Processing
Data transformation and parsing
notebooklm-knowledge-base-organizer
by agmangas
Use when preparing files for NotebookLM, organizing documents into a knowledge base, converting formats for NotebookLM compatibility, or reducing a large document collection to fit NotebookLM's 50-source limit. Scores and prioritizes sources, performs strategic merging (time-series, topic-based, format consolidation), converts unsupported formats (PPTX to PDF, XLSX to CSV), applies flat structure with descriptive snake_case names, and optimizes for RAG retrieval performance.
jtbd-segmentation
by ivanintouch-labs
Универсальная методология JTBD-сегментации СВОИХ клиентов по СВОИМ разговорам (звонки/чаты/мессенджеры/боты). Self-serve для предпринимателя или продакта, который работает со своими данными — без discovery с внешним заказчиком. Извлекает из каждого диалога полное JTBD-досье на лида (per-lead JSON) и собирает 5-12 JTBD-сегментов с отнесением каждого лида к одному из них. Адаптируется к любому уровню глубины данных — от «только разговоры» до «полная воронка + конверсия». Используй, когда нужно сегментировать своих клиентов по реальным мотивам (не по демографии и не по CRM-типу), отнести каждого лида к сегменту с описанием и evidence. Триггеры — «сегментировать клиентов», «JTBD из звонков», «JTBD из переписок», «понять кто наши клиенты», «отнести лидов к сегментам».
trust-and-recovery
by bfmcneill
Use when designing error handling, confirmation dialogs, undo functionality, or any interaction where user trust matters. Covers building confidence through predictability and graceful failure.
ad-performance-learning
by tonyflo79
Post-launch performance analysis and intelligence feedback loop for paid ad campaigns. Use after ads are live and performance data is available. Analyzes real performance data, extracts actionable learnings, and propagates them back into engine files (A01 intelligence, A02 hook taxonomy, A06 Arena calibration, A10 scoring models). When data conflicts with predictions, data wins. Learnings must be actionable (WHAT + WHY + HOW to apply) and the loop must close by updating engine files, not just producing reports. Trigger when users mention ad performance, campaign results, ad analytics, what worked, learning from ads, or updating the engine with results. Requires live campaign performance data.
bird-cli
by zahid47
Use this skill when the user wants to interact with X/Twitter via command line. Triggers include requests to tweet, reply to tweets, read tweets or threads, search X/Twitter, check mentions, view bookmarks, get trending topics, manage lists, or any other X/Twitter operations via CLI. Also use when the user mentions the Bird CLI tool specifically or wants to automate X/Twitter interactions from the terminal. Do NOT use for web-based Twitter interactions or Twitter API integrations.
loader-action-optimizer
by code-visionary
Best practices for React Router v7 loaders and actions - parallel fetching, deferred data, optimistic UI, and error handling patterns
n8n-prd-generator
by prabha-oss
Convert discovery call transcripts into concise n8n Automation Blueprints with interactive question flow. USE THIS SKILL WHEN user says "create a blueprint", "generate automation spec", "convert transcript to blueprint", provides discovery call transcripts or client documentation, needs an n8n automation blueprint for workflow implementation, mentions scoping calls, client requirements, or workflow documentation, or asks to document automation requirements or create implementation specs.
pubfi-crypto-daily-report
by helixbox
Aggregates crypto news from multiple sources and generates curated daily markdown reports with automated scoring and deduplication.
Human Extractor Skill
by yousufjoyian
Claude agent skills and workspace configuration
caps-format-validator
by asadullah48
Validate CAPS (Coding Agent Playbook Spec) playbooks for correctness, completeness, and compatibility with Claude Code and Goose
fsharp-code-review
by bromanko
This skill should be used when the user asks to "review F# code", "fsharp code quality", "F# idioms check", "review my F#", "check code quality", or wants feedback on F# code patterns, idioms, Result handling, or module organization.
关键词研究
by yanglei1826877278
基于种子关键词生成关键词创意，包含搜索量、难度和趋势数据
turborepo
by kunhai-88
"Turborepo monorepo 构建系统指导。触发词：turbo.json、task pipelines、dependsOn、caching、remote cache、turbo CLI、--filter、--affected、CI optimization、environment variables、internal packages、monorepo structure/best practices、boundaries。"
rails-postgres
by shivamsinghchahar
Master PostgreSQL in Rails with native types (UUID, JSON/JSONB, arrays, enums), efficient queries, indexes, and optimization. Use when designing databases, writing complex queries, using PostgreSQL-specific features, optimizing performance, or working with specialized data types.
browser-control
by LLzijian
Control Chrome browser via Chrome DevTools Protocol (CDP). Use when user asks to operate browser, open webpage, search, get web content, click links, fill forms, or any browser-related tasks. Triggers on phrases like "操作浏览器", "打开网页", "搜索", "获取网页内容", "控制浏览器", "Chrome", "browser", "网页", "填表".
elixir-development
by vircung
Modern Elixir idioms, functional patterns, testing strategies, and implementation best practices
youtube-playlist-manager
by FyziGo
Manage, analyze, and clean up YouTube playlists. Use when the user wants to work with YouTube playlist data, including (1) fetching video metadata from CSV exports (Google Takeout) using YouTube Data API v3 or yt-dlp, (2) analyzing playlist contents - statistics, channel breakdown, duration distribution, engagement metrics, (3) searching and filtering videos by channel, duration, tags, title, or date, (4) finding cleanup candidates - unavailable/deleted videos, duplicates, old entries, (5) generating recommendations on what to watch next, (6) exporting playlists to CSV, Markdown, or JSON formats with filters and sorting. Triggers on mentions of YouTube playlists, Watch Later, Google Takeout video exports, playlist analysis, or playlist cleanup.
cl-code-visualizer
by h20hg
Convert Claude Code, VS Code, and Visual Studio Code chat JSON files (JSONL format) into professional HTML visualizations. Use when users need to visualize, view, export, or convert Claude Code conversation logs (.claude/chats/, .claude/projects/) into readable HTML with terminal-style aesthetics, syntax highlighting, collapsible tool results, and search functionality. Handles chat exports, conversation logs, JSONL files, and Claude AI chat history.
campaign-structure
by tonyflo79
Define the structural architecture of the campaign — format, channel strategy, and how all elements connect. Use after offer stack design (Skill 07) is complete and you need to determine the campaign's structural context before writing begins. Defines whether the campaign is a VSL, sales letter, landing page, webinar, or multi-channel promotion, and how each element relates. Produces the structure package with format decisions, channel mapping, and element relationships. Trigger when users mention campaign structure, format selection, VSL vs sales letter, channel strategy, or how the campaign elements fit together. Requires offer package from Skill 07.
opengrid-drawer-filler
by crhan
计算抽屉最优瓦片分割方案并生成 STL 文件用于 3D 打印。根据抽屉尺寸计算最优 openGrid 瓦片布局，支持库存管理和批量计算。当用户需要为抽屉创建 3D 打印瓦片铺满方案时使用此技能。
azure-virtual-desktop-manager
by tippyentertainment
Design, deploy, manage, and automate Azure Virtual Desktop (AVD) environments, including host pools, images, scaling, access, security, and monitoring.
excalidraw
by VisualxIntelligence
"Use when working with .excalidraw or .excalidraw.json files, user mentions diagrams/flowcharts, or requests architecture visualization - delegates all Excalidraw operations to subagents to prevent context exhaustion from verbose JSON (single files: 4k-22k tokens, can exceed read limits)"
robonet-workbench
by robonet-tech
"Use Robonet's MCP server to build, backtest, optimize, and deploy trading strategies. Provides 24 specialized tools for crypto and prediction market trading: (1) Data tools for browsing strategies, symbols, indicators, Allora topics, and backtest results, (2) AI tools for generating strategy ideas and code, optimizing parameters, and enhancing with ML predictions, (3) Backtesting tools for testing strategy performance on historical data, (4) Prediction market tools for Polymarket trading strategies, (5) Deployment tools for live trading on Hyperliquid, (6) Account tools for credit management. Use when: building trading strategies, backtesting strategies, deploying trading bots, working with Hyperliquid or Polymarket, or enhancing strategies with Allora Network ML predictions."
structure-design-skill
by maxoreric
v1.0.0 (2026-01-19): åå§çæ¬