发现 Skills

Build MCP servers with the Node/TypeScript SDK — implement tools, read-only resources, and prompt templates; validate parameters with Zod; and choose transport: stdio or Streamable HTTP. Refer to Context7 or the official MCP docs for the latest API.

Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.

Apply Bloom's revised taxonomy to classify learning objectives and design assessments across six cognitive levels. Use this skill when the user needs to write learning objectives at specific cognitive levels, align assessment with instructional goals, or evaluate curriculum for cognitive complexity distribution — even if they say "how to write learning objectives", "what level of thinking does this require", or "higher-order thinking skills".

Applies prompt repetition to improve accuracy for non-reasoning LLMs

Diagnose and fix CI/CD pipeline failures including lint errors, build failures, test failures, and push-triggered workflow issues. This skill should be used when users encounter GitHub Actions failures, lint errors on push, CI build errors, or need to debug any CI/CD pipeline issue. Triggers on: "fix CI", "pipeline failed", "lint error", "push failed", "GitHub Actions error", "workflow failed", "build broke".

Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.

Convert feature intent into a coherent technical approach tied to the codebase. Use during /plan Technical stage.

Compress old low-importance Hive memories using claude-haiku. Reduces DB size while preserving key facts.

Troubleshooting dependencies, installations, environment issues, and platform-specific problems. Use when facing npm/pip/package errors, installation failures, environment setup issues, or platform compatibility problems.

Automate X (formerly Twitter) for research, video understanding, and content creation. Use when navigating X, searching posts, analyzing videos, or creating content.

Design, tune, or review EF Core data access with proper modeling, migrations, query translation, performance, and lifetime management for modern .NET applications. USE FOR: DbContext, migrations, model configuration, EF queries, tracking, loading, performance, transactions, and EF6 migration decisions. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.

Generate a concise Indonesian morning digest about latest developments in AI agents, Hermes Agent, and related tooling for delivery via cron job.

Find nearby places (restaurants, cafes, bars, pharmacies, etc.) using OpenStreetMap. Works with coordinates, addresses, cities, zip codes, or Telegram location pins. No API keys needed.

Replace 100+ API keys with one. Instant access to LLMs, Twitter, YouTube, LinkedIn, Finance, Tavily & Scholar data. Enterprise stability for your local agent.

Use when you need Clawdbot to perform coding tasks, including writing code, debugging, refactoring, code review, generating tests, and explaining code.

Horizontal sharding (partitioning) for Azure DocumentDB collections — when to shard vs stay single-shard, how to pick a shard key for read-heavy vs write-heavy workloads, the logical/physical shard mental model, scaling out vs scaling up, hot-partition diagnosis, and the `sh.shardCollection` / `sh.reshardCollection` commands. Use when deciding whether to shard a collection, choosing or changing a shard key, sizing a cluster, or troubleshooting uneven storage / throughput across physical shards.

Prepare the development environment for immediate coding by orchestrating memory loading, context validation, and pre-flight checks in a single interaction. Eliminates the need to run multiple manual slash commands (/memory-read, /standards-check, /arch-check) before starting work. Use when the user says 'ready to code', 'start coding', 'let's implement', 'begin development', 'coding time', or needs to transition from planning directly to implementation without manual warm-up.

View an SAP system status snapshot and edit values in `.sc4sap/sap.env` (connection, blocklist) and HUD usage limits in `~/.claude/settings.json` → `env` — a single entrypoint for all sc4sap runtime options.

Breaks epics into developer stories.

Conduct periodic access reviews and certifications. Implement access governance and recertification workflows. Use when managing access compliance.

Non-custodial perpetual DEX on Arbitrum. Use when user says buy, sell, trade, long, short, open position, close position, flip trade, set leverage, deposit USDC, withdraw funds, check balance, view positions, cancel order, copy a thesis, publish trade on-chain, check leaderboard, top traders, Rep Score, market intel, crypto news, funding rate, thesis, analyst feed, who's winning on Nexus.

Complete Venice AI platform — text generation, web search, embeddings, TTS, speech-to-text, image generation, video creation, upscaling, and AI editing. Private, uncensored AI inference for everything.

Applies memory-safe programming patterns such as RAII, ownership, smart pointers, and bounds checking across Rust, C++, and C. Use when managing resources, preventing memory bugs, or choosing safety strategies.

Spawns AI coding agents in isolated git worktrees. Use when the user asks to spawn or launch an agent, delegate a task to a separate agent, work in a separate worktree, or parallelize development across features.