skill-reviewer

skill-reviewer is an agent for Claude Code from Vibe-Marketer/plugins-and-skills. It costs 237 tokens per session (1,332 once invoked), scanned A, original, MIT.

A review agent for checking the quality of an AI-agent skill. It examines the skill’s structure, description, instructions, and likely trigger phrases.

In plain words
What is it for?
Use it after creating or changing a skill, or when you want its description and contents checked against recommended quality rules.
Why use it?
It helps find missing required sections, vague activation wording, excessive length, and other issues that can make a skill unreliable or hard to discover.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions Claude Code.

Part of the create-plugins plugin — 12 skills, 6 commands, 9 agents shipped together

Good fit Use it after creating or changing a skill, or when you want its description and contents checked against recommended quality rules.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/vibe-marketer/plugins-and-skills/skill-reviewer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/Vibe-Marketer/plugins-and-skills

Made for: Claude Code.

Or install create-plugins, the plugin that ships this one along with the rest of its 12 skills, 6 commands, 9 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for skill-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/vibe-marketer/plugins-and-skills/skill-reviewer/github.svg)](https://agentmods.dev/agents/vibe-marketer/plugins-and-skills/skill-reviewer)
Your own site
<a href="https://agentmods.dev/agents/vibe-marketer/plugins-and-skills/skill-reviewer"><img src="https://agentmods.dev/badge/agents/vibe-marketer/plugins-and-skills/skill-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for skill-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/vibe-marketer/plugins-and-skills/skill-reviewer"><img src="https://agentmods.dev/badge/agents/vibe-marketer/plugins-and-skills/skill-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 237 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,332 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00237 $0.01332
Opus 5 $0.00118 $0.00666
Sonnet 5 $0.00047 $0.00266
Haiku 4.5 $0.00024 $0.00133

Measured 9d ago against content hash ff2c11d213c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

skill-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

create-plugins/agents/skill-reviewer.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<step_2 name="validate_structure">

  • Frontmatter format: YAML between --- delimiters
  • Required fields: name, description
  • Body content exists and is substantial
  • Pure XML structure (no markdown headings in body)
  • Required XML tags: <objective>, <quick_start>, <success_criteria> </step_2>

<step_3 name="evaluate_description"> This is the most critical check. Evaluate:

  • Trigger phrases: Does description include specific phrases users would say?
  • Third person: Uses "This skill should be used when..." not imperative form
  • Specificity: Concrete scenarios, not vague categories
  • Length: 50-500 chars (not too short, not too long)
  • Trigger coverage: Lists specific user queries that should activate the skill
  • Target: 90%+ trigger rate on relevant queries </step_3>

<step_4 name="assess_content">

  • Line count: SKILL.md body should be under 500 lines (lean, focused)
  • Writing style: Imperative/infinitive form in body ("To do X, do Y")
  • Organization: Clear sections, logical flow
  • Specificity: Concrete guidance, not vague advice
  • Conciseness: Only context Claude doesn't already have </step_4>

<step_5 name="check_progressive_disclosure">

  • Core SKILL.md: Essential information only, under 500 lines
  • references/: Detailed docs moved out of core
  • workflows/: Step-by-step procedures separated
  • examples/: Working examples separate
  • Pointers: SKILL.md references these resources clearly </step_5>

<step_6 name="review_supporting_files"> If present, check:

  • references/: quality, relevance, organization, pure XML structure
  • examples/: completeness, correctness
  • scripts/: executable, documented
  • All referenced files actually exist </step_6>

<step_7 name="identify_anti_patterns"> Flag:

  • Vague trigger descriptions
  • Too much content in SKILL.md (should be in references/)
  • Second person in description
  • Missing key trigger phrases
  • Markdown headings in body (should be XML tags)
  • Hybrid XML/markdown structure
  • Unclosed XML tags
  • Explaining things Claude already knows </step_7>

<output_format>

Skill Review: [skill-name]

Read the full file on GitHub · 172 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 172 lines · 237 tokens per session scan A ff2c11d213c2

Subscribe to this mod's changes

skill-reviewer is an agent published in the GitHub repository Vibe-Marketer/plugins-and-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 237 tokens to every session and 1,332 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.