一组可独立装载的 Agent / Claude Code Skills：编码行为准则、横切规范、多仓脚手架与多 agent 代码审计

A safe docker compose wrapper for local development, plus the agent rules and skill that stop AI assistants from wiping volumes or hanging on logs

Thin agent adapters for @paniolo/scan — run the AI Technical Debt Scanner from any coding agent and optionally remediate findings. Portable skill (npx skills add paniolo-ai/scan --all), Claude Code plugin (/paniolo-scan), Antigravity workflow, GitHub Action. Not the scanner source.

🤖 AI 驱动的 Obsidian 知识库自动化管家 · Zettelkasten + PARA + 渐进摘要 · 零手动维护

Bragi（布拉吉）— 把一眼假的 AI 草稿改成对的人爱看、内行挑不出毛病的稿子。去AI味(两层破绽清单+人话参照) · 对准角色(换讲法卖出去,载体全留) · 逼垂类纵深(不造料只逼真料) · 溯源审稿(每句可追源)。支持改写与0→1从素材建。

Claude Code skill (v2, modular): raw idea → researched, phased, implementation-ready product programme. Lean core + 11 reference files + evals.

Skill that turns a chat conversation (claude.ai / ChatGPT) into a brief any coding agent can build from

SDD, but for landing pages — a phased multi-agent workflow that ships modern, high-converting landings that don't look AI-generated. One-command install.

Agent skills for working with jsPsych — best-practice guides for building plugins and timelines, usable in Claude Code, Cursor, Copilot, and other skills-compatible agents.

Open Agent Skill for PE-grade system design interview prep. Generates 10 artifacts per problem with quality gates, cross-file checks, and a Python validator. Works with Cursor, Codex, Claude Code, Copilot, and Gemini CLI.

Analyze LLM agent codebases as architecture reports.

Claude Agent for automated API migration using Anthropic Skills & Subagents. Migrates Python/JS code from deprecated APIs with parallel subagents, progressive disclosure, and structured outputs.

Upgrade GitHub Actions versions interactively from your terminal

Yap at your UI — live HTML preview with a two-way feedback loop, as a Claude Code skill

Shippo's AI distribution surfaces: Agent Skills + plugins for Claude Code, OpenAI Codex, ClawHub, and the Claude apps.

An AI council that picks its own experts — adaptive multi-persona panel with preserved dissent. Skill for Claude Code, Codex & the Claude app. EN+PL.

Make your repo agent-ready for Claude Code, Codex, Copilot, Cursor, and AI coding agents.

bathe your agents in engineering rigour and flames

把任意概念讲成寓言的 Agent Skill — Turn any concept into a fable people remember and retell.

Agent Kaizen skill for Claude Code & Codex, etc: build, review & validate agent skills, SKILL.md drafting, trigger descriptions & frontmatter, references/scripts/assets, progressive disclosure, gotchas, verification checks, forward tests and skill-generation prompts. Applies the Spec -> Verifier -> Environment method.

Skills and guardrails that make AI coding agents prove their work: planning gates, test preflights, fail-closed deployment, and a self-improving skill library.

Stop guessing which agent skills exist. Describe your task naturally and Skill Advisor finds the right tools for you. Cross-agent compatible (Claude Code, Codex, Cursor, Copilot & more).

An Agent Skill that reviews and writes PostgreSQL/Supabase authentication code against a researched set of common and uncommon security mistakes - before it ships.

Agent Skill for optimizing Apache Hive on MapReduce — 26 actionable best-practice rules covering storage, query, JOIN, data skew, and MR parameter tuning. Works with Cursor & Claude Code.

An AI second brain with an action layer — Notion + Claude.

Session handoff skills for coding agents — Claude Code, Codex, Cursor, Gemini CLI & Grok Build. Capture a session to a file, then resume it fresh.

Codex Agent Bus skill family for local multi-agent coordination

repaint — a self-contained npx-skills / Claude Code skill for frontend UI that doesn't look AI-made: research, tokens, a reference library, and a live browser slop-audit loop.

Who Am I Skill — personality tests ask 60 questions; your machine already heard 8,000 answers. A skill that turns your local AI conversations into an evidence-grounded self-portrait. Local-only, zero deps.

Browser use, but for terminals: agents drive Ghostty, test CLIs and TUIs, and read the screen back (macOS)

Talk to a humanoid in a 3D apartment — on screen, in VR, or in your real room (MR). Voice/text commands, an open-source BYO-key LLM brain, and ~950 composable motion skills. Three.js + WebXR (Quest 3).

Make AI copy stop sounding like AI. A Claude Code / Agent Skill for character-voice rewriting with linguistic fingerprints.

Forkable, draft-only multi-agent GitHub-notification triage on ZeroClaw / Claude Code

Agent skill for reverse-engineering undocumented website APIs with Chrome CDP, curl, and JS bundle analysis.

沉淀十年实战的地产项目品牌叙事的结构化方法论“故事线storyline“ · Agent Skill — 覆盖住宅 / 办公 / 商业三业态。向内梳理项目的资源禀赋与价值根基，向外审视市场生态与竞争格局，最终找到那个最锋利的切入角度，形成完整的叙事逻辑，回答根本问题“这个项目凭什么值得被讲述？”。

Config-driven SDLC skills for coding agents: task flow, releases, debugging, and security triage.

mcp server serving coding agent skills with helper tools

An agent skill for DeFi incident investigations with parallel multi-agent investigation and adversarial validation, generates schema-compliant reports

Consensus & debate board for error-not-allowed work: diverse lenses either verify new work before it ships (Generate), or inspect existing work and report findings (Audit/Review). Bounded cost + zero-breakage. Cross-agent - validated on Claude Code + Antigravity. Part of TheColliery.

The lazyway.io design system as a portable kit: tokens, component classes, zero-dependency JS, favicon tooling, and an Agent Skill that keeps AI-generated UI on-brand

A fully local Markdown memory system for AI agents. No cloud, no lock-in.

A Claude Agent Skill that turns anyone's public footprint into one interactive, sourced HTML profile board — identity, contact, expertise, work, highlights, and an optional LLM-visibility read.

Turn supported RAW files into verified Fujifilm-ready DNG copies for Lightroom—without touching originals.

🏃 Sprint — every TODO item gets a full mini-sprint: autonomous plan→implement→review for Claude Code via git-hook agent chain, isolated worktree, deterministic gate & fail-closed review

Agent Skill for building SEO/GEO-ready corporate, brand, B2B, and proposal-grade business websites.

Eleven free, vendor-neutral AI engineering skills for common SDLC workflows.

Agent Skill for turning reference media into reusable prompt packs, shotlists, video packaging prompts, thumbnail prompts, and content systems.

Swiss Army knife for AI visibility & GEO. 50+ GEO tools, audits, benchmarks, prompts, and monitoring — all in one super-skill. Install once, run anything.

Cross-platform AI-agent skill for natal and relationship astrology — Codex, Claude Code, Cursor, Cline, Windsurf and JSON CLI

Run and verify code changes by driving the real app — run, verify, and run-skill-generator skills for Claude Code, Codex, and Antigravity

I've Got the Big Sad: a low-affect response-compression skill for Codex with bilingual docs and token evaluation.

Evidence-first meeting minutes for AI agents: decisions, actions, numerical scope, traceability, and cross-validation.

Claude Code plugin marketplace of my personal agent skills

Clear technical writing for AI agents.

Factorial design amplification skill for Claude Code — 5x → 10x → +3x staged UI polish with adversarial design judges

Agent plugins/extensions for Shopify App Store intelligence.

Dual-runtime Agent Skills for Claude Code, Codex GPT, CC Switch, and authorized CTF workflows.

Agent skills for Home Assistant: connection doctrine, instance mapping, verified automations, and price/LLM-driven triggers. Claude Code plugin marketplace included.