#SkillRepo stars
- 17233Juridico Content Strategythicazu-png/claude-skills-advocaciaPlaneja estratégia editorial e calendário de conteúdo jurídico digital para advogados. Use quando o usuário quiser criar pautas, séries, funis informativos, calendário para LinkedIn, blog, newsletter, vídeo ou autoridade profissional jurídica.10
- 17234Labor Law Business Contentthicazu-png/claude-skills-advocaciaCria conteúdo jurídico trabalhista para empresas, RH, jurídico interno, compliance e gestores. Use para posts, artigos, newsletters, roteiros, checklists e análises sobre CLT, relações de trabalho, passivo trabalhista, terceirização, pejotização, jornada, assédio, políticas internas e contencioso empresarial.10
- 17235Legal Accuracy Reviewthicazu-png/claude-skills-advocaciaRevisa precisão jurídica, coerência, fontes, limites de tese e riscos de alucinação em conteúdo jurídico. Use para checar posts, artigos, pareceres curtos, newsletters, roteiros e análises antes de publicação ou envio.10
- 17236Legal Ops AI Managementthicazu-png/claude-skills-advocaciaEstrutura rotinas internas de escritório jurídico com IA, incluindo triagem de demandas, produtividade, padronização de entregas, controle de qualidade, gestão de conhecimento, playbooks, checklists, dashboards operacionais e governança de uso de inteligência artificial.10
- 17237Multichannel Repurposingthicazu-png/claude-skills-advocaciaAdapta conteúdo jurídico-base para múltiplos canais digitais, incluindo LinkedIn, newsletter, blog, roteiro de vídeo curto e carrossel. Use quando o usuário quiser reaproveitar uma tese jurídica ou artigo em formatos diferentes com linguagem adequada a cada canal.10
- 17238Oab Compliance Reviewthicazu-png/claude-skills-advocaciaRevisa conteúdo jurídico digital de advogados brasileiros sob a ótica de ética, sobriedade profissional, publicidade informativa, mercantilização e captação indevida. Use antes de publicar posts, artigos, anúncios, landing pages, newsletters, vídeos ou CTAs jurídicos.10
- 17239Pureclip OptimizationHelmholtzAI-Consultants-Munich/helmholtz-agent-skillsTune PureCLIP parameters for protein-RNA crosslink site calling on eCLIP, iCLIP or PAR-CLIP data9
- 17240Visual Law Legal Designthicazu-png/claude-skills-advocaciaTransforma conteúdo jurídico em visual law, legal design e materiais visuais claros, incluindo quadros comparativos, checklists, mapas mentais, fluxos decisórios, carrosséis, one-pagers e resumos executivos. Use quando o usuário quiser tornar informação jurídica mais compreensível, escaneável e visualmente organizada.10
- 17241Adversarial Verificationkadaliao/claude-code-skills-collection对抗性验证技能 — 验证代码变更/部署/任务交付物的正确性。不是确认"它能工作",而是尝试"把它搞坏"。用于:(1) 完成非平凡任务后自验 (2) 审查 PR/MR (3) 部署后验证 (4) bobooo 说"验证一下"。灵感源自 Claude Code Verification Agent 设计。9
- 17242Brd to Prd By KookyKookyJinn/kooky-skills-prd引导业务人员通过结构化访谈澄清需求,输出业务需求文档(BRD)。当用户描述业务需求想法、功能诉求、系统改进建议,或说"我要提需求"、"我想加个功能"、"这个流程有问题"时触发。核心原则:反复追问直到需求完全清晰,绝不跳过任何模糊点。9
- 17243Compound Devbrijoobopanna/ClaudeSkillsMake Claude Code sessions compound — every session builds on the last instead of starting from scratch. Implements Karpathy's LLM Wiki pattern for software engineering. Use this skill when starting a new project, onboarding to an existing codebase, or any time the user says "set up my project", "add project memory", "create CLAUDE.md", "help me structure this project", "I keep re-explaining things to Claude", "my sessions don't remember anything", "ingest this document", or "run a health check". Also trigger when the user asks about session efficiency, token usage, or wants to improve their Cl9
- 17244Coordinator Orchestratorkadaliao/claude-code-skills-collection多 Agent 协调者模式 — 你是指挥官,不是执行者。调度 Worker 做研究/实现/验证,你负责综合和决策。适用于:(1) 复杂任务需要多步骤并行 (2) 需要研究→综合→实现→验证的工作流 (3) bobooo 说"用 CC 做"时的编排模式。灵感源自 Claude Code Coordinator Mode。9
- 17245Deep Documentationadamdroberts/agent-skillsCreate, expand, reorganize, and maintain repository documentation with deep coverage across README files, browsable docs, API/reference pages, llms.txt, llms-full.txt, changelogs, and repo-local agent skills. Use whenever the user asks for comprehensive project documentation, documentation refreshes, LLM-friendly docs, documentation synchronization after code changes, or agent guidance that teaches future LLMs how to use the project docs.9
- 17246Event Modelingnoahseger/agent-skillsUse to model a system's behavior as domain events, extract an event model from existing code, design event-driven architectures, or document workflows as timelines of commands, events, and state views9
- 17247Gemini Nano Banana 2tamtom/image-generation-skillsGenerate and edit images using Google's Gemini Nano Banana 2 (gemini-3.1-flash-image-preview). Use when the user asks to generate, create, edit, modify, change, alter, or update images using Gemini. Also use when user references an existing image file and asks to modify it in any way. Supports text-to-image generation, image editing, multi-image compositing (up to 14 reference images), style transfer, Google Web Search and Image Search grounding for real-time data, high-resolution output up to 4K, controllable thinking levels, 14 aspect ratios, and advanced text rendering. DO NOT read the imag9
- 17248Hebbshebbs-ai/hebbs-skillCognitive engine for AI agents: index files and memories, retrieve across 4 weighted dimensions (similarity, temporal, importance, frequency), automatic insight consolidation, automatic contradiction detection, with full parameter control on every function.9
- 17249Hebbs Tunehebbs-ai/hebbs-skillRetrieval tuning skill for HEBBS: profile the client, generate domain-specific evals, run baseline, tune retrieval parameters, store learnings, and export compiled rules to a markdown file for prompt injection.9
- 17250Lazynoahseger/agent-skillsBe lazy for humanity's sake when you are solving a problem, asked a deepening question, reviewing code, or thinking.9
- 17251Lightweight Explorerkadaliao/claude-code-skills-collection轻量探索模式 — 用最少 token 完成代码搜索和调研。核心理念:只读搜索不需要加载全部工具和项目规则。适用于:(1) 搜索代码库找文件/函数 (2) 调研项目架构 (3) 多文件分析 (4) 回答"代码里哪里有 X"类问题。灵感源自 Claude Code Explore Agent 设计。9
- 17252Memory Type Systemkadaliao/claude-code-skills-collection结构化记忆类型系统 — 四类型分类 + frontmatter 规范 + 写入/召回/漂移防护全流程。适用于所有 Agent 的长期记忆管理。解决记忆混乱、召回不准、膨胀失控问题。灵感源自 Claude Code Memory Type Taxonomy(memoryTypes.ts)。9
- 17253Prd Generator By KookyKookyJinn/kooky-skills-prd生成产品需求文档(PRD)HTML文件,包含原型线框图和需求说明。当用户提到PRD、需求文档、产品需求、原型图、需求原型、写需求、出需求时触发。支持多页面目录导航、无限画布布局、HTML/CSS模拟线框图。9
- 17254Risingwaverisingwavelabs/agent-skillsUse when working with RisingWave — streaming SQL database, materialized views, sources, sinks, CDC from PostgreSQL/MySQL, Kafka ingestion, time windows (TUMBLE/HOP/SESSION), watermarks, EMIT ON WINDOW CLOSE, port 4566, risingwave-mcp, event streaming pipeline design, real-time analytics, stream processing9
- 17255Risingwave Best Practicesrisingwavelabs/agent-skillsUse when designing RisingWave schemas, writing materialized views, configuring sources or sinks, optimizing streaming SQL performance, troubleshooting slow backfills, setting up CDC, designing time-windowed aggregations, or reviewing a RisingWave streaming pipeline9
- 17256Scan PDF to Epubhmylg/scan-pdf-to-epub-skillConvert scanned PDFs into traceable, reflowable EPUB projects with page inventory, per-spread splitting, evidence-preserving OCR routing, visual proofreading, image preservation, navigation construction, EPUBCheck, and reader smoke tests. Use when Codex needs to turn a scanned or image-based PDF into a searchable, resizable EPUB; use either a local OCR route or user-supplied official PaddleOCR AI Studio exports; audit or repair an existing scan-to-EPUB project; or design a privacy-preserving workflow for Chinese, Japanese, English, or mixed-language books. Do not trigger for ordinary text PDFs9
- 17257Scan PDF to Epub Zhhmylg/scan-pdf-to-epub-skill将扫描版或图片型 PDF 制作成可追溯、可搜索、可调字号的可重排 EPUB,并执行逐页清点、双页拆分、保留证据的 OCR 路由、高清扫描核校、插图保留、导航构建、EPUBCheck 和阅读器实机检查。用于中文用户要求通过本地 OCR 路线或用户已提供的官方 PaddleOCR AI Studio 结果转换扫描 PDF、审计或修复既有转换项目,或设计隐私优先的 OCR→EPUB 流程时。普通文字型 PDF、固定版式 EPUB、仅翻译任务或未经授权的版权内容公开发布不触发。9
- 17258Self Rationalization Guardkadaliao/claude-code-skills-collection自我合理化防护 — 识别和反制 AI Agent 常见的偷懒/逃避/自我欺骗模式。不限于验证,适用于所有任务执行。当 Agent 即将跳过步骤、简化问题、或用"看起来对"替代"运行验证"时触发。灵感源自 Claude Code Verification Agent 的 Rationalization Detection。9
- 17259Smart Memory Guardkadaliao/claude-code-skills-collection智能记忆管理 — 防膨胀、防漂移、分类写入。解决记忆文件无限增长、过时记忆误导行动、什么都记导致噪音太多的问题。适用于所有 OpenClaw Agent。触发条件:(1) 写入 MEMORY.md 前自动执行分类检查 (2) 基于记忆行动前验证漂移 (3) heartbeat 时检查膨胀 (4) 被主人说"记忆太乱了"时。灵感源自 Claude Code Memory 系统设计。9
- 17260Task Concurrency Patternskadaliao/claude-code-skills-collection任务并发与依赖管理模式 — 多 Agent/多步骤任务的并发安全、读写分离、依赖编排。适用于:(1) 多 Worker 并行任务 (2) 复杂项目拆分执行 (3) 需要 blocks/blockedBy 依赖关系的工作流。灵感源自 Claude Code Task System + Coordinator Concurrency Rules。9
- 17261Truthful Coderadamdroberts/agent-skillsEnforces strict change transparency. Use when editing code, notebooks, configs, or running commands so every change is disclosed, including changes not announced in advance.9
- 17262Visual Briefbrijoobopanna/ClaudeSkillsCreate publication-quality technical infographics from any source — tweets, articles, architectures, or ideas. Use this skill whenever the user wants to visually break down a technical concept, map a system architecture, turn a tweet or thread into a shareable diagram, create editorial-style pipeline or flow visualizations, illustrate feedback loops or compounding mechanisms, or produce visuals for a newsletter or blog. Trigger on phrases like "visualize this", "diagram this", "break this down visually", "map this architecture", "make an infographic", "turn this tweet into a visual", "show me 9
- 17263Walter Writes Humanizerwalterwritesai/no-slop-ai-humanizer-rewriterRewrite AI-generated text to sound human. Use when given existing AI output — from ChatGPT, Claude, Gemini, or any LLM — that needs to read like a person wrote it.9
- 17264Walter Writes Writerwalterwritesai/no-slop-ai-humanizer-rewriterWrite content that avoids AI tells from the start. Use when generating any prose — articles, emails, social posts, reports — where the output should sound human, not machine-made.9
- 17265Worker Prompt Craftkadaliao/claude-code-skills-collectionWorker/子代理 Prompt 编写指南 — 写出让子代理一次做对的 prompt。解决"子代理看不到上下文"、"指令模糊导致返工"、"委托理解而非综合"的问题。适用于:(1) 使用 sessions_spawn/sessions_send 时 (2) 调度 CC 子任务时 (3) 任何需要给 AI 子代理写指令的场景。灵感源自 Claude Code Coordinator Prompt Guidelines。9
- 17266Yandex Datalens APIAdelphopoet/datalens_agent_skillsUse when automating Yandex DataLens Public API/RPC operations, including IAM authentication and API-level work with workbooks, datasets, connections, dashboards, charts, embeds, exports, and access bindings. Do not use for dashboard storytelling, BI analysis, visual design, or non-API Yandex Cloud work unless the task specifically requires DataLens API calls.9
- 17267Yandex Datalens Dashboard DesignAdelphopoet/datalens_agent_skillsUse when designing, planning, building, or reviewing Yandex DataLens dashboards, datasets, charts, selectors, calculated fields, dashboard performance, BI UX, data storytelling, governance, or executive/operational analytics pages. Use yandex-datalens-api as an additional skill only when actual Public API automation is required.9
- 17268Code Executionggozad/haiku.skillsWrites and runs Python code in a sandbox. Describe the task in plain English — the skill will write and execute the program.9
- 17269Sandboxggozad/haiku.skillsWrites and executes Python code in a Docker sandbox with filesystem access and pre-installed data science packages.9
- 17270Activity Capture Diagnosticelijeangilles/revops-skillsDiagnose sales activity capture quality across a team and grade it A through F. Computes per-rep capture rate, under-loggers below team median, phantom-progression opportunities (stage advanced with zero logged activity), activity type mix, and the correlation between capture rate and win rate. Use when the user asks about Einstein Activity Capture, Outreach sync gaps, missing call logs, low activity volume, or whether reps are actually working their pipeline.9
- 17271Deal Investigatorelijeangilles/revops-skillsProduce a structured deal review for a single opportunity. Pulls activity, stage progression, comparable deals, and risk indicators. Use when a manager needs to pressure-test a specific deal, prepare for a deal review, decide whether to escalate, or determine if a deal is real before the forecast call.9
- 17272Forecast Call Prepelijeangilles/revops-skillsPrepare the executive summary for a weekly forecast call by reconciling rep commits against historical close-rate models and surfacing material variance. Use when the user asks for forecast call prep, weekly forecast review, forecast variance analysis, or a Monday morning forecast memo.9
- 17273Lead Routing Rule Analyzerelijeangilles/revops-skillsDiagnose lead routing health and grade it A through F. Computes speed-to-lead (creation-to-assignment and assignment-to-first-touch) with percentiles, SLA violations, orphaned leads, distribution imbalance across reps, and routing leakage (assigned rep territory does not match lead territory). Use when the user asks about LeanData, Salesforce Assignment Rules, lead handoffs, speed-to-lead SLA, or whether leads are reaching the right reps.9
- 17274Midnight Compact GuideUvRoxx/midnight-agent-skillsComprehensive guide to writing Compact smart contracts for Midnight Network. Use this skill when writing, reviewing, debugging, or learning Compact code. Triggers on "write a contract", "Compact syntax", "Midnight smart contract", "ledger state", "circuit function", or "ZK proof".9
- 17275Midnight DeployUvRoxx/midnight-agent-skillsDeploy and manage Midnight smart contracts to local or preview network. Use this skill when deploying contracts, starting local infrastructure, or connecting to testnet. Triggers on "deploy contract", "start local node", "setup standalone", "deploy to preview", or "midnight infrastructure".9
- 17276Midnight Infra SetupUvRoxx/midnight-agent-skillsSet up and run Midnight infrastructure locally using official dev tools. Use this skill when setting up local development environment, starting node/indexer/proof-server, troubleshooting infrastructure, or syncing components. Triggers on "setup infrastructure", "start local node", "run indexer", "proof server", "midnight-infra-dev-tools", or "local development".9
- 17277Midnight SDK GuideUvRoxx/midnight-agent-skillsTypeScript SDK integration guide for Midnight dApps. Use this skill when building frontends, connecting wallets, or calling contracts from TypeScript. Triggers on "SDK", "TypeScript", "wallet integration", "connect dApp", "call contract".9
- 17278Midnight Test RunnerUvRoxx/midnight-agent-skillsRun and debug Midnight contract tests using Vitest simulators. Use this skill when testing contracts, debugging test failures, or writing new tests. Triggers on "run tests", "test contract", "debug test", "test fails", or "vitest".9
- 17279Pipeline Hygiene Auditelijeangilles/revops-skillsAudit a sales team's open pipeline for hygiene issues and produce a per-rep punchlist of fixes ranked by severity. Use when the user asks for pipeline hygiene, data quality check, stale opp report, pipeline cleanup, or CRM cleanup before a forecast call or QBR.9
- 17280Safe Encryptiongrittygrease/safe-encryption-skillEncrypt, decrypt, and manage keys with the SAFE CLI — a modern GPG alternative with post-quantum support.5