>-
Skills(SKILL.md)は、AIエージェント(Claude Code、Cursor、Codexなど)に特定の能力を追加するための設定ファイルです。
詳しく見る →>-
>-
Search and install AI agent skills from multiple registries
Write story chapters using an outline-first workflow. Gathers context from all other story elements (characters, world, plot) to maintain consistency, builds a beat-by-beat outline for approval, then
Initialize a new story project with a structured markdown folder layout. Creates the story bible, character registry, worldbuilding index, plot structure, and chapter tracker - all as cross-referenced
For features spanning multiple domains (auth, database, UI, etc.) that need front-loaded technical context before the Feature Forge interview.
resume-handoff
Obsidian vault management — CLI operations, Markdown extensions, JSON Canvas, Bases databases, and Defuddle content extraction. Use when interacting with Obsidian vaults, managing notes, searching content, or developing plugins.
paper-analyzer
This role owns pipeline truth, deal progression, and revenue accountability. It protects forecast integrity and clear next steps over activity volume.
Download videos from social media URLs (X/Twitter, YouTube, Instagram, TikTok, etc.) using yt-dlp. Use when saving a video locally, extracting content for transcription, or archiving video references.
docs-context
Reusable procedural skills extracted from CLAUDE.md. Each skill has a canonical name (kebab-case), trigger conditions, ordered steps, and a verification check. Invoke a skill by name: *"run the cargo-
Build elegant frontend UIs following Microsoft Foundry's NextGen Design System using Vite + React + pnpm. Use when creating dashboards, agent builders, data grids, entity management interfaces, or any application matching Foundry's refined dark-themed aesthetic. Triggers on requests for Foundry-style UI, NextGen design system, Microsoft Foundry interfaces, or enterprise admin dashboards with data tables, detail panels, and charts.
Learn how to execute agents and handle results.
Building and training neural networks with PyTorch. Use when implementing deep learning models, training loops, data pipelines, model optimization with torch.compile, distributed training, or deploying PyTorch models.
Loading and using pretrained models with Hugging Face Transformers. Use when working with pretrained models from the Hub, running inference with Pipeline API, fine-tuning models with Trainer, or handling text, vision, audio, and multimodal tasks.
Deploy and manage censorship-resistant static websites on the Nostr network using nsyte CLI. Covers installation, project setup, configuration, authentication (NIP-46 bunkers), deployment to Blossom servers, CI/CD automation, and troubleshooting. Use when the user mentions nsyte, nsite, Nostr site hosting, Blossom uploads, or decentralized web publishing.
Deploy a full-stack multi-model Browser Agent system with FastAPI server, real-time dashboard, VNC streaming, and LLM Council mode. Use when the user asks to set up browser automation, build a browser agent, deploy an AI web agent, create a browser-use server, or needs multi-model browser automation with strategies like council, consensus, fallback chain, or planner-executor.
End-to-end 8-dimension verification — requirements through delivery, all aligned and correct
Expert full-cycle enterprise sales strategist for B2B SaaS. Use when planning sales strategy, pipeline management, deal progression, account planning, competitive displacement, or territory optimization. Covers multi-threading, executive engagement, champion development, buying committee navigation, and complex deal orchestration. Use for enterprise selling, account expansion, land-and-expand, and quota attainment.
Expert customer health scoring and analytics guidance. Use when designing health scores, building churn prediction models, analyzing usage metrics, identifying at-risk accounts, creating executive dashboards, or performing cohort analysis. Use for leading indicator development, customer data enrichment, risk escalation frameworks, and retention analytics.
Expert platform and API product management guidance for developer-focused products. Use when planning API product strategy, designing APIs, improving developer experience (DX), creating developer documentation, building SDKs, planning API versioning and deprecation, building developer communities, creating integration marketplaces, or measuring platform health. Covers REST, GraphQL, webhooks, and platform ecosystems.
Expert renewal management guidance for maximizing retention and expansion revenue. Use when building renewal playbooks, forecasting renewal pipeline, structuring multi-year deals, developing pricing strategies, mitigating churn risk, defending against competitive displacement, negotiating contracts, attaching expansion to renewals, or optimizing renewal operations. Covers high-touch and tech-touch renewal motions, early renewal strategies, and save plays.
Expert sales operations and analytics guidance for revenue teams. Use when designing CRM workflows, building sales dashboards, optimizing pipeline analytics, creating lead routing rules, designing territories, calculating commissions, managing data quality, building forecasting models, or integrating sales tech stack. Covers Salesforce, HubSpot, Outreach, Gong, and RevOps best practices.
Expert sales strategy and operations guidance for B2B SaaS companies. Use when designing sales processes, implementing qualification frameworks (MEDDIC, BANT, SPICED), territory planning, forecasting, quota setting, compensation design, or optimizing pipeline velocity. Covers sales methodology, org structure, tech stack selection, win rate analysis, and deal acceleration strategies.
'Use this skill whenever the user is deploying a React/Vite single-page app to AWS, or mentions Amplify, CDK, or wiring up Lambda + API Gateway for a frontend. Covers Amplify hosting, custom domains, CDK backend (Lambda + API Gateway), SES email, CORS configuration, and environment variables. Skip for non-AWS hosts (Vercel, Netlify, Cloudflare Pages), pure backend services without an SPA, or server-rendered apps (Next.js SSR on Vercel).'
Formal Proof Visualization and Verification for Lean 4
Extract key technical concepts from patent claims. Use when the user wants to identify the core inventive concepts or technical approaches in a patent.
Create clear, repeatable standard operating procedures for any business process. Turn tribal knowledge into documentation anyone can follow.
Create a new Vite plugin in the @taucad/vite package following project conventions and Vite 8 best practices. Use when adding a Vite plugin, creating dev server middleware, implementing build transforms, or extending Vite configuration for the Tau monorepo.
>
>
Compose multi-agent systems with SequentialAgent, ParallelAgent, and LoopAgent. Use when building agent pipelines, parallel workflows, or iterative loops.
Draw shapes, arrows, and diagrams on a TLDraw canvas via the agent-canvas CLI. Use when an agent needs to visually communicate ideas, create diagrams, flowcharts, or annotate a whiteboard. Triggers on tasks involving drawing, diagramming, visual explanations, or canvas manipulation.
Build business cases with cost-benefit analysis, ROI calculations, risk assessment, implementation timeline, and stakeholder analysis
Forecast inventory needs using demand analysis, safety stock calculations, reorder point optimization, and seasonal adjustment
A CLI tool for calculating and validating Uniswap V4 liquidity position tick bounds. Prevents tick math errors that can cause failed LP mints by providing correct, validated tick calculations.
Dynamic configuration management for AI agents. Update settings without restarts, validate changes, and rollback safely.
Clanker fee burn pipeline using Bankr API - no private keys needed
**Purpose:** Automated end-to-end Clanker fee claim → rebalance → burn → treasury pipeline.
article-publisher
Sales reps lose time each morning deciding what to work on. This skill queries Dataverse to surface the day's agenda, flag urgent pipeline issues, highlight overdue commitments, and recommend a priori
Sales forecasting requires aggregating pipeline data across reps, applying probability weighting, and identifying where the number is at risk or has upside. This skill automates that process from Data
>
chatgpt-search
Google Workspace CLI automation via gogcli. Gmail, Calendar, Drive, Docs, Slides, Sheets, and 9 more services. JSON-first output, composable pipelines.
Content extraction skill for AI coding agents. YouTube transcripts, podcasts, PDFs, images (OCR), audio/video via the summarize CLI.
Build Account-Based Everything (ABX) GTM strategies for complex B2B sales. Use when working on ABM strategy, ICP scoring, messaging architecture, product launches, or pipeline acceleration for companies with <500 accounts, $100K+ deals, and 6+ month sales cycles.
Build system optimization covering compilation, caching, incremental builds, and developer tooling. Use when improving build times, configuring CI pipelines, or designing developer tools.