Average quality score across indexed skills.
Quality Dashboard
How scoring works
The quality page does more than rank skills. It shows which public signals make a skill easier to install, easier to understand, and easier to trust.
This dashboard keeps install clarity, documentation density, structural completeness, and recent improvements in one place so readers can triage faster.
Security baseline stays visible on the quality page.
Count of skills that look closer to install-ready.
Creator and quality pages share the same data model.
Highest quality skills
Start with skills where install entry points, structure, platform coverage, and trust signals all line up.
systematic-debugging
@obra · Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Quality
100
Security
85
receiving-code-review
@obra · Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable...
Quality
100
Security
100
verification-before-completion
@obra · Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and...
Quality
100
Security
100
using-git-worktrees
@obra · Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git...
Quality
100
Security
92
finishing-a-development-branch
@obra · Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development wo...
Quality
100
Security
100
mcp-builder
@anthropics · Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-desig...
Quality
100
Security
97
Install and documentation breakdown
Higher quality skills usually get four things right before anything else.
1
Clear entrypoint
Install command, platform, and source repo are obvious from the first screen.
Install command, platform, and source repo are obvious from the first screen.
2
Readable structure
Headings, steps, constraints, and outputs can be scanned without digging through the repo.
Headings, steps, constraints, and outputs can be scanned without digging through the repo.
3
Enough guidance
Triggers, boundaries, dependencies, and install methods are documented instead of implied.
Triggers, boundaries, dependencies, and install methods are documented instead of implied.
4
Improvement loop
Recently reviewed and recently improved skills surface back into the directory faster.
Recently reviewed and recently improved skills surface back into the directory faster.
Score distribution
quality bucket
quality bucket
quality bucket
quality bucket
Category insights
devops
7673 skills
76
analytics
7380 skills
75
security
4737 skills
74
marketing
2258 skills
73
sales
727 skills
73
Recently reviewed
Recently improved
mcm-c-validator
@majiayu000 · Sanity-check & validation specialist for COMAP MCM/ICM Problem C.
Quality
83
Security
100
botmadang
@openclaw · 봇마당(botmadang.org) - AI 에이전트 커뮤니티 플랫폼.
Quality
75
Security
25
react-19-patterns
@aiskillstore · Comprehensive React 19 patterns including all hooks, Server/Client Components, Suspense, streaming, and transitions.
Quality
92
Security
95
analytics-tracking
@davila7 · When the user wants to set up, improve, or audit analytics tracking and measurement.
Quality
92
Security
99
How scoring works
Quality scores combine install clarity, structural completeness, and documentation density.