and avoids vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'analyzing token approvals, permissions, and transaction patterns' — within a clearly named domain (wallet security), matching the anchor for listing multiple specific concrete actions.	3 / 3
Completeness	It explicitly answers both 'what' (audit wallet security by analyzing approvals/permissions/transaction patterns) and 'when' via an explicit 'Use when...' clause plus trigger phrases, satisfying the highest anchor.	3 / 3
Trigger Term Quality	It supplies natural user phrasings — 'audit wallet', 'check approvals', 'security scan', or 'revoke tokens' — giving good coverage of terms a user would actually say rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	The crypto wallet-security niche and its distinct approval/revocation triggers make it unlikely to fire for the wrong skill, fitting the clear-niche anchor.	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: 3 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.