Agent-drivable Remotion pipeline: structured JSON in, a loudness-normalized MP4 out. A production harness that layers on top of remotion-dev/skills.

Reusable, project-agnostic engineering and multi-model skills for Claude Code

Scan-gated safety for Agent Skills before they reach Codex, Claude Code, CI, or a registry.

AI skill for inkle's ink scripting language — branching narrative, dialogue trees, and interactive fiction.

CLI that automates eval-driven iteration for AI skills: run with/without skill, grade with LLM judge, and benchmark results.

Capability orchestration skills for AI agents: runtime-agnostic + Codex/OMX + OpenCode/OMO variants. Works with Claude Code, Cursor, OpenCode, Codex.

Self-advocacy for non-lawyers: from a wrong you suffered to a verified, deadline-aware paper trail, demand letter, and the right complaint forum.

Native macOS skill-catalog studio for Claude Code — browse 1,492 Markdown skills, customize with variables or AI (hosted or local), export to .claude/skills. SwiftUI + Liquid Glass.

Turn a capability spec into a correct agent/tool architecture: decide skill vs subagent vs MCP vs workflow, design tool contracts, context strategy, safety, and a test harness.

A dependency-free, agent-agnostic skill to create, validate, preview & export DESIGN.md files — no CLI required.

Reusable Claude Code skills that help AI agents collaborate: handoffs, shared task tracking, code-review exchange, ADRs, and changelogs. Installable as a plugin.

Local-ancestry inference that fine-maps QTL and predicts trait donors from whole-genome sequence libraries — a reproducible, typed, tested rebuild of the method in Anderson et al. 2024 (The Plant Journal).

your documents to a second brain that cites every claim or admits it doesn't know. a Claude Code skill for grounded Obsidian knowledge bases.

Mine your past agent conversations into high-quality Agent Skills

Standalone WorkBuddy marketplace for VOC-Industry-Clustering

Standalone WorkBuddy marketplace for VOC-KANO-Prioritization

Screen-reader-friendly, keyboard/voice-friendly Codex session behavior skill.

AI-powered product-creation pipeline — ideation → brand → business plan → marketing → operations. Forked from santifer/career-ops; skill layer built on coreyhaines31/marketingskills. Local-first, AI-agnostic, human-in-the-loop.

Claude skill that counteracts LLM sycophancy: honest assessment over the agreeable one. Mirror-test, steelman-the-opposite, resist caving. Calibrated, not contrarian.

Provider-neutral AI conversation continuity framework for verified session handoffs

A triage-gated process for taking a behavioral skill from works to publish-grade and beyond. Scale the apparatus to the skill; every step leaves a checkable artifact.

One-command BMAD METHOD + Odoo dev environment for Claude Code (BA skill, Odoo subagents, agent overrides, Visual-QC)

AWS Blocks Skills

Metacognitive debugging and Project-Based Learning skill for Codex and Claude AI coding agents

An LLM agent skill for high-performance Entity Framework Core — fast queries, bulk inserts, high-throughput patterns — that fixes code without changing its behavior.

Grok Build skill: read-only second opinions from Claude Code (plan, review, advice)

Claude Agent Skills for building casual iOS games in Unity 6 — orchestration, MCP Editor control, generative 2D/3D/audio assets, graphics, UI, monetization, QA & release.

A native MeTTa decision gate that ranks agent actions against explicit goals, policy norms, and graded evidence.

Agent skill for Locus MCP, free tools, and x402 property-context workflows

Open Source Agentic scrapping skill with 8 hyperfocused skills, to give research subagents web-search on steroids.

Hermes-compatible skill for proof-backed, trust-preserving website copywriting.

A drop-in self-improving memory + operations harness for AI agents (OpenClaw / Hermes / Claude Code / Codex). Layered memory, autonomous drift-fixing loop, evals, and one-command DR. Templates + scripts, no secrets.

Codex 设计类 Skill 自动编排与一键安装套件

A debugging reflex for AI assistants: when a third-party tool breaks, search the community before guessing. The bug is usually external state that moved, not your code.

Agent skills for Chrome

Agent Skills for Wassenger — automate WhatsApp Business (official WABA) by chatting with Claude, Cursor, Codex or any Agent Skills client. 22 skills + the Wassenger MCP server.

WorkBuddy marketplace for a seven-step VOC insight pipeline

Primevue skills for ai agents

Canonical aggregation point for Claude Code skills authored by the deessejs org

THE definitive curated resource for wealth-agent-skills | GenCreator 6-Pillar CoE • Starlight Intelligence • Arcanea Creative Execution • Agentic Passive Income Systems

THE definitive curated resource for gamification-agent-skills | GenCreator 6-Pillar CoE • Starlight Intelligence • Arcanea Creative Execution • Agentic Passive Income Systems

Team coding-standards plugins for Claude Code (Agent Skills marketplace) · 面向 Claude Code 的团队代码规范插件(技能 marketplace)

Local GitHub issue-to-PR agent loop with proof, adversarial review, and human-gated merge.

A collection of AI agent skills I have written

Claude Code skill/plugin that rewrites a raw question into a high-performing LLM prompt by auto-selecting research-backed prompt-engineering strategies.

Codex plugin for handing off near-full context threads to fresh continuation sessions

Agent Skills for using Scout: web research, sourced answers, company enrichment, structured extraction, monitoring. Works in Claude Code, Claude.ai, the Agent SDK, and Vercel eve.

Practical agent skills for vibe coders: move fast, verify faster, ship cleaner.

Standalone governed multi-vendor network ops (NAPALM) — 13 MCP tools with audit/budget/undo/risk-tier harness

OpenGod - 14-module AI super skill. Fuses 18 of Top 50 GitHub AI projects.

🧰 Practical agent skills for OctopusGarage workflows.

Codex skill for converting media, subtitles, and transcripts into reusable learning notes

Zotero-based portable Agent Skills package for full-text scientific literature analysis and research-gap discovery

A security skills pack for Claude Code, Cursor, Codex and Gemini CLI: secrets pre-flight, dependency audit, secret rotation, STRIDE threat modeling, secure code review, Dockerfile hardening and env hygiene.

Agent skill for using Open Placeholder images in generated frontend code

Agent Kaizen skill for Claude Code & Codex: faithful, identifier-preserving reference for Tauri v2 development, tauri.conf.json, calling Rust/frontend, state management, resources & sidecar binaries, app icons, plugin & mobile development, debugging (VS Code/RustRover/Neovim), and testing (mocking, WebDriver). Not Tauri v1.

Portable evidence-grounded academic writing Agent Skill for Codex and compatible agents.

Model-agnostic Agent Skills covering the entire public Discogs API (api.discogs.com).