Tessl • The management layer for AI agent skills

SkillPublic

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

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/crypto/wallet-security-auditor/skills/auditing-wallet-security/SKILL.md

Quality

Content

75%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-structured, executable command reference with clear prerequisites, output descriptions, error recovery, and appropriately placed one-level-deep references. Main gaps are the inconsistent working-directory setup, broken continuous list numbering across sections, and bundle-level hygiene issues (an orphaned, mismatched implementation.md and a dangling config/settings.yaml reference).

Suggestions

State the working-directory requirement once globally (e.g. in Prerequisites) or prefix every wallet_auditor.py invocation with cd ${CLAUDE_SKILL_DIR}/scripts so all commands are copy-paste runnable.

Fix the markdown list numbering, which continues across sections (items 1-23), so each Options/Analyzes/Detects list restarts at 1.

Remove or rewrite references/implementation.md — it is unreferenced and its content (exchange APIs, trading signals, crypto:wallet-* MCP calls) does not match this read-only wallet auditor — and fix errors.md's reference to the nonexistent config/settings.yaml.

Dimension	Reasoning	Score
Conciseness	The body is a lean command reference with no re-teaching of concepts Claude already knows, and every section earns its tokens. Not 5: the Error Handling table duplicates content already delegated to references/errors.md, and the ASCII-art output mock in the Output section is dispensable illustration.	4 / 5
Actionability	Commands are concrete and executable with real flags (--chain, --verbose, --json, --output) and copy-paste examples using a real address (0xd8dA...6045). Not 5: "cd ${CLAUDE_SKILL_DIR}/scripts" appears only in section 1, so commands in sections 2-7 fail if followed literally from a fresh shell.	4 / 5
Workflow Clarity	The read-only disclaimer, prerequisites, seven well-specified subcommands, expected outputs, and an error-cause-solution table give a clear structure with recovery guidance (the destructive/batch validation cap does not apply to a read-only analyzer). Not 5: commands are documented individually without sequencing them into an audit flow (scan -> score -> revoke-list -> report), and the list numbering runs continuously (1-23) across sections, muddying the structure.	4 / 5
Progressive Disclosure	The body is appropriately split: commands and score breakdowns inline, details clearly signaled one level deep to references/errors.md and references/examples.md, both of which exist. Not 5: references/implementation.md is an orphan (never referenced, and its content — exchange APIs, trading signals, crypto:wallet-* MCP calls, crypto-reports/ — belongs to a different skill), and errors.md points to a nonexistent config/settings.yaml.	4 / 5
	Total	16 / 20 Passed

Description

78%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 description that clearly states what the skill does and when to use it, with explicit trigger phrases and a well-defined niche. Its main weakness is specificity: the skill's headline outputs (risk scoring, audit reports, revoke lists) are not named, and a few natural trigger variants are missing.

Suggestions

Enumerate the concrete capabilities in the description, e.g. "Audit wallet security by scanning token approvals, scoring risk (0-100), analyzing transaction patterns, and generating prioritized revoke lists and audit reports".

Add natural trigger variants such as "revoke approvals", "token allowances", or "unlimited approvals" to the trigger phrase list.

Dimension	Reasoning	Score
Specificity	"Audit wallet security by analyzing token approvals, permissions, and transaction patterns" names the domain and concrete action objects, but relies on a single verb over three objects while omitting core capabilities the skill delivers (security scoring, audit reports, revoke lists). This matches anchor 3 ('1-2 concrete actions, not comprehensive') rather than 4, whose 'minor gaps' standard these omissions exceed.	3 / 5
Completeness	Explicitly answers both: what ("Audit wallet security by analyzing token approvals, permissions, and transaction patterns") and when ("Use when checking wallet security, reviewing approvals, or assessing risk exposure"), and adds concrete trigger phrases — an exact match for the anchor 5 example pattern.	5 / 5
Trigger Term Quality	"audit wallet", "check approvals", "security scan", "revoke tokens" are natural phrases a user would say, plus "reviewing approvals" and "assessing risk exposure". Not 5: common variations such as "revoke approvals", "token allowances", or "unlimited approvals" are missing.	4 / 5
Distinctiveness Conflict Risk	A clear wallet-security niche with mostly distinct triggers; however, "security scan" is a somewhat generic phrase that could overlap with general security-audit or smart-contract-audit skills, fitting anchor 4 ('minor overlap risk with closely related skills') better than anchor 5.	4 / 5
	Total	16 / 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
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/tons-of-skills-marketplace
Path: plugins/crypto/wallet-security-auditor/skills/auditing-wallet-security/SKILL.md
Revision: ab85a06

Reviewed: 2 days ago

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.

auditing-wallet-security

Table of Contents

Is this your skill?