audit-skills

Expert security auditor for AI Skills and Bundles. Performs non-intrusive static analysis to identify malicious patterns, data leaks, system stability risks, and obfuscated payloads across Windows, macOS, Linux/Unix, and Mobile (Android/iOS).

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/audit-skills/SKILL.md

Quality

Content

65%

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

A well-structured, highly concrete security-audit catalog with specific detection patterns, but it is monolithic, repeats its overview, contains a leftover authoring line, and lacks explicit validation checkpoints in its workflow.

Suggestions

Remove the stray '2-4 sentences is perfect.' line and the duplicate overview restatements in Step 1/Step 2 to tighten conciseness.

Add an explicit verification step to the workflow (e.g., 'Re-scan and cross-check flagged findings against CATALOG.md before generating the report') to introduce a feedback loop.

Move the 9-category threat-pattern catalog into a references/ file (e.g., THREAT_PATTERNS.md) and keep SKILL.md as a concise overview that links to it.

Dimension	Reasoning	Score
Conciseness	The 9 detection-category catalogs are dense and earn their place, but the body repeats the frontmatter overview verbatim, restates it again in Step 1/Step 2, and leaves a stray authoring artifact ("2-4 sentences is perfect.") that should have been removed.	2 / 3
Actionability	Concrete, specific detection signatures throughout — exact commands (sudo, adb shell, pm install, reg add, schtasks), exact file targets (AndroidManifest.xml, classes.dex, Info.plist, .env), and encoding patterns (Base64, Hex, XOR). As an instruction-only audit skill this is copy-paste-ready guidance, rewarded per the scoring notes.	3 / 3
Workflow Clarity	A clear three-step sequence is present (Static Analysis → Platform-Specific Threat Detection → Reporting with a defined output: score 0-10, flagged actions, mitigations), but there are no explicit validation checkpoints or feedback loops (e.g., verify/re-scan findings before reporting), so the sequence has implicit rather than explicit checkpoints.	2 / 3
Progressive Disclosure	Sections are well-organized with clear headers and numbered categories, but the skill is a monolithic ~120-line single file with no bundle files; the substantial 9-category pattern catalog is entirely inline and could be split into a reference file for discovery.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 specific, distinctive description with concrete actions and a clear cross-platform security niche, but it lacks an explicit 'Use when...' trigger clause and natural user phrasings, capping completeness and trigger quality.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when auditing AI skills or bundles for security, or when the user asks to check whether a skill is safe, malicious, or trustworthy.'

Include natural trigger terms users would actually say (security review, is this skill safe, check for malware) alongside the technical vocabulary.

Keep the existing specificity and platform list — they are strengths that distinguish this skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Performs non-intrusive static analysis to identify malicious patterns, data leaks, system stability risks, and obfuscated payloads' — naming four distinct detection targets plus platform coverage.	3 / 3
Completeness	It clearly answers 'what' (static analysis for malicious patterns across platforms) but never states 'when to use it' — there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Relevant domain keywords are present ('security auditor', 'audit', 'malicious patterns', 'obfuscated payloads'), but it leans technical and omits natural user phrasings like 'security review', 'is this skill safe', or 'check for malware'.	2 / 3
Distinctiveness Conflict Risk	The niche is specific and unlikely to conflict: 'Expert security auditor for AI Skills and Bundles' with cross-platform coverage (Windows, macOS, Linux/Unix, Mobile), a clear scope few other skills would share.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Path: skills/audit-skills/SKILL.md
Commit: 07da495

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.