Claude
Tools

Agent skills for VillageSQL - gemini-cli-extension; claude-code-plugin

Claude Code skill that invisibly rates every external resource (WebFetch / WebSearch / MCP / curl) via PostToolUse hooks. Two rater backends: Anthropic API key or claude.ai subscription via 'claude -p'.

Skill Claude Code — méthodologie rigoureuse de recherche en droit français, conçue contre 14 modes d'erreur LLM.

Deepdive skill for Claude Code — 11-phase research pipeline: plan-review gate, parallel sub-agent search with circuit breaker, claims-ledger triangulation, relevance-filtered evidence, multi-angle red team, citation verification (liveness + faithfulness), machine-checked phase completeness. 105 blocks, 29 channels, 460+ stat sources, 39 APIs.

Open-source Claude Skill + MCP integration for job search and interview prep. Live job data, role-specific interview intel, voice mock interviews on four-leaf.ai.

A native desktop companion for Claude Code with hook-driven animations, permission controls, Pomodoro support, and OpenAI-compatible LLM proxying.

Claude Code skill that generates a publication-ready Table 1 (baseline characteristics) for clinical research data, with study-design-aware statistical policy (CONSORT 2010 for RCT, SMD-first for observational). Outputs HTML + Word (.docx) + LaTeX.

Claude Code plugin for Interactive Brokers — read-only IB Client Portal Gateway lifecycle, REST + Flex Web Service skills, options/portfolio/tax tooling, order-blocking hook.

Turn any URL into agent-callable MCP tools. One spec-compliant MCP server endpoint, no per-site build.

Claude Skill for scientific research, thesis, and academic paper writing. Analyzes documents, provides detailed feedback, suggests structural improvements, citations, and academic language enhancement.

从零开始系统掌握 AI Agent 工程：70 章完整知识体系，覆盖 LLM 原理、Prompt Engineering、Tool Calling、ReAct 推理、RAG 检索增强、Memory 记忆系统、Planning 规划能力、Multi-Agent 多智能体协作、生产部署与可观测性。适合有 Python 基础的工程师，从概念到生产级架构的系统级教程。全书由 Claude Code（Anthropic 官方 CLI）生成。

Should you care about this CVE? An agent skill that triages whether a CVE applies to your environment, with sourced, verifiable reasoning.

UltraCode is a local AI-assisted coding CLI inspired by Claude Code. It runs agentic coding workflows in your workspace with OpenAI-compatible models, function-calling tools, task planning, memory, permissions, hooks, background commands, MCP integration, and subagent support.

Long-term spoken-English coaching tracker for Claude Code: practice by voice in the Claude app, get scored reports, a mistake bank, trend charts, and an adaptive next-session focus.

Native Claude Code + Codex skills for AI security review. Also ships instruction files for Cursor, Copilot, and Windsurf. Checks 33 risks: OWASP LLM Top 10 2025 · applied RAG/MCP/agent checks · OWASP Agentic 2026.

集中版控 Claude Code 使用者層級設定(skills / hooks / settings.json / CLAUDE.md),以 symlink 連回家目錄 — 換機或重灌時 git clone + install.sh 一鍵還原。

💼 Recruiter-grade LinkedIn audit + copy-paste rewrites + action plan — a skill for Claude Code & Claude Cowork. 4 goal modes.

Never lose critical data in Claude Code. Extracts only nouns and verbs from conversations — 93% compression vs 70% for summaries. Structured anchors with bidirectional links, auto-saved via hooks.

赛博氛围灯编程：hook light。用codex、claude code、gemini等客户端的hooks让对话状态拥有更明显的提示

Vibe Dev — harness-first pipeline для Claude Code: от бизнес-идеи до работающего продукта. 20 проверяемых механизмов (hooks из коробки) + онбординг под пользователя (/setup).

Prompt Engineering skill for Claude Code — rewrites and optimizes prompts using proven techniques (Anthropic, OpenAI, Gemini, The Prompt Report).

Turn a short prompt into one clean, hand-drawn concept illustration starring a deadpan peanut — an agent skill for Claude Code and OpenAI Codex.

Measure the context-window tax an MCP server charges your AI agent — the real token cost of its tool schemas + responses. Ground truth (Anthropic count_tokens) or keyless estimate. Cross-platform single-file CLI.

🎓 Tutor interactivo para aprender a crear skills de Claude desde cero (escalera de 5 niveles). Skill creada por Luis Salgado · SalgadoIA, compartida por IA Masters Academy.