Writing & Editing

Five rigorous Codex skills for planning, brownfield stewardship, branch recovery, data provenance, and adversarial review.

Production-grade engineering skills and specialist agent personas for AI coding assistants. Orchestrates the full SDLC, from spec to ship, with structured verification gates, anti-rationalization checks, and senior-level engineering discipline.

A Codex skill for persistent agent–subagent interviews that explore user intent, surface novel solution paths, and keep decisions independently owned by the main agent.

Memory consolidation skills for Claude Code — read-only dream pass, checkbox/validator gate, full-auto mode, snapshot + one-command rollback. No rm, ever.

生产环境的 skill 自进化系统 | A production self-evolving system for Claude Code: every installed skill keeps accumulating evidence from real usage and evolves when the gate opens - governed, user-authorized, reversible.

A Claude Skill to perform security code review for repositories (code and Skill)

A browser for LLMs, not humans.

The security-first skill manager for AI agents — every install runs a security scan. Manage skills & MCP servers across 87 agents. Zero-dependency CLI.

A command-line interface for Garmin Connect - activities, health, workouts, devices, and more - with JSON output, secure credential storage, and a bundled agent skill for AI assistants like Claude Code, Codex, Hermes, and OpenClaw.

Delegate a coding task to a separate coding agent CLI, review the diff, land the commit yourself — one per implementer.

每日追踪 GitHub 最新热门 AI Agent Skills、用途与行业应用

Two Claude skills that pause AI work and hand the thinking to you on paper, then resume from your handwriting.

Reviews any draft for AI slop by writing where the point is fine but it's dressed up as a stock formula, forced metaphor, or filler instead of clear analysis. Flags it, explains why, and rewrites it in plain language. Works as a Claude Skill or a portable Gemini/ChatGPT system prompt.

Codex skill for turning photos into vertical editorial works with preserved subjects, limited abstract brushstrokes, and generous negative space.

Community-maintained agent skills for MapLibre GL JS — helping AI coding assistants write better mapping code

A supplementary CV VCS and custom Claude skill to store, score, modify, and proof check resumes.

A Claude Skill for end-to-end scholarly manuscript authoring — journal papers, theses, and systematic reviews.

A Claude skill that writes in a named author's manner — or in a functional writing register — either generating new text in that style, or rewriting text you supply while keeping its meaning intact.

🧩 A collection of Agent Skills + a `just` installer that symlinks them into any skill-aware agent's skills folder (~/.claude/skills/ by default) 🔗 — edits stay live and git-tracked.

Agentic system for situation report, secondary reviews, weekly bulletin, proposal writing and more

These are Skills I built for my private and professional life as a GTM consultant and ghostwriter for B2B tech founders & executives.

An integration platform where every capability is a plugin from the core — public shell, private overlay, no deployment state in the repo.

Claude skills

The supply chain for agent extensions — install an agent plugin into every AI coding assistant, with a lockfile, secrets off disk, and a scanner that reads what a plugin tells your agent to do.