Skills

Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.

calesthio/OpenMontage

Skill Claude CodeCodex

Build scalable design systems with Tailwind CSS v4, design tokens, component libraries, and responsive patterns. Use when creating component libraries, implementing design systems, or standardizing UI patterns.

not rated 77k +3.7k 3d ago A Socket: passSnyk: passSkillSpector: pass 42 tokens AGPL-3.0

skill-release-gate

50

rohitg00/ai-engineering-from-scratch

Skill Claude CodeCodex

Evaluate an Agent Skill bundle for structural integrity, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity, and target-host portability before release.

not rated 77k +1.3k yesterday A SkillSpector: pass 36 tokens original MIT

openai/openai-cookbook

Skill Codex ✓ vendor

Bootstrap a new realtime eval folder inside this cookbook repo by choosing the right harness from examples/evals/realtimeevals, scaffolding prompt/tools/data files, generating a useful README, and validating it with smoke, full eval, and test runs. Use when a user wants to start a new crawl, walk, or run realtime eval…

not rated 77k +92 today A Snyk: passSkillSpector: warn 76 tokens original MIT

improve-rule

52

thedaviddias/Front-End-Checklist

Skill Claude CodeCodex

Use when reviewing or improving a Front-End Checklist rule MDX file to raise its quality score, fix stub prompts, add missing fields, or enrich content with real code examples.

not rated 75k +50 6d ago A SkillSpector: pass 39 tokens original MIT

openspec-explore

53

Fission-AI/OpenSpec

Skill Claude Code

Enter OpenSpec explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements in a project that uses OpenSpec. Use when the user wants to think through something before or during an OpenSpec change. Also use when the user says "openspec explore" or "opsx explore".

not rated 74k +592 changed 20d ago A Socket: passSnyk: passSkillSpector: warn 67 tokens original MIT

usestrix/strix

Skill Claude CodeCodex

Security-test a REST, GraphQL, or gRPC API with Strix — autonomous agents that enumerate endpoints from an OpenAPI/GraphQL schema (or by crawling), then actually exploit the API-specific vulnerability classes in the OWASP API Security Top 10 (2023) — broken object-level authorization (BOLA/IDOR), broken object…

not rated 74k +1.0k changed 1mo ago A Socket: warnSnyk: passSkillSpector: pass 144 tokens original Apache-2.0

OpenBB-finance/OpenBB

Skill Claude CodeCodex

This guide covers installation, configuration, authentication, tool discovery, prompt management, and client integration for openbb-mcp-server.

not rated 74k changed 1mo ago A ✓ AI review SkillSpector: warn 31 tokens

publish-desktop

56

cline/cline

Skill Claude CodeCodex

Use when preparing, tagging, and publishing a Cline desktop app (apps/examples/desktop-app) release — stable (desktop-vX.Y.Z from main), beta (desktop-vX.Y.Z-beta.N from desktop-experimental, shipped as the side-by-side "Cline Beta" app), or nightly (artifact-only test build of main's HEAD, tagged desktop-nightly…

not rated 71k +290 changed 23d ago A Snyk: passSkillSpector: warn 130 tokens original Apache-2.0

claude-api

58

asgeirtj/system_prompts_leaks

Skill Claude CodeCodex

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude…

not rated 71k +384 changed 2d ago A ✓ AI review Snyk: passSkillSpector: warn 294 tokens original CC0-1.0

visual-qa

59

code-yeongyu/oh-my-openagent

Skill Claude CodeCodex

Runs rigorous visual QA across web, terminal, and paginated surfaces: an Apple HIG-based checklist, paired light/dark captures at phone and desktop widths, screenshot evidence, and a per-item PASS/FAIL verdict. Use for any UI build or change, or when asked whether a page, component, or TUI looks right or follows the…

not rated 71k +228 changed 7d ago A SkillSpector: pass 78 tokens

babysit-pr

60

openinterpreter/openinterpreter

Skill Codex

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

not rated 69k +57 2d ago A SkillSpector: warn 114 tokens original Apache-2.0

memory-triage

62

mem0ai/mem0

Skill Claude Code

Persistent long-term memory protocol powered by mem0. Evaluate conversations for durable facts worth storing via memoryadd. Handles identity, preferences, decisions, configurations, rules, projects, and relationships. Loaded by the openclaw-mem0 plugin when skills mode is active.

not rated 68k +360 2d ago A Snyk: passSkillSpector: pass 58 tokens original Apache-2.0

claude-api

63

warpdotdev/warp

Skill Claude CodeCodex

Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…

not rated 66k +91 today A SkillSpector: warn 193 tokens AGPL-3.0

find-docs

64

upstash/context7

Skill Claude CodeCodex

Retrieves up-to-date documentation, API references, and code examples for any developer technology. Use this skill whenever the user asks about a specific library, framework, SDK, CLI tool, or cloud service — even for well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot. Your training…

not rated 64k +273 changed 24d ago A ✓ AI review Socket: passSnyk: passSkillSpector: warn 172 tokens original MIT

rust-string-enums

65

BerriAI/litellm

Skill Claude CodeCodex

Define or refactor Rust string-valued enums and their Serde adapters in litellm-rust, using Strum and serdewith while preserving parsing, wire values, and schemas.

not rated 63k +384 changed 8d ago A 41 tokens

security-audit

66

cloudflare/security-audit-skill

Skill Claude CodeCodex ✓ vendor

Security guidance and vulnerability review for codebases, APIs, services, CLI tools, libraries, and daemons. Use for security questions, focused reviews, vulnerability research, security audits, or pen tests. Run the complete workflow only for explicit codebase audit or pen-test requests, full/comprehensive/end-to-end…

not rated 62k +7.4k changed 1mo ago A Socket: passSnyk: warnSkillSpector: pass 72 tokens original MIT

hindsight-architect

67

vectorize-io/hindsight

Skill Claude CodeCodex

Expert memory architect. Understands your application, identifies where memory adds value, and produces an implementation plan with bank config, tag schema, and code.

not rated 59k +2.5k yesterday A Snyk: failSkillSpector: warn 35 tokens original MIT

HKUDS/CLI-Anything

Skill Claude CodeCodex

Capability-based multi-tool matrix for video production. Agents pick providers (CLI-Anything harnesses, public CLIs, Python libs, native binaries, cloud APIs) per capability rather than marching through fixed stages, including storyboard planning, story/audio direction, source triage, internet video/music…

not rated 58k +473 1mo ago A ✓ AI review SkillSpector: warn 93 tokens original Apache-2.0

writing-blogs

69

appwrite/appwrite

Skill Cursor ✓ vendor

Writes, structures, and formats SEO-optimized blog posts for the Appwrite blog following established conventions for voice, tone, frontmatter, and post structure. Use when the user asks to write, draft, create, or outline a blog post, or when working with files in src/content/blog/posts/.

not rated 58k +69 yesterday A 64 tokens original BSD-3-Clause

agent-state-bar

70

bojieli/ai-agent-book

Skill Claude CodeCodex

A design guide for an agent status bar: a short, automatically updated summary of progress, remaining tasks, tool counts, errors, and system state placed near the latest model input.

not rated 57k +585 29d ago A 105 tokens original Apache-2.0

compare-tasks

71

aaif-goose/goose

Skill Claude CodeCodex needs its repo

Compare how two harbor benchmark runs performed on a single shared task.

not rated 56k +285 yesterday A Snyk: passSkillSpector: pass 16 tokens original Apache-2.0

markitdown

72

K-Dense-AI/scientific-agent-skills

Skill Claude CodeCodex

Converts heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.

not rated 56k +813 changed 1mo ago A Socket: passSnyk: passSkillSpector: pass 62 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: