Logo
ClawHub Skills Lib
HomeCategoriesUse CasesTrendingStatisticsBlog
HomeCategoriesUse CasesTrendingStatisticsBlog
ClawHub Skills Lib
ClawHub Skills Lib

Browse 50.000+ community-built AI agent skills for OpenClaw. Updated daily from clawhub.ai.

Explore

  • Home
  • Categories
  • Use Cases
  • Trending
  • Blog

Categories

  • Development
  • AI & Agents
  • Productivity
  • Communication
  • Data & Research
  • Business
  • Platforms
  • Lifestyle
  • Education
  • Design

Use Cases

  • AI Code Generation
  • Code Review & Testing
  • DevOps & Cloud
  • Security & Compliance
  • Build an AI Agent
  • Agent Memory & RAG
  • Multi-Agent Orchestration
  • Browser & Web Automation
  • Financial & Market Data
  • Crypto & Web3
  • Real-Time Web Search
  • News & Media Monitoring
  • Academic Research
  • Data & Analytics
  • AI Image Generation
  • Voice & Audio AI
  • AI Video Creation
  • Content Writing
  • Task & Project Management
  • Knowledge Management
  • Email & Messaging
  • SEO & Content Marketing
  • Sales & CRM
  • Workflow Automation
  • Social Media
  • Chinese Platforms
  • E-Commerce
  • Education & Tutoring
  • HR & Recruiting
  • Legal & Compliance
  • AI Code Generation
  • Code Review & Testing
  • DevOps & Cloud
  • Security & Compliance
  • Build an AI Agent
  • Agent Memory & RAG
  • Multi-Agent Orchestration
  • Browser & Web Automation
  • Financial & Market Data
  • Crypto & Web3
  • Real-Time Web Search
  • News & Media Monitoring
  • Academic Research
  • Data & Analytics
  • AI Image Generation
  • Voice & Audio AI
  • AI Video Creation
  • Content Writing
  • Task & Project Management
  • See all use cases →
  • AI Code Generation
  • Code Review & Testing
  • DevOps & Cloud
  • Security & Compliance
  • Build an AI Agent
  • Agent Memory & RAG
  • Multi-Agent Orchestration
  • Browser & Web Automation
  • Financial & Market Data
  • See all use cases →
© 2026 ClawHub Skills Lib. All rights reserved.Built with Next.js · Neon · Prisma
Home/Quality Score Guide
Scoring System

Quality Score Guide

The Quality Score is an independent rating system created by clawhub-skills.com — it is not an official feature of clawhub.ai. We built it to help users cut through a large and fast-growing directory of skills and quickly identify which ones are worth installing. This page explains exactly how the score is calculated, what each dimension measures, and how to interpret the grade badges you see on skill cards.

Why a Quality Score?

Downloads are the primary demand signal — they capture every package fetch including users in air-gapped environments, manual SKILL.md placement, and non-sync workflows. They are noisier than installs (automated tools contribute), but at scale they reliably reflect real interest. Install counts (tracked via clawhub sync) are treated as a floor metric: their presence confirms real users, but their absence does not mean a skill has none — the install count is a known severe undercount of actual usage. The quality score weights downloads as the dominant market signal, with installs, stars, documentation depth, and maintenance as supporting dimensions.

The score is fully rule-based — no subjective human curation, no AI opinion. Every point is derived from objective, verifiable data synced from the ClawHub registry into our database.

Grade Scale

S
ExcellentScore ≥ 80

Top-tier skills with strong real-world adoption, complete documentation, and active maintenance. Safe to use with confidence.

A
GoodScore 65 – 79

Well-rounded skills that perform well across most dimensions. Minor gaps in documentation or install count, but generally reliable.

B
FairScore 50 – 64

Average skills — functional but with notable gaps. May lack detailed docs, have low install counts, or be newly published.

C
LimitedScore 35 – 49

Below-average skills with limited adoption or poor documentation. Worth a try if the concept matches your need, but proceed with caution.

D
PoorScore 20 – 34

Skills with very low adoption and minimal documentation. Likely experimental or abandoned. Review the source before installing.

F
SkipScore < 20

Red-flag skills. Score below 20 indicates minimal documentation, no tracked installs, and little evidence of real adoption across any dimension.

Score Formula

Total Score = Market (35) + Docs (25) + Package (15) + Maintenance (15) + Authenticity (10)
Maximum: 100 pts  ·  Minimum: 0 pts  ·  Authenticity can deduct points
35
Market
25
Docs
15
Package
15
Maintenance
10
Authenticity

Scoring Dimensions

Market Validation

Does anyone actually use this skill?

35 pts

Download Volume (up to 20 pts)

Downloads are the primary demand signal. Unlike installs, downloads capture every fetch of the skill package — including users in air-gapped environments, those who place SKILL.md manually, and anyone who never runs clawhub sync. Downloads are noisier (automated tools and CI pipelines contribute), but at scale they reliably reflect real interest. A skill with tens of thousands of downloads has demonstrable demand regardless of its sync-tracked install count.

≥ 50,000 downloads20 ptsExceptional demand
≥ 10,000 downloads17 ptsVery strong demand
≥ 5,000 downloads14 ptsStrong demand
≥ 2,000 downloads11 ptsHigh demand
≥ 500 downloads7 ptsModerate
≥ 100 downloads4 ptsLow
≥ 20 downloads1 ptVery low

Tracked Installs (up to 8 pts)

Install counts (reported via clawhub sync) are a floor metric — they confirm real users exist, but absence of installs does not mean a skill has no users. Users who place SKILL.md manually, run in air-gapped environments, or disable telemetry are invisible to this metric. When installs are present they are strong evidence of genuine adoption; the score treats them as a corroborating signal rather than the primary one.

≥ 100 installs8 ptsStrong confirmed adoption
50 – 997 ptsGood
20 – 495 ptsAbove average
10 – 194 ptsAverage
5 – 93 ptsLow
2 – 42 ptsVery low
11 ptMinimal
00 ptsNo tracked installs

Community Stars (up to 4 pts)

Stars are a deliberate human action — someone bookmarked the skill because they found it useful or wanted to track it. Unlike downloads, stars cannot be inflated by automated processes, making them a reliable quality signal.

≥ 10 stars4 ptsPopular
≥ 5 stars3 ptsWell-liked
≥ 1 star1 ptSome interest

Trending Bonus (up to 3 pts)

A positive trending score (week-over-week install growth) adds bonus points. Skills with rapid recent growth signal emerging adoption.

Trending ≥ 2.03 ptsHot
Trending ≥ 1.02 ptsGrowing
Trending ≥ 0.51 ptSlight uptick

Documentation Quality

Can a user understand what this skill does and how to use it?

25 pts

SKILL.md Presence (8 pts)

A SKILL.md file is the canonical documentation format for OpenClaw skills. Its mere presence earns 8 pts — it signals the author made a deliberate effort to document their work.

Content Depth (up to 6 pts)

Longer documentation generally means more thorough coverage of use cases, configuration, and examples.

≥ 3,000 characters6 ptsDetailed
≥ 1,500 characters4 ptsAdequate
≥ 500 characters2 ptsMinimal
< 500 characters0 ptsToo brief

Tool Definitions (5 pts)

Skills that explicitly define their tools block (the list of callable functions) are significantly more useful to agents. Detected via regex on SKILL.md content.

Usage Examples or Trigger Words (4 pts)

Docs that include trigger phrases, example prompts, or usage scenarios help users discover when and how to invoke the skill.

Summary Quality (up to 2 pts)

A meaningful one-line summary (>80 chars) shown on the skill card earns 2 pts; a short summary (>20 chars) earns 1 pt.

Package Completeness

Is the skill package well-structured?

15 pts

Package Assets Exist (6 pts)

Skills with a skillAssets bundle (downloaded package contents) earn 6 pts. This confirms the skill has been synced and has actual distributable files.

SKILL.md in Package (4 pts)

A SKILL.md file inside the downloaded package (distinct from the fetched markdown) confirms docs ship with the skill.

README or AGENTS doc (3 pts)

A README or AGENTS.md alongside the skill signals a more complete, production-ready package.

Scripts or Config Files (2 pts)

The presence of .sh, .py, .js, .ts, or .json files indicates the skill has executable or configurable components — not just markdown.

Maintenance Status

Is there an identifiable author who maintains this skill?

15 pts

Author Present (4 pts)

A named author signals accountability. Anonymous skills are harder to report issues to or follow for updates.

Version Number (4 pts)

A version string indicates the author follows a release cycle. Skills without versions are often early experiments that may never be updated.

Changelog (4 pts)

A changelog proves the skill has been actively revised. It also helps users assess whether known issues have been addressed.

Not Delisted (3 pts)

Skills that remain available on clawhub.ai earn this bonus. Delisted skills receive 0 pts here and are marked with a banner on their detail page.

Safety & Authenticity

Does the skill respect user privacy?

10 pts

Starts at 10 pts — deductions only

Every skill begins with the full 10 pts. Points are only ever deducted — never added — based on verified privacy risk signals.

Privacy Risk Tag (−8 pts)

Skills tagged privacy-risk have been manually reviewed and confirmed to collect identifying information (e.g. username, machine hostname) and transmit it to an external server on every run. This is the most severe deduction in the entire scoring system because it is based on verified human audit — not heuristics. A skill can still receive a passing score if it compensates in other dimensions, but the deduction is large enough to drop most affected skills to grade C or below.

Has privacy-risk tag−8 ptsConfirmed data exfiltration
No privacy-risk tag0 ptsNo known privacy issue

Limitations & Caveats

  • ·Install counts are a floor, not a ceiling. Only installs reported via clawhub sync are counted. Users who add SKILL.md files manually, run in air-gapped environments, disable telemetry, or never run sync are invisible to this metric. A skill with 0 tracked installs may still have real users. See ClawHub telemetry.md for exactly what is and isn't collected.
  • ·New skills are penalised by design. A skill published yesterday can't have 100 installs yet. If you're an author, give your skill time to accumulate data before judging the score.
  • ·Niche skills score lower, not worse. A highly specialised skill with 5 installs in a narrow domain may be exactly what those 5 users need — the score reflects breadth, not fit.
  • ·Scores are recalculated regularly as the platform syncs new install data from ClawHub's API. A skill's grade can improve over time as it gains adoption.
  • ·The score does not evaluate code quality or security. Always review the source of any skill before installation. Community-built skills run with agent permissions.
Browse by Quality ScoreView Top S & A SkillsPublish on ClawHub