claude-skills

claude-skills is a marketplace-style repository of many standalone “skills” (each with SKILL.md, plugin.json, templates, scripts, references) intended to be installed into Claude Code to help the agent build modern web apps using common patterns and integrations (notably Cloudflare, React, Tailwind v4, and AI tooling).

Evaluated Mar 30, 2026 (22d ago)
Repo ↗ DevTools claude-code claude-skills plugins skills typescript templates cloudflare react tailwind ai-integration developer-tooling
⚙ Agent Friendliness
44
/ 100
Can an agent use this?
🔒 Security
23
/ 100
Is it safe for agents?
⚡ Reliability
31
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
0
Documentation
55
Error Messages
0
Auth Simplicity
100
Rate Limits
0

🔒 Security

TLS Enforcement
50
Auth Strength
10
Scope Granularity
0
Dep. Hygiene
30
Secret Handling
30

Security posture can’t be fully assessed from the provided README/manifest (no dependency/SBOM/CVE data shown). Skills may include templates and guidance touching auth/security topics, but there is no stated security model, secrets handling policy, or enforcement mechanism within the package itself. Treat any templates as guidance requiring review and adaptation.

⚡ Reliability

Uptime/SLA
0
Version Stability
65
Breaking Changes
35
Error Recovery
25
AF Security Reliability

Best When

You want structured, reusable guidance for Claude Code to implement common stacks/patterns quickly and consistently, especially for web app + Cloudflare + AI integration work.

Avoid When

You require a documented, official programmatic interface (REST/GraphQL/SDK/MCP) for this package itself, or you need strong guarantees that every skill is compatible with your exact versions/configuration without validation.

Use Cases

  • Install targeted Claude Code skills to speed up and standardize implementation of web app features (frontend tooling, architecture patterns, auth/authz, testing, SEO, etc.)
  • Use bulk installation to bootstrap a full skill catalog locally for development
  • Use specialized skills to guide Cloudflare (e.g., D1/Workers AI/agents), API design, and AI integration scaffolding

Not For

  • Directly calling a programmatic API to manage resources at runtime (it’s a documentation/skill catalog, not a service API)
  • Production security/compliance of your app by itself (skills provide guidance/templates but do not enforce runtime security)
  • Automated “set-and-forget” deployments without reviewing skill content and fit for your environment

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
No
SDK
No
Webhooks
No

Authentication

OAuth: No Scopes: No

No authentication is described for accessing this repository/package; installs are performed via Claude Code plugin marketplace tooling.

Pricing

Free tier: No
Requires CC: No

Pricing for Claude Code marketplace usage is not described in the provided content; this repo itself does not specify paywalls.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Skill visibility is constrained by a character budget in the system prompt (token/character limits), so not all skills may be visible at once.
  • The README notes a workaround via SLASH_COMMAND_TOOL_CHAR_BUDGET, implying behavior depends on environment configuration.
  • Marketplace/bulk installs may introduce many skills; agents may select irrelevant skills unless constrained by user goals/context.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for claude-skills.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered