Skills for repairing math gaps through visual intuition, small simulations, and targeted practice.

Harness-neutral Agent Skills for safe VS Code crash recovery and project-scoped build cleanup on macOS.

Skills for learning APIs through first requests, docs maps, auth debugging, and SDK examples.

YUAN元解密 AI Skills：面向真实内容运营场景的可安装智能体技能

Agent Skills for stealthy, human-like browser automation with Playwright and Camoufox — real-browser agentic browsing that evades bot detection.

Composable AI agents and skills for operating Azure Database for PostgreSQL Flexible Server - PostgreSQL can be used for everything.

Agent Skills for prompt optimization - tune prompts for the latest frontier models like Fable 5 and GPT 5.6, write effective goals and success criteria, and engineer agentic loops that converge.

Community agent skills for safe, behavior-preserving refactoring (OpenCode, Claude Code, and any SKILL.md-compatible agent)

Agent skills, SDKs, and integration docs for Immersive Commons (immersivecommons.com) - Floor 10, Frontier Tower SF. Includes .claude/, .cursor/, .windsurf/ agent configs.

Skills for refactoring and optimizing React and Vite applications.

A software engineering creed for coding agents — discipline skills for tests, design, and evidence over claims.

Clean Architecture para .NET + SQL Server + Angular, destilada de años de experiencia real en decenas de proyectos en producción.

MrCha Skills — portable Agent Skills for ChatGPT, Codex, and compatible agents

Zero coding experience? Give Codex an AI delivery crew that turns ideas into working, tested, releasable software with guardrails, browser QA, rollback, and production closure.

Nine production Claude Code skills and one command pack: repo security scanning, LLM-output validators, agent-fleet guardrails, credential hygiene. Deterministic cores, agentic edges.

Claude to Codex Migrator: convert Claude skills, plugins, and assistant packages into validated Codex packages.

Claude Code / GitHub Copilot 等向けエージェントスキル集（gh skill installで導入可能）

Self-overcoming skill libraries for AI coding agents. COMPASS synthesizes what's missing; SAGE evolves what underperforms — training-free, evidence-driven.

Skills for tracking fast-moving research without drowning in arXiv, benchmarks, and lab updates.

A Codex and Claude Code Agent Skill that revisits a focused subagent partner at key checkpoints to challenge assumptions before they become actions or answers.

Cohort Method — portable Agent Skill for multi-agent creative panels, UX swarms, build cohorts, and cross-QC (10 agents / 5 cohorts).

Skills for checking claims, auditing sources, detecting hallucinations, and labeling uncertainty.

Personal agent skills

Agent Skills for recording, sanitizing, and rendering terminal session demos - capture real command walkthroughs with agents, redact sensitive output, and render polished casts for READMEs and docs.

Installable MarineConnect agent skills and OAuth-backed MCP plugin for Codex and ChatGPT Work mode.

Skills for diagnosing prompt failures, compressing context, testing prompts, and reviewing system instructions.

Installable Agent Skills for integrating the Linkrunner SDK and deep linking, for AI coding agents (Claude Code, Cursor, Windsurf, Copilot)

Agent Skills that strip AI writing tells from copy - em dashes, 'it's not X, it's Y' constructions, hedging, and bloat - so text reads like a human wrote it, with evals to verify.

A personal, growing collection of agent skills, portable across Claude Code, Codex, Cursor, and other coding agents, each shipped as an installable plugin.

Portable Agent Skills for Codex, Claude, and compatible AI agents.

Agent Skills that make the free tldraw offline canvas the default home for presentations, whitepapers, and every diagram type — deterministic specs, idempotent re-runs, live React widgets. Works in Claude Code, Cursor, Codex and 70+ agents.

Agent skills for small and local models

Shared project memory across Codex, Claude Code, Kimi Code, Antigravity, and any coding-agent harness.

Memory-safe engineering-peer plugin for Claude Code + Codex: 11 skills, 6 bounded agents, 4 hooks. Claims only what it can prove; closes every turn with one next action.

A Design Gate for complex AI agent work: design first, execute second, preserve evidence always.

Evidence-led agent skills for CAD, engineering artifacts, independent review, and bounded revision

Entalpa MCP client instructions, Agent Skills, and plugin bundle

Bidirectional Codex and Claude coordination skills and plugins for reviewed, evidence-driven multi-agent delegation.

My personal Agent Skills for coding agents: engineering workflows plus a few personal-use tools. Personalized forks, with every upstream author credited.

Frontend design skill pack for AI coding agents: briefs, design systems, audits, motion, copy, and ship checks.

Provider-neutral Agent Skills compiler, validator, projection generator, and safe downstream installer.

Portable, self-contained agent skills for Copilot CLI / Claude Code / Cursor. First skill: project-room.

A skill library for AI coding agents with a CI quality gate: 38 skills, four-target sync, and an 18-check eval harness that fails the build on malformed skills.

BMad Method v6.10.0 packaged for Pi Coding Agent. Global & project-local install, portable defaults, project-scoped outputs, /bmad-init initializer. Retains bmad-investigate.

Small, harness-neutral engineering skills for coding agents

Unofficial, cross-platform Fable-inspired workflow skills for Claude Code and Codex, plus portable GPT prompt templates.

Guildshelf free funnel skills for Claude Code — Apache-2.0. Try before you subscribe: guildshelf.com

Operational product-management skills and a /pm router for Codex and Claude.

Official Scrappycoco MCP plugin and portable agent skill

Production-grade Agent Skills for Claude — reusable capability modules with tone rules, output contracts, eval suites, and CI validation.

AI job-search agent

Self-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.

Claude Code plugin to help write TableTest-style JUnit tests in Java and Kotlin

Offline security and compatibility auditor for AI agent skills

Provide Go agent skills for cleaner, idiomatic code across Claude Code, Cursor, Copilot, and more with one install

Human-paced stealth browser skill for AI agents — drives CloakBrowser behind Playwright MCP. Works with Claude Code, Codex, Cursor, OpenClaw & any MCP-capable agent. Evidence-gated, authorized browsing only.

A library of reusable instructions and Claude Code skills for AI coding agents.

Connect to the COTI blockchain to manage accounts, transfer native tokens, and deploy and operate…

Run SOQL queries against your Salesforce org to explore and retrieve data. Quickly iterate on filt…

Geospatial AI MCP server — satellite imagery, embeddings, weather, GNS governance