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.
npx skills add moonlight-lupin/agent-skills --skill skill-quality-reviewgit clone --depth 1 https://github.com/moonlight-lupin/agent-skillsWrote 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.
[](https://agentmods.dev/skills/moonlight-lupin/agent-skills/skill-quality-review)<a href="https://agentmods.dev/skills/moonlight-lupin/agent-skills/skill-quality-review"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/skill-quality-review/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.
<a href="https://agentmods.dev/skills/moonlight-lupin/agent-skills/skill-quality-review"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/skill-quality-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.06308 |
| Opus 5.5 | $0.00022 | $0.02523 |
| Sonnet 5.5 | $0.00011 | $0.01262 |
| Haiku 4.5 | $0.00006 | $0.00631 |
Grade A, and why
skill-quality-review 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Quality Review
Audit SKILL.md quality across a set of skills. Identifies the most-used skills, classifies them as self-developed vs builtin, then runs batch writing-for-agents checks and fixes.
The review framework blends Matt Pocock's writing-for-agents (context pointers, two loads, information hierarchy, completion criteria, leading words, pruning) with hermes-agent-skill-authoring peer-matched structure and cross-reference parity. See references/writing-for-agents-framework.md for the full lever set.
references/skill-review-methodology.md lives HERE in this skill — it covers per-skill grep-based review (3-sources-of-truth drift, pricing registry, guardrail asymmetry). This skill covers batch automated checks, the deep per-skill methodology, and usage-based prioritisation across all skills in a repo or local library. Authoring-time mechanical sweeps (TOC coverage, nesting, orphans) run via scripts/check_references.py in this skill — format-agnostic, works on any repo (this skill vendors it so plugin repos do not depend on a Hermes-side script). For Hermes in-repo skills, hermes-agent-skill-authoring/scripts/audit_references.py remains the canonical checker; see references/hermes-library-review.md. Deep methodology below.
Know the skill format first
Before running any checks, identify the skill format — the frontmatter fields, structural sections, and validation rules differ:
| Aspect | Hermes in-repo | Claude Code plugin |
|---|---|---|
| Required frontmatter | name, description, version, author, license, metadata.hermes.{tags, related_skills} |
name + description only |
| Description trigger convention | Starts with "Use when ..." | Often carries Triggers: "phrase1", "phrase2" inline |
| Structural sections | ## Overview → ## When to Use → ## Common Pitfalls → ## Verification Checklist |
## What this skill is for → ## Workflow → skill-specific sections |
| Validator source | tools/skill_manager_tool.py in hermes-agent repo |
.claude-plugin/plugin.json + tools/build_plugin.py in the plugin repo |
| License field | In frontmatter | In .claude-plugin/plugin.json, not per-skill |
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/batch-checks.md 23 KB
- references/claude-plugin-review.md 11 KB
- references/domain-passive-voice.md 1.8 KB
- references/efficacy-ab-test.md 6.3 KB
- references/fix-phase-pitfalls.md 3.3 KB
- references/hermes-library-review.md 3.3 KB
- references/independent-skills.md 2.1 KB
- references/recurring-failure-patterns.md 15 KB
- references/skill-review-methodology.md 39 KB
- references/writing-for-agents-framework.md 12 KB
- scripts/add_toc.py 5.1 KB runs code
- scripts/check_calls.py 26 KB runs code
- scripts/check_references.py 6.3 KB runs code
- templates/efficacy-rubric-template.md 1.1 KB
- tests/acceptance.md 1.5 KB
- tests/test_harness_acceptance.py 4.7 KB runs code
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.
- 10d ago Changed · -12 lines 2bee6a67feb1
- 11d ago First seen · 273 lines · 55 tokens per session scan A d2e955bac5f5
skill-quality-review is a skill published in the GitHub repository moonlight-lupin/agent-skills (101 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 6,308 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-06.
Other skills, from other repositories
ecommerce-marketing-strategy-builder
Full-stack e-commerce marketing strategy builder. Analyzes your product, market, and competitors, then builds a complete omnichannel marketing plan covering paid ads, SEO, email/SMS, content marketing, social media, influencer partnerships, and referral programs. Includes target audience persona, competitive…
product-description-generator
E-commerce product description generator for any platform. Generates optimized titles, bullet points, descriptions, and backend keywords using competitor research + keyword scoring + FABE copywriting. Two modes: (A) Create — generate listing from product specs with optional competitor analysis, (B) Optimize — improve…
tiktok-shop-cross-border
Cross-border selling on TikTok Shop. Market selection, logistics setup, localization strategy, compliance requirements, and international expansion. Use when the user asks about TikTok Shop international selling, cross-border ecommerce, global expansion, or selling in multiple countries.
supply-chain-optimization-tiktok
Supply Chain Bottleneck Analyzer for TikTok Shop sellers. Diagnose cash flow, inventory turnover, affiliate commissions, and return rates. Includes FBT cost analysis, influencer payout optimization, and viral product lifecycle management. No API key required for basic analysis.
ecommerce-landing-page
Audit and optimize e-commerce landing pages for conversion. CTA placement, trust signals, page structure, copy optimization, and A/B testing strategy for product pages, collection pages, and campaign landing pages.
product-title-optimization
Optimize product titles for search visibility and click-through rate across e-commerce platforms. Platform-specific title rules for Amazon (200 chars), Etsy (140 chars), Walmart, Shopify SEO, and eBay.