Hand Rush a task: an agent does the work in its own cloud sandbox and returns a PR, report or files.

Full-stack consulting skill for Claude Code — 6 AI agents, 16 strategy frameworks, CPA-level financial modeling, zero hallucinations

Turn any recording or document into notes, flashcards and quizzes your agent can read and act on

Enables AI assistants to look up credentials such as API keys, database URLs, and service tokens by account name, and to read inbox messages like notifications, alerts, and task assignments routed to the agent, all from self-hosted infrastructure.

A markdown editor — and the bridge to your LLM. Local-first, MIT, ~15 MB. Bundled MCP server lets Claude Code / Codex / Cursor drive your vault directly. 14 AI providers BYOK.

genshijin 原始人 🗿| Claude Code / Codex等AIエージェント 向け超圧縮コミュニケーションスキル。caveman の日本語版をベースに、日本語特有の冗長表現に最適化。

A living personal wiki. Wenlan turns your documents, notes, and AI chats into pages with links to their sources, and updates them as sources change without overwriting your edits. Claude Code, Codex and other AI tools can build on it.

💡DSH 的 Prompt提示词工具箱：常用prompt保存后点击即可注入到对话框——省时省力，/prompt 自动提示已有Prompt。 💡The Prompt toolbox for DSH: save frequently-used prompts and inject them into the dialog with one click — saving time and effort, with /prompt auto-suggesting your existing prompts.

A living wiki your AI writes from your notes, code, AI chats (memories), and docs, checked against sources. It flags what it can’t back up and updates pages when sources change. Supports Claude, Codex, Obsidian...

Claude Code hooks that auto-switch model tier based on task complexity

Local-model (Ollama) integration for DeepSeek Harness: discover, pull, remove, and inspect local models, route requests to them by task type or keyword with automatic fallback to the cloud, and get a one-shot status overview via /ollama.

Inspect 1NFER models, crypto funding terms and task cost without keys or paid calls.

Shorter replies with Claude Code. Save output token spend.

Claude Code plugin for building LLM-maintained Obsidian wikis from raw research — compile, query, lint, and evolve your personal knowledge base. Inspired by Karpathy's knowledge base workflow.

Enables LLM clients to perform sandboxed file operations, manage persistent notes, fetch live weather and Wikipedia summaries, calculate arithmetic safely, and retrieve current UTC time via a standalone tool server over stdio or HTTP.

See where your AI spend goes - by task, tool, model, and project

Iterative worker-reviewer cycle that spawns a critic subagent to score work 1-10 and provide actionable feedback, then revises until a quality gate is met. Use when implementing features, writing specs, reviewing existing code, or completing any task where quality matters more than speed. Trigger ph

Turns a Frappe site into a remote MCP server that AI clients such as Claude can sign in to with OAuth and use curated, task-level tools registered by installed apps. Every call runs as the signed-in user with that user's permissions, with schema-checked arguments and rollback on failure.