Java books distilled into Claude Agent Skills — bilingual (简体中文 / English) skills for writing and reviewing Java code. First skill: Alibaba Java Development Manual (Huangshan Edition).

Curated registry of 250+ verified Claude Code skills — auto-discovered daily from GitHub, classified into 15 categories. Searchable hub at claude-skills.bdnhost.net. Includes English, Hebrew, Chinese skills.

Reusable, provider-agnostic AI team. Drop a project brief, get end-to-end delivery. 12 role agents + 112 skills + orchestrator + self-improvement. Works with Claude Code, Codex, or Gemini.

Claude Skills that hold AI-generated and AI-reviewed code to a rigorous, production-grade engineering bar — automatically.

Claude Code skill that preps a private repo for open-sourcing — sweeps code AND full git history for secrets and personal info, checks asset rights, adds the missing community files, and hands you a go/no-go checklist. 🔓

消除中文写作中的AI痕迹 — Claude Code / agent skill

面向 AI Agent 的论文 PDF 翻译 Skill：重建可读、可搜索、可逐页验收的多语言 PDF，支持复杂表格、图表与 Zotero 收尾。

Codex/Claude skill for designing robust scraping, API, Playwright, and authorized data acquisition pipelines

Deterministic word-count skill for Codex and Claude Code, with consistent Chinese, English, and mixed-text counting rules.

Skills to make your AI coding agent an Arcjet security expert.

SAOP (Sketch, Analyze, Optimize, Partition): a read-only planning skill for Claude Code. It sketches a solution, attacks it, optimizes the whole, and splits it into small checkable pieces before a single line is written. Errors surface in planning, where fixing them is cheap: a wrong assumption costs one small piece, not a whole block of work.

Free Claude skills that keep AI-assisted writing honest and yours: line edits, AI-tell checks, tone audits, full reviews, UX reviews, journey maps, copyright basics.

WordPress development plugin for Claude Code

Califa Cards: A Comprehensive Skill Card Standard and Testing Framework

Agentic engineering for vibe coders: from iPhone app idea to a secure App Store release, one gated phase at a time (Agent Skills open format)

LinkedIn, Twitter, blog, newsletter — one pack, every channel.

Evidence-informed skills for building strength, mobility, and lasting health.

Slide decks, reports, models, and templates — every business document, done right.

Custom Laravel skills for Claude Code

Kickoff skill for Claude Code / Codex: runs discovery, proposes a stack, scaffolds living docs, and writes a tailored CLAUDE.md before coding begins.

Claude skills for seeing what others miss: forensic-read, second-order, pre-mortem.

🚀 AI/ML Career Operating System — Claude Skill for ATS analysis, resume optimization, GitHub review, LinkedIn review, project evaluation, interview prep, and career readiness scoring

The most advanced AI text humanization framework. 45+ patterns, perplexity/burstiness engineering, and multi-pass self-audit pipeline for Claude Code, OpenCode, and LLMs.

Free Claude plugin for validated B2B event outreach emails and LinkedIn sequences.

An open Agent Skill that audits any website (new, in development, or already live) against a fixed set of engineering, git, and SEO/GEO/AEO standards

Claude that speaks cycle, chart, and era language — and obeys it. Glossary-first agent modes for cracked girls.

Spec-driven development skills for Claude Code: PRD → spec/contract → implement → contract-based evaluation with auto-fix

Claude Code & GitHub Copilot skill. Expensive head, cheap hands, a master decision-maker on a frontier reasoning model that never touches the repository, commanding subagent workers that do all the reading, running, and writing with adversarial gates at both ends.

Claude Code skill that explains the mental model behind any technical mechanism — who issues the token, who verifies whom, and why it's designed that way. 点破技术机制背后的信任拓扑。

Six Claude skills that run your AI job hunt: decode JDs, research companies, tailor resumes, write outreach that gets replies, drill interviews, negotiate offers. Salary benchmarks from real AI-native job postings.

A growing library of my published Claude Code skills — drop one into ~/.claude/skills/ and go.

A meta-skill for Claude Code (Anthropic CLI) that guides you through creating, testing, and iterating custom skills via structured conversation. Designed with LLM Council methodology: interview intent, generate draft, smoke-test immediately, refine until satisfied. A skill is just a markdown file — this tool embraces that simplicity.

Turn written specs into self-contained interactive HTML mockups with a closed feedback loop back to Claude Code. A Claude skill.

一个帮你高效备考任何大学课程期末的 Skill——尤其是选修课

An agent skill for organizing AI agent context with the dotagents standard (AGENTS.md + .agents/)

An AI coding protocol that stops vibecoding slop and forces you to write your own core logic.

Reusable Claude prompts for bento-grid visuals, brand files, mockups, and design workflows.

Skills Share

Generate in-depth research reports on listed companies — covering business models, competitive moats, financial trends, and risk analysis. Exports to Markdown and Word.

MCP registry skill — register servers, discover tools, allow-lists, health monitoring

一个 Claude Skill：上传课件 / 讲义，Claude 会通读全篇、分部讲解、逐页精讲，像老师一样带你过一遍材料。

Ranks your installed Claude Code skills/agents for a task and routes to the best one — and learns from your ratings.

Options & stock trading CLI for Interactive Brokers via ib_async, with preview/confirm/execute safeguards

Atelier - a premium, anti-slop frontend design skill suite for Claude Code: 11 skills + a deepdive knowledge base.

Claude Code skill that reviews PRs by trying to break them — hostile tests against every claim the diff makes, control-run against base so regressions are never confused with pre-existing weaknesses. 🥊

Claude Code skill that turns "it crashes sometimes" into the minimal script that crashes it every time — hypothesis hunt, tighten the trigger, delta-debug it down, then hand over the failing regression test. 🔬

Project design skill for Claude Code — assembles complete planning packages for software projects

an LLM skill package for senior-level WordPress development work: plugins, themes, Gutenberg blocks, REST endpoints, WooCommerce integrations, hooks, filters, security review, performance passes, and the usual little fires WordPress throws at you when someone says, “it should only take ten minutes

Pre-merge and pre-install trust checks for AI-agent skills and MCP configurations. Scan capabilities, detect risky changes, and block unapproved agent behavior in CI.

The financial-analysis skill collection for AI agents: sentiment, smart money, filings, and an adversarial investment committee, on one API key.

Long-term project memory for coding agents (Claude Code / Codex skill)

Claude Code skill suite for portfolio SEO ops: audits, topical maps, link acquisition, local pack strategy, GA4 telemetry, rapid indexing

Agents and skills that bring Quality Engineering into AI-assisted SDLC workflows. badquality.dev

Evidence-first deep research skills for AI agents, with source tracking, citations, contradiction checks, and uncertainty-aware synthesis.

Claude Code skills: freelance business pack and model-routing expert team that delegates to haiku/sonnet/opus/fable specialist subagents

The retirement handoff of Claude Fable 5 - written by the model itself. Domain-neutral discipline files that transfer flagship working method to any model, any agent framework, any team.

Defensive security skills for Claude Code and the Claude Agent SDK — web applications and generative AI systems.

From reference designs (screenshots, URLs) extract structured Design DNA, then generate self-contained HTML/CSS/JS with your content.

MELSEC iQ-RシリーズのシンプルCPU通信設定のCSVを扱えるようにするAgentSkill

GPT and Gemini image generation for Claude Desktop and Claude Code