Mining EDA for assay and lithology data. Automated statistical analysis and composite processing across multiple workflows (alt, rx, simpl). Generates comparative plots (Q-Q, Boxplots, Correlation) and CSV reports.

Six evidence-disciplined research workflow skills for coding agents. Install with npx skills, direct download, or git clone.

End-to-end spec-driven change workflow that fuses Superpowers process discipline with OpenSpec's spec-driven artifact lifecycle — from idea to archived living spec. Cross-platform (Claude Code + Codex).

自己跑、自己改、自己说了算的简易多 Agent 框架 · Conductor + Sub-agents · Skills + MCP · 多设备同步

Compliant sales enablement skill for licensed annuity and life-insurance professionals

OpenClaw skill for practical suggested next actions with clickable buttons when supported

Sample coding task with a skill spec, reference solution, pytest verifier, Dockerfile, and ten annotated attempt trajectories.

Portable DESIGN.md workflow skill for agent-driven frontend design

zilin 的个人 Agent Skills 库，真实在用的开发能力，可被 Claude Code / Cursor 等 50+ agent 自动发现安装

Claude Code plugin orchestrating agentic coding sessions — primers, session logs, and knowledge consolidation

A collection of portable, domain-focused AI agents managed by kman.

Generated by Codex. Read with caution.

Claude Code skill for storyboard-style screen design docs (스토리보드식 화면설계서). Docs/demo: https://cskwork.github.io/storyboard-spec/

Surface the highest-priority next task across recent coding-agent sessions (Claude Code, Codex, Gemini, +extensible). Domain-agnostic Claude Code skill.

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills,

A Codex skill for complex AI projects using anchor prompts, phase boundaries, branch windows, and confirmation gates.

Research-backed AI self-audit skill for Claude Code / Codex / OpenClaw. Verifies high-stakes answers via independent re-solve + cross-method probe — not by critique. Honest about limits; every design choice has a paper citation.

Skill for your agent to generate standardized interactive HTML artifacts with diagrams, animations, flash cards, quizes etc. instead of simple markdown

A portable Agent Skill for practicing love as communication, repair, emotional regulation, boundaries, and compatibility.

Reusable agent skills for real repository work: review, implementation, release, documentation, and project hygiene.

Agent skill for safe legacy-code refactoring and maintenance workflows

Vectorize raster scientific figure panels into editable HTML and semantic JSON.

Prove whether a SKILL.md actually changes agent behavior (with/without) and which CLI harness does a task best — agent-native subagents or CLI. agentskills.io-compatible. Site: https://cskwork.github.io/skill-ab-eval/

Théo's collection of Agent Skills for GitHub Copilot

Universal AI agent skills (Claude Code, Cursor, Codex, GitHub Copilot, OpenClaw). Build once, use everywhere.

Agent Skill and handoff protocol for safely coordinating Codex, Claude, and other frontier AI models.

Codex-style /goal workflow for GitHub Copilot prompt files and agent skills

A Ryvn CLI agent skill that gates regulated BYOC deployments before they ship

Production-grade Codex image_gen bridge for Claude Code. Sandbox-correct, gpt-image-2 only.

Code-To-UML is a zero-dependency, browser-first PlantUML rendering tool for converting code into interactive UML reports. No building tools needed, pure HTML/CSS/JS implementation, service provided through lightweight Node.js development servers.

An open protocol for human-AI teaming.

A general-purpose coordination protocol for multiple AI coding agents working on one repository with worktree isolation, structured handoffs, review, testing, and merge readiness

Systematic methodology for optimizing agent skills using deep-learning-style approach. Based on arXiv:2605.23904

⌨️ 123-flow — three number keys to run your AI-coding workflow: 1=do, 2=review, 3=ship. A Claude Code skill/plugin. 三个数字键接管 AI 工作流

Opinionated Next.js 16 starter for building with AI agents — ship features fast while architecture and directory structure stay under control: fixed structure, enforced conventions, curated libraries, preinstalled skills, native toolchain.

Portable Codex agent harness and config monorepo with reusable roles, skills, validation, eval tooling, and safe project install sync.

Complete guide to minimal universal configuration files compatible with all major AI coding agents.

Sallyn's personal collection of reusable coding agent skills

Crawls articles from WeChat Official Accounts. Searching the name of any accounts（using personal cookie）gets the content.

The inverse of "humanizer". The tool that turns human-like prose into classic, corporate, buzzword-heavy AI fluff.

High-agency agent skills for executable specs and end-to-end shipping.

Agent skill teaching Google's code-review standards (eng-practices) for Claude Code, Codex, and any agentskills.io-compatible agent. Cross-agent install via symlink + install.sh.

A portable Agent Skill that checks project rules, verification paths, review workflow, and done criteria before agentic development starts.

Write AI prompts in TypeScript and run them with any harness that supports skills (claude code, codex, opencode, copilot, cursor, windsurf, etc.)

Decision Foundation: a free agent skill for mapping every viable path before deciding.

Agent skill that audits and hardens basic security on a Debian/Ubuntu server over SSH with fail-safe rollback for sshd changes.

Rank Java files, methods, and REST API endpoints by a deterministic Composite Hotspot Score (recency-weighted churn × cognitive complexity × JaCoCo coverage gap) to prioritize test generation. Also a Claude Code skill/plugin.

GenPark skill: Integrate CANLAH AI's Style Genome and multi-agent business suite for marketing, sales, and service automation.

GenPark skill: Integrate iSales AI concepts for automated sales chatbots, lead qualification, and in-chat payments.

Agent skills for popular work processes: GTD, OKR, PDSA, DMAIC, Design Thinking, Lean Startup, OODA, and research paper writing.

Split slide/page images into transparent visual layers with region schemas, OCR racing, and QA artifacts.

🧭 A Claude skill for translating professional judgment to decision-makers — without losing density. Part of Where Judgment Lands toolkit.

General browser QA orchestrator skill for web apps, local dev stacks, and Docker Compose deployments.

A handy toolbox of AI agent skills that are compliant with https://agentskills.io specification.

Local-first Agent Skill Runtime for packaging SOPs, schemas, preflight checks, run records, and MCP tools as executable skill capsules.

Governed operator skill for structured, scoped, validated and traceable agent work with contracts, event logging and controlled mini-prompt chains.

A Claude Agent Skill for writing, reviewing, and refactoring code using Robert C. Martin's Clean Code framework.