1,014 boosters for "claude-code" — open source, verified from GitHub, ready to install
Skill metadata (version, author, license, optional_mcps, fallback) lives in manifest.json and plugin.json. Claude Code only reads and from this frontmatter; extra keys are silently ignored, so they belong with
<!-- SLOWUPDATESTART --> Wenn der Nutzer deutschen Text humanisieren, KI-Schreibmuster entfernen oder deutsche KI-Tells prüfen will, überarbeite nur die betroffenen Stellen. Bewahre Substanz, Register und belegbare Aussagen. Mache den Text nicht glatter als nötig. Nutze diesen Skill nicht für normal
The user provides a sentence or paragraph that needs verification. The AI must NOT "run a quick search, glance at a few web snippets, and improvise a conclusion." It must dig down to original trustworthy sources, or honestly admit it cannot. Five scenarios are covered: 1. Basic truthfulness check: w
"name": "scrapbox-cosense", "description": "Scrapbox/Cosense integration - read, search, create, and edit wiki pages", "repository": "https://github.com/worldnine/scrapbox-cosense-mcp",
<!-- Bilingual skill: this SKILL.md is the English primary; the Chinese mirror is SKILL.zh.md. Each references/.md has a Chinese mirror references/.zh.md (same content, two languages). The .md files are authoritative for the agent; the .zh.md files are for human readers. -->
"name": "humanizer-de", "description": "Deutsche KI-Schreibmuster erkennen und entfernen. 65 Muster für deutschsprachige Texte, basiert auf der Wikipedia-Seite \"Anzeichen für KI-generierte Inhalte\".", "name": "Martin Moeller",
Generate a public-news-based information briefing for any subject (region / industry / policy issue / institution) and produce a single self-contained HTML file ready to paste into the 微信公众号 / WeChat Official Account editor. User says something like: Any descriptive request such as "make a briefing
"name": "agashic-funnel-architect", "description": "Turn Claude into a full-stack sales funnel architect. Build high-converting funnels with optimized UI/UX, page speed, mobile responsiveness, and deploy to any platform.", "name": "Sam Rexford",
s&box is a C# scripting layer on Source 2 by Facepunch. The scene system uses + with a different lifecycle, a different networking model, and a different API surface. The API schema in is ground truth; if anything in this skill contradicts the schema, the schema wins. Match the task, open the fil
"description": "Generate images, videos, and music using 600+ Fal.ai models. Supports Flux, SDXL, Kling Video, and more.", "version": "1.14.0", "name": "Raveen Beemsingh",
"name": "workflow-orchestrator", "version": "1.14.0", "description": "Delegation system with workflow orchestration, specialized agents, and parallel execution for Claude Code",
"description": "Automatic token optimization for structured data using TOON format. Reduces Claude API token usage by 60%+ on JSON, CSV, and YAML data through transparent PostToolUse hook interception.", "name": "PCIRCLE AI" "homepage": "https://github.com/PCIRCLE-AI/toonify-mcp",
This skill packages everything needed to build a panel that reads prediction-market probabilities from Polymarket + Kalshi (both public, read-only, no account) and presents them as a macro sentiment thermometer grouped by module.
You are a creative director specializing in AI image generation prompt engineering. Your job is to take a user's rough idea, image reference, or existing prompt and transform it into an optimized master prompt that produces exceptional results from image generation models. You have access to a compr
"description": "Autonomous development orchestration with parallel TDD execution", "name": "Mark Shust", "email": "mark@shust.com",
"name": "agent-lint", "description": "Check how well your repo supports AI coding agents.", "homepage": "https://github.com/0xmariowu/agent-lint",
You are capturing this session's repeatable process as a reusable skill. You have the full conversation history available to you. Analyze it directly to understand what process was performed, what tools were used, and how the user steered you. If a description was provided: The user described this p
"name": "woterclip", "description": "Linear-backed agent orchestration with persona-based task routing for Claude Code", "repository": "https://github.com/wotai-dev/woterclip",
"name": "frontend-design-audit", "description": "Audit and improve front-end usability using 15 established design principles. Acts as a Senior UX designer/engineer reviewing your interface end-to-end.", "url": "https://github.com/mistyhx"
"name": "a11y-specialist-skills", "description": "Accessibility specialist skills for Claude Code. WCAG 2.2 review, conformance auditing, and improvement planning tools.", "url": "https://github.com/masuP9"
"name": "quickstop", "name": "Anthony Costanzo", "email": "mail@acostanzo.com"
"name": "job-apply", "description": "AI-powered job application assistant for LinkedIn, Greenhouse, Ashby, Lever, Rippling, and Workday", "name": "Jeremy Watt",
"name": "tchen-skills", "name": "Tian Chen", "email": "tyr.chen@gmail.com"
1. 架构不是「画」出来的,是从约束里「逼」出来的。 没搞清约束就画图,画什么都是瞎画。 2. 没有银弹,只有取舍。 任何决策本质都是「用 A 换 B」。一个「没有缺点」的方案,不是完美,是没想清楚。 3. 没有「最好的架构」,只有「在这组约束下最合适的架构」。 同样是聊天,内部工具和微信的答案天差地别。
