plugin-audit

Comprehensive audit pipeline for skills, plugins, agents, and commands. Validates structure, quality, security, marketplace compliance, cross-platform compatibility, and ecosystem integration. Runs all built-in validation tools, invokes domain-appropriate agents for code review, and produces a pass/fail gate report. Usage: /plugin-audit <skill-path>

Quality

78%

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 ./.gemini/skills/plugin-audit/SKILL.md

Quality

Content

88%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.

The body is highly actionable and excellently sequenced, with exact commands, gate thresholds, validation feedback loops, and auto-fix rules that make the 8-phase audit unambiguous to execute. The only real weakness is progressive disclosure: it is a single inlined monolith with no reference files to offload detail, and the decorative boxed report adds token weight.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational with minimal concept re-explanation, but the boxed ASCII report and the repeated gate-rule/verdict tables carry some tokens a tighter summary could omit, so it is efficient with minor trimming possible rather than the fully lean 5 anchor.	4 / 5
Actionability	It provides copy-paste-ready exact commands for each phase (e.g. 'python3 engineering/skills/skill-tester/scripts/skill_validator.py {skill_path} --tier {detected_tier} --json'), explicit gate thresholds, and concrete auto-fix instructions, fully matching the executable 'copy-paste ready' anchor.	5 / 5
Workflow Clarity	The 8 phases are explicitly sequenced with validation checkpoints and feedback loops ('Re-run after fixes. If still below 75, report as FAIL', 'Only proceed when validation passes'), plus gate rules and a verdict table — matching the 5 anchor's clear sequence with explicit validation and error-recovery loops.	5 / 5
Progressive Disclosure	Content is well-organized into clear sections and offloads specifics to a 'Skill References' table of tool paths, but the body is largely a single self-contained monolith with no one-level-deep reference files (no references/ scripts/ assets/ bundles exist), so it is well-structured but lacks the clearly signaled external references of the 5 anchor.	4 / 5
	Total	18 / 20 Passed

Description

67%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.

The description is concrete and covers its 'what' comprehensively across multiple audit dimensions, with an explicit usage trigger. It is held back by trigger-term naturalness — users are unlikely to phrase the 'when' as a slash-command invocation rather than a stated need — and by not enumerating the most common natural synonyms.

Suggestions

Append a natural 'Use when ...' clause with user-facing phrasings (e.g. 'Use when checking if a skill or plugin is ready to merge/publish, or when validating plugin structure and marketplace compliance').

Add common synonyms and file extensions users might say (e.g. 'audit', 'review', 'validate', 'plugin.json', 'marketplace entry', 'pass/fail gate') to improve trigger-term coverage.

List the concrete validation phases inline (structure, quality, scripts, security, marketplace, ecosystem, code review) so capabilities are enumerated rather than summarized.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Validates structure, quality, security, marketplace compliance', 'invokes domain-appropriate agents for code review', 'produces a pass/fail gate report') with only minor coverage gaps, matching the 'lists several specific actions; minor gaps' anchor; not a 5 because it does not enumerate the individual validation phases that the body reveals.	4 / 5
Completeness	It clearly answers 'what' (audit pipeline that validates multiple dimensions and produces a gate report) and 'when' via the explicit 'Usage: /plugin-audit <skill-path>' trigger clause, but the 'when' is a bare invocation hint rather than natural trigger phrases, fitting the 4 anchor of having both with 'when' less explicit rather than the 5 anchor's concrete trigger phrases.	4 / 5
Trigger Term Quality	Relevant domain keywords appear (audit, skills, plugins, agents, commands, marketplace compliance) but common natural user phrasings and synonyms ('review my plugin', 'check a skill', 'is this ready to publish') are absent, so it sits at 'some relevant keywords but missing common variations' rather than the 4 anchor's broad keyword coverage.	3 / 5
Distinctiveness Conflict Risk	The scope is a clear niche ('audit pipeline for skills, plugins, agents, and commands') unlikely to misfire for unrelated skills, though the breadth across four artifact types leaves minor overlap risk with general code-review skills; not a 5 because it does not sharply distinguish from a plain code-review skill via trigger phrasing.	4 / 5
	Total	15 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/plugin-audit/SKILL.md
Commit: 19392f7

Reviewed: ~11 hours 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.