Claude
Tools

Claude API CLI demonstrating all 5 CCA-F certification domains — chat, tool use, agents, MCP, and safety guardrails in a single production-pattern tool.

The missing architectural layer above MCP. Production patterns for LLM agents wired to enterprise systems at scale — without context blowout, hallucinated tool selection, or audit gaps.

Coordinate multiple Claude Code terminals on one project — file locks, shared kanban, planner approval gate. Battle-tested in production.

JDfit · 简历岗位优化助手 — Claude Code Skill：智能匹配 JD 与简历，用 Word 原生批注解释每处修改的优化逻辑

Native macOS menu bar app to use your Cursor, Claude Code, ... subscriptions with AI coding tools

A Claude skill that audits a codebase end-to-end and produces a top-5-per-dimension improvement plan across seven lenses (Performance, Functionality, Stability, Reliability, Security, Usability, Attractiveness).

⚡ 2026 SEO Audit & Content Agent – Claude for SE Ranking MCP

Drive your own already-open browser from your AI coding agent (any MCP client) via a self-hosted relay + MV3 extension. Tools: screenshot (+full-page), navigate, click, fill, query, new_tab, evaluate (arbitrary JS, even on CSP-locked sites via userScripts). Toolbar activity flash + sqlite audit log for visibility.

Claude Code skill that ships a full production feature while you sleep. No push, you review.

A self-extending Model Context Protocol (MCP) server. Ships with one tool that creates other tools — describe what you need, get a working tool registered live.

Course-ready CLI reference for the Model Context Protocol. Demonstrates all six MCP primitives (tools, resources, prompts, sampling, elicitation, roots) wired to Anthropic's Claude. Adapted from Anthropic Academy for O'Reilly Live Training.

Claude Code skill: interview-style design review that persists the full decision tree + SaaS-vs-self-host cost tradeoffs to decision-tree.md. Fork of @mattpocock's grill-me.

A communication layer between you and your codebase: it keeps your AI coding agent talking in plain language — no jargon, no invented timelines — with one clear yes before anything irreversible.

v3 of the positive-routing anti-slop skill. Integrates WikiProject AI Cleanup's pattern catalog into v2's editorial layer without breaking the architectural principle.

Anthropic-standard Skill — decide API-vs-self-host LLM costs and fine-tune ROI from any agent context (Claude Code, Cursor, Codex). Live GPU+API prices, deterministic local math.

A hands-on tutorial for building a Claude Code-style coding agent with tools, memory, hooks, subagents, and plugins.

Claude Code skill — multi-agent orchestration loop (worker + adversarial validators) for complex production work

Agent skills for publishing engineering docs, repo summaries, PR digests, changelogs, API docs, onboarding guides, and specs to Uselink.

A Claude Code skill that designs, audits, and extracts CLAUDE.md — the highest-leverage prompt in any project. From ZenityX (จับมือทำจริง ใช้ได้จริง · Hands-on AI. Real results.) — bilingual Thai/English.

Principal-engineer operating mode for Claude Code: 5-phase loop, 30 red flags, cognitive layers for software and security, grounded chapter-by-chapter in 10 canonical engineering books. MIT.

Automatically mirror your spec-kit specs into Linear — one issue per spec, a sub-issue per task phase, kept in sync as you work.

A Claude Code skill that watches the source pages behind the facts you cite (prices, versions, limits, rules, deadlines) and updates every file that has gone out of date, once you approve.

Claude Code MCP native extension delivering a zero-human closed loop: Auto Bug Retrieval → Intelligent Troubleshooting → Automated Structured Accumulation. Equips Claude Code with long-term troubleshooting memory and establishes a reusable bug knowledge library for individuals and teams.

Chrome browser MCP for Claude — navigate, click, type, take screenshots, monitor network & console logs. Connects Chrome to Claude (Cowork / Claude Code) via a Chrome Extension + Python MCP server. 20+ browser control tools.