Name: plugin-audit
Rating: 67.2 (1 reviews)
Author: vercel

plugin-audit

Audit vercel-plugin performance on real-world projects. Extracts tool calls from Claude Code conversation logs, tests hook matching against actual inputs, identifies pattern coverage gaps, and checks plugin cache staleness. Use when asked to audit, test, or investigate plugin skill injection on a real project.

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

Quality

Content

68%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, actionable audit workflow with concrete code and real bundle references, but the batch processing path has no explicit validation checkpoint and a little content overlap with the referenced log-format file.

Suggestions

Add an explicit verification checkpoint after tool-call extraction (e.g., confirm extracted tool_use count against raw JSONL line count) to lift workflow clarity above the batch-operation cap of 3.

Replace the `...` placeholder in the cache-diff command with a concrete expansion or a named variable so the step is fully copy-paste executable.

Trim the inline JSONL parsing explanation in step 2 since references/log-format.md already covers it, keeping the body to the unique guidance.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, with code blocks and targeted detail rather than padded explanation; a few explanatory lines (e.g., the JSONL parsing note) duplicate content already in references/log-format.md and could be trimmed.	4 / 5
Actionability	Provides concrete, mostly executable guidance — `ls -lt ~/.claude/projects/...`, JS imports, `loadSkills()`/`matchSkills()` calls, and a diff command — though placeholders like `<project-name>` and `...` in the cache-diff keep it just short of copy-paste ready.	4 / 5
Workflow Clarity	The five steps are clearly sequenced, but this batch operation (extracting all tool calls and matching them) lacks any explicit validation or verification checkpoint, capping workflow clarity at 3 per the batch-operations guideline.	3 / 5
Progressive Disclosure	Good structure with a Workflow, Report Format, and References section pointing to two real one-level-deep bundle files; minor organization gaps stem from the mild duplication of log-format detail between the body and references/log-format.md.	4 / 5
	Total	15 / 20 Passed

Description

92%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, specific description that concretely lists multiple actions and provides an explicit 'Use when' trigger clause tied to a distinct niche. The only minor gap is trigger-term variety, which leans on domain jargon over everyday synonyms.

Dimension	Reasoning	Score
Specificity	Lists four concrete actions — 'Extracts tool calls from Claude Code conversation logs', 'tests hook matching against actual inputs', 'identifies pattern coverage gaps', and 'checks plugin cache staleness' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (extracts tool calls, tests hook matching, identifies gaps, checks cache staleness) and 'when' ('Use when asked to audit, test, or investigate plugin skill injection on a real project') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases 'audit, test, or investigate plugin skill injection on a real project', but leans on domain jargon ('plugin skill injection') and omits common synonyms or file extensions, leaving a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche — vercel-plugin skill injection auditing on real projects — with distinct triggers and minimal overlap risk against unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: vercel/vercel-plugin
Path: .claude/skills/plugin-audit/SKILL.md
Commit: 358400a

Reviewed: 1 day 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.