Recently Added
Fresh skills just added to the collection. Be the first to try them out!
🚀 Wire Code: Premium Demo Orchestrator v2.0
by vasylniger34-lgtm
НАГАДУВАННЯ: ui-ux-pro-max + 21st.dev = обов'язкові інструменти для кожного Wire Code проекту. Без них якість недостатня.
Design System — Agent Instructions
by llgsoldiersonly
content.md — grid system, responsiveness
Boris-Token-Slim
by ZCDeng
审计并精简 Claude Code 的隐性 token 开销——CLAUDE.md 臃肿、MEMORY 过期记录、插件爆炸、MCP 常驻、死 symlink、scientific-skills 大类、重复 skill。用户说"优化 token""Claude Code 变慢了""减少 token 消耗""claude 变笨了""额度不够用""audit claude code""slim down claude code"时触发。也响应 /Boris-Token-Slim。
storytelling-with-data
by AliDujie
数据可视化与数据叙事技能，基于 Cole Nussbaumer Knaflic《Storytelling with Data》 方法论。提供 8 项可执行能力和 11 篇知识库文档，覆盖上下文分析→图表选择→去杂乱→ 注意力引导→设计评估→故事构建→综合诊断→图表改造完整工作流，以及 CEO 决策视角扩展。
gptnb-image
by yangyixxxx
"Generate images and videos via gptnb.ai. 图像：gpt-image-2 / gpt-image-2-vip(分层) / dall-e-3。视频：seedance 2.0 / 2.0 fast / 1.5 pro / 1.0 系列（doubao-seedance-*）。Use when the user asks to create/generate images, posters, layered images, videos, animations, or mentions gptnb / seedance / doubao-seedance. 支持文生图、图生视频、首尾帧视频、多模态参考视频。"
SKILL.md — arqel-dev/export
by arqel-dev
ADR-008 — Pest 3
SKILL.md — arqel-dev/workflow
by arqel-dev
Externos: spatie/laravel-model-states (suggest — integração canônica, opt-in)
SKILL.md — arqel-dev/ai
by arqel-dev
PLANNING/10-fase-3-avancadas.md §2 (AI fields) — roadmap completo + tickets AI-001..AI-016.
aido-wrapper
by mdhb2
"Multi-platform AI development lifecycle wrapper for Antigravity, OpenCode, Copilot, and Gemini CLI. Provides a suite of workflow commands prefixed with /aido."
Harness: Project Development Scaffold Meta-Skill
by xwtro0tk1t-cloud
templates/agent-role.md Agent role definition template
required-attribute
by PoleonDe
Use this skill when working with the Control Tools Required Attribute Unity package, especially when adding required-field validation, explaining package behavior, or changing its Unity Editor tooling.
lolla
by gofarrrr
Conversation-aware reasoning audit. Captures the current conversation, extracts decision structure, and runs the full Lolla pipeline (structural pressure, model companion, frame pressure) via OpenRouter against a curated substrate of 222 mental models. Use when asked to "audit this", "check my reasoning", "find blind spots", "stress test", "what am I missing", "challenge this", "devil's advocate", "lolla", "what are we not seeing", or "pre-mortem". Also use proactively when the conversation contains strategic advice that hasn't been challenged. Do NOT use for coding tasks, simple Q&A, or non-strategic topics.
CyberOwl AI Skill
by karimhabush
Aggregates security advisories from 10 international CERTs daily and provides an AI skill that cross-references alerts against your project's tech stack.
re-frame-pair
by day8
Pair-program with a live re-frame application via shadow-cljs nREPL. Inspect app-db, dispatch events, hot-swap handlers, trace dispatches, read epoch data, time-travel, and perform post-mortems without source edits when probing. Use whenever the user asks about their running re-frame app or mentions: re-frame, app-db, dispatch, subscribe, reg-event, reg-sub, reg-fx, epoch, interceptor, re-frame-10x, re-com, shadow-cljs.
Waiona — SKILL: Generación de Código
by rodrigozucchini
¿Hay spec de service y controller?
hebrew-writer
by baldiga
v5 — Write Hebrew content indistinguishable from a native Israeli human. Generates, rewrites, or detects AI patterns in Hebrew text. 9-layer system with Variation Fingerprint Engine: Hebrew-first thinking, 55+ AI pattern detection, Israeli voice injection, linguistic precision, rhythm engineering, self-audit scoring (95/100 threshold), adaptive voice cloning (Key Tells + style-extreme passages + calibration loop), Soul Layer (נשמה עמוקה), and Versatility Engine (מנגנון המגוון). v5 adds: Pre-Write Commitment Oath (Step 0), Soul-First Planning (Step 4b), Tier 1 Violation Scanner (Step 6.5), Tier 1 auto-fail severity system in Self-Audit, reordered Quick-Check Checklist (Tier 1 items first). Enforcement rebuild — all rules from v1-v4 already existed; v5 ensures they execute. Grounded in PNAS 2025 register-leveling research, Antislop ICLR 2026 (8,000+ pattern taxonomy), MATTR lexical diversity, and Hebrew argumentative discourse stance research (Frontiers 2025). Use when: writing Hebrew content, humanizing Hebrew text, checking Hebrew text for AI tells, or matching someone's Hebrew writing voice. Triggers: "write in Hebrew", "Hebrew content", "כתוב בעברית", "humanize Hebrew", "sound Israeli", "Hebrew blog", "Hebrew article", "rewrite in Hebrew", "detect AI Hebrew", "תכתוב לי", "shadow writer"
frontend-design
by regev-ima
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
doc2ml-json
by usagi-epta
Ingest any document (PDF, EPUB, DOCX, TXT, HTML, Markdown) and convert it into structured, ML-ready JSON. Use when the user asks to: extract text from documents, convert documents to structured data, create ML datasets from documents, parse PDF/EPUB/DOCX content, chunk documents for RAG, or produce tokenizable JSON from unstructured documents. Triggers on file uploads of supported formats or requests mentioning document conversion, text extraction, dataset creation from documents.
project-brain
by Ethan-YS
Use this skill when the user explicitly asks to set up, resume, update, or hand off persistent project context for AI-assisted work. Triggers (all require an explicit user request — do NOT activate just because a brain/ folder exists): (1) The user wants to set up project-level memory ("set up project brain", "scaffold project context", "init project brain", "建项目脑"). (2) The user is in a directory containing brain/ AND explicitly asks to resume / continue / load the project / check status / "what's the state of this project". (3) The user signals window switch / context compaction ("switch windows", "context's getting full", "I'll head out", "压缩了") — write a HANDOFF before they leave. (4) The user says "update the project brain" / "let's record this" / "更新项目脑" — propose a list with reasons; user approves per item. Do NOT auto-activate during casual conversation that happens to occur inside a brain/-bearing directory. The methodology's "activation boundary" requires an explicit user request. This skill provides a folder structure (brain/), copy-able templates for multiple AI tools, and a four-workflow protocol (startup / kick-off / update / handoff). Methodology details in METHODOLOGY.md alongside this file.
nebula-insurance-data-contracts
by gajakannan
"Work on Nebula's platform-neutral canonical insurance data contracts. Use when designing, editing, validating, documenting, or generating ODCS v3 YAML contracts, modeling patterns, design decisions, glossary terms, or target-specific implementation guidance for this repository."
web-publisher
by sipingme
输入文章 URL 或本地文档（PDF/DOCX/PPTX/XLSX/EPUB/图片/音频/...），自动提取正文、可选 AI 改写、并发布到微信公众号；也可只把任意文档转成 Markdown 文本（不发布）。抓取 / 转换 / 改写 / 发布都在服务端 (tools.siping.me) 完成，CLI 不装任何 npm 依赖；登录、公众号配置全部通过对话 + 一次性浏览器跳转完成。⚠️ 服务端走云端固定 IP，对小红书、部分知乎专栏、登录墙文章、海外站点经常被反爬挡掉——此时由 AI Agent（Hermes / Cursor / OpenClaw 等）改调用用户本地安装的 news-to-markdown-skill 把 URL 抓成 Markdown，然后人工复核 / 归档。也可配合 browser-web-search 先搜索拿到 URL 再批量发布。
wecom-cs-mano
by JZQiang
"企业微信智能客服 V4（全自动版）- mss截图 + PIL红点检测 + EasyOCR + DeepSeek AI + pynput打字，全自包含无需外部API视觉模型"
fbs-bookwriter-lrz
by sawakso
"福帮手出品 高质量长文档手稿工具链：书籍、手册、白皮书、行业指南、长篇报道、深度专题；支持联网查证（宿主允许时启用，离线自动降级）、S/P/C/B 分层审校、中文排版与 MD/HTML 交付。触发词：福帮手、福帮手写书skill、福帮手写书、写书、出书、写长篇、写手册、写白皮书、写行业指南、协作写书、定大纲、写章节、封面、插图、排版构建、导出、去AI味、质量自检、图文书、写报道、写深度稿、写特稿、写专题、写调查报道、写长文、拆书改写、海外本地化改写、爆款结构改写、激活原料、原料盘点、整理素材、续写、继续写、接着写、补写、扩写"
Constraint Enumeration Protocol
by Droptops
It remains decision-useful rather than merely verbose.