The SkillOx catalog

Browse agent skills by their security grade.

Every skill below has been scanned and graded by SkillOx — click any card for the full findings report. Filter by grade in the sidebar.

19,710

Indexed

18,968

Grade A

65

Malicious

5,111 skillsshowing 961–1020· grade=A · source=crawl-github

Clear all filters

Macro is a unified interface for email, messaging, tasks, calls, agents, docs, diagrams, CRM — linked together with shared AI memory.

Clean scan — no findings.

190NOASSERTIONscanned 1w agomacro-inc/macro

Macro is a unified interface for email, messaging, tasks, calls, agents, docs, diagrams, CRM — linked together with shared AI memory.

Clean scan — no findings.

190NOASSERTIONscanned 1w agomacro-inc/macro

SpECTRE is a code for multi-scale, multi-physics problems in astrophysics and gravitational physics.

Clean scan — no findings.

190NOASSERTIONscanned 1w agosxs-collaboration/spectre

This repository contains a comprehensive set of development rules, standards, and AI agent configurations designed to work seamlessly with multiple AI coding copilots. The setup is portable and can be imported into any project to provide consistent, high-quality AI-assisted development.

Clean scan — no findings.

186MITv 1.0.0scanned 1w agoLIDR-academy/lidr-specboot

This repository contains a comprehensive set of development rules, standards, and AI agent configurations designed to work seamlessly with multiple AI coding copilots. The setup is portable and can be imported into any project to provide consistent, high-quality AI-assisted development.

Clean scan — no findings.

186MITv 1.0.0scanned 1w agoLIDR-academy/lidr-specboot

Human directs. AI delivers.

Clean scan — no findings.

184MITscanned 1w agoxg-gh-25/SwarmAI

Official collection of iFLYTEK skills for speech, OCR, translation, proofreading, and multimodal AI capabilities.

Clean scan — no findings.

178Apache-2.0scanned 1w agoiflytek/iFly-Skills

WOZCODE plugin for Claude Code

Clean scan — no findings.

178scanned 1w agoWithWoz/wozcode-plugin

drizzle-migrations

The most hackable AI agent

Clean scan — no findings.

177AGPL-3.0scanned 1w agoiterate/iterate

Linter for agent skill files

Clean scan — no findings.

177MITscanned 1w agothedaviddias/skill-check

real-review-skill

Linter for agent skill files

Clean scan — no findings.

177MITscanned 1w agothedaviddias/skill-check

global-faq-retrieval

Clean scan — no findings.

176Apache-2.0scanned 1w agoaifinlab/FinClaw

global-faq-retrieval

Clean scan — no findings.

176Apache-2.0scanned 1w agoaifinlab/FinClaw

global-faq-retrieval

Clean scan — no findings.

176Apache-2.0scanned 1w agoaifinlab/FinClaw

Clean scan — no findings.

176scanned 1w agoWenJunDuan/Rlues

Clean scan — no findings.

176scanned 1w agoWenJunDuan/Rlues

Clean scan — no findings.

176scanned 1w agoWenJunDuan/Rlues

spec-generation

Specula: A framework for finding deep bugs in system code using TLA+

Clean scan — no findings.

166Apache-2.0scanned 1w agospecula-org/Specula

IJFW — It Just F*cking Works. Ferrox Labs' local-first infrastructure for AI coding agents: shared memory, smart routing, multi-AI cross-audits, disciplined workflow.

Clean scan — no findings.

165MITscanned 1w agoFerroxLabs/ijfw

Clean scan — no findings.

164MITscanned 1w agodancinlab/sidecar

Clean scan — no findings.

164MITscanned 1w agodancinlab/sidecar

B端 PRD 生成工具 — 基于《决胜B端》方法论，让 AI 帮你生成 14 章结构化 PRD

Clean scan — no findings.

159scanned 1w agopmYangKun/create-prd-skill

A multi-platform (Flutter) application for connecting to Matrix - an open network for secure, decentralized communication, with your favorite devices.

Clean scan — no findings.

158AGPL-3.0scanned 1w agolinagora/twake-on-matrix

ct-dev-workflow

Agent-first task orchestration. Persistent memory. Multi-provider coordination.

Clean scan — no findings.

157MITv 3.0.0scanned 1w agokryptobaseddev/cleo

nextjs-seo-foundations

Clean scan — no findings.

157MITv 1scanned 1w agokennyzir/7deer_skills

Custom OpenCode settings

Clean scan — no findings.

153MITscanned 1w agofmflurry/settings-opencode

221 AI skills for construction: BIM analysis, cost estimation, scheduling, document control, and automation with Claude Code

Clean scan — no findings.

152MITscanned 1w agodatadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction

Pre-configured agent skills for Vibe Coded projects. These skills provide AI coding assistants (Claude Code, Cursor, etc.) with specific guidelines for code quality and design standards.

Clean scan — no findings.

152MITscanned 1w agowednesday-solutions/ai-agent-skills

Comprehensive collection of Claude Code skills for academic research in economics, finance, and social sciences

Clean scan — no findings.

152scanned 1w agofranklee16/academic-research-skills

Professional-grade AI coding toolkit: 94 skills, 44 agents, multi-platform (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, Antigravity, Codex CLI, opencode).

Clean scan — no findings.

150MITscanned 1w agosoftspark/ai-toolkit

The switchboard for the agent era. Per-channel isolation, encrypted credential vault, per-session hash-chained audit log. Single static Rust binary.

Clean scan — no findings.

150MITscanned 1w agogebruder/wirken

fireworks-training-research

Recipes and resources for building, deploying, and fine-tuning generative AI with Fireworks.

Clean scan — no findings.

149Apache-2.0scanned 1w agofw-ai/cookbook

90a8a5dd3a15c39e59062e2518171615fecff5c3

Ataraxy-Labs/inspect

Entity-level code review. Triages pull requests by structural risk using cross-file dependency graphs and LLMs that read for meaning.

Clean scan — no findings.

147NOASSERTIONscanned 1w agoAtaraxy-Labs/inspect

shopify-admin-skills

Community-maintained AI agent skills for operating Shopify stores — workflows, optimization, reports and more

Clean scan — no findings.

147MITscanned 1w ago40RTY-ai/shopify-admin-skills

strategy-compare

Agentic coding skills for backtesting trading strategies using VectorBT. Supports Indian, US, and Crypto markets with realistic transaction cost modeling, TA-Lib indicators, QuantStats tearsheets, and 12 ready-made strategy templates.

Clean scan — no findings.

145scanned 1w agomarketcalls/vectorbt-backtesting-skills

The agent OS that evolves itself.

Clean scan — no findings.

145Apache-2.0scanned 1w agoiii-experimental/agentos

ie-connect-dots

Clean scan — no findings.

143scanned 1w agowpsnote/wpsnote-skills

architecture-extract

Turns AI coding tools into reliable software delivery systems. Drop a .gaai/ folder into any project — Discovery defines what to build, Delivery executes autonomously until criteria pass. Works with Claude Code, Codex CLI, Gemini CLI, Cursor, and more. No SDK. No package. Markdown + YAML + bash.

Clean scan — no findings.

143NOASSERTIONscanned 1w agoFr-e-d/GAAI-framework

spectre-handoff

SPECTRE is an agentic Coding Workflow - /Scope, /Plan, /Execute, /Clean, /Test, /Rebase, /Evaluate - that uses simply step by step product development workflow to generate high quality results from your AI Coding Agents.

Clean scan — no findings.

142MITscanned 1w agoCodename-Inc/spectre

Agentic ✧ Gemma Inference for Android System Intelligence

Clean scan — no findings.

142MITscanned 1w agovNeeL-code/GHOST

Agentic ✧ Gemma Inference for Android System Intelligence

Clean scan — no findings.

142MITscanned 1w agovNeeL-code/GHOST

sc-velocity-prep

Conversational & memory-enabled AI research partner for multi-omics analysis. CLI + Desktop App (installers in Releases). From biological idea to full research paper.

Clean scan — no findings.

140Apache-2.0v 0.3.0scanned 1w agoTianGzlab/OmicsClaw

40a5ecc44ce3099a89167e5c5e478598ba05f997

laolin5564/openclaw-wx-echo

🦞 微信 AI 个人助手 — 自动提取待办、日程、干货（Alpha，欢迎共建）

Clean scan — no findings.

140scanned 1w agolaolin5564/openclaw-wx-echo

Clean scan — no findings.

136MITv 1.3.1scanned 1w agounnoo/zsxq-skill

databricks-spark-structured-streaming

Clean scan — no findings.

136NOASSERTIONscanned 1w agodatabricks/databricks-agent-skills

Feishu/Lark group for Claude Code and Codex sessions, vibe coding anytime, anywhere

Clean scan — no findings.

136MITscanned 1w agofrancize/agents-to-im

Agentic Coding Rules, Templates etc...

Clean scan — no findings.

136Apache-2.0scanned 1w agosammcj/agentic-coding

Agentic Coding Rules, Templates etc...

Clean scan — no findings.

136Apache-2.0scanned 1w agosammcj/agentic-coding

fireauto-harness-guide

Claude Code 자동화 플러그인 — SEO, 보안, 팀 에이전트, PRD, 레딧 리서치를 커맨드 하나로

Clean scan — no findings.

134MITscanned 1w agoimgompanda/fireauto

ios-background-audio

Mobile voice notes app — Rust, Dioxus iOS, local-first (SQLite + LanceDB + RIG)

Clean scan — no findings.

133EUPL-1.2scanned 1w agomirkobozzetto/flowflow

stay on top of your favorite blogs

Clean scan — no findings.

133MITscanned 1w agoHyaxia/blogwatcher

Clean scan — no findings.

133scanned 1w agoenvy-ai/ai_rpg

For experienced Framer creators looking to push the boundaries.

Clean scan — no findings.

130MITscanned 1w agofredm00n/framerlabs

⛯ Environment variable validation from editor to runtime

Clean scan — no findings.

125MITscanned 1w agoyamcodes/arkenv

creating-bookmarklets

My collection of Claude skills

Clean scan — no findings.

124MITscanned 1w agooaustegard/claude-skills

testing-pd-hunter-frontend

AI-powered bounty intelligence dashboard for Github repositories.

Clean scan — no findings.

124MITscanned 1w agoFuZoe/PD-Hunter

nansen-web-searcher

Clean scan — no findings.

124MITscanned 1w agonansen-ai/nansen-cli

jj-uncommit-to-working-copy

Real-time web dashboard for pi coding-agent sessions. Multi-session view, live chat mirroring, integrated terminal, diff viewer, pi-flows execution, and mobile-first remote control via mDNS or zrok tunnel. Coexists with pi's TUI — doesn't replace it.

Clean scan — no findings.

123MITscanned 1w agoBlackBeltTechnology/pi-agent-dashboard

Clean scan — no findings.

122v 2.0.0scanned 1w agoamanning3390/deepswarm

Open-source legal workspace.

Clean scan — no findings.

117Apache-2.0scanned 1w agostella/stella

Want your skill listed? Publish through the creator portal — every submission is scanned, graded, and (if you pass identity verification) shown with your verified badge.