Tools

Open-source personal AI assistant that runs on your own machine and talks to you over 20+ chat channels such as Telegram, Slack and iMessage. The openclaw CLI manages the gateway, channel pairing and plugins; switch models between Claude, Codex and local ones.

Curated index of Claude skills with about 30 practical skills in the repo (resume tailoring, content research and writing, file organization, meeting analysis) plus 800+ automation skills that reach third-party apps via Composio, which need Rube MCP and account authorization.

General-purpose AI agent that runs on your machine, with a desktop app, CLI and API. Written in Rust, works with 15+ model providers and connects to 70+ extensions via MCP. Originally from Block, now part of the Linux Foundation's AAIF.

Skyvern's official MCP: drives a browser with vision LLMs to complete multi-step tasks like filling forms, downloading files and web research. Connect to Skyvern Cloud (OAuth or API key), or self-host Skyvern and run it as a local process.

Lets agents look up docs, properties and workflow templates for n8n's 2,000+ nodes and build and validate workflows; with an n8n API key configured it can create and update workflows in your instance directly.

Lets Claude Code push ML research forward unattended: literature review, topic selection, experiment deployment, cross-model review loops and paper writing through rebuttal, in 80+ skills. Codex acts as the independent reviewer by default; other model pairings work too.

14 n8n workflow skills: expression syntax, MCP tool usage, node configuration, validation and troubleshooting, Code nodes, AI Agent workflows and self-hosted n8n deployment. Meant to be used with the n8n-mcp server.

14 skills plus a hook-based reminder layer for use with n8n-mcp: teaches agents to write correct n8n expressions, configure nodes, apply workflow patterns, fix validation errors and deploy self-hosted n8n. Requires n8n-mcp to be set up first.

GitHub's official gh extension for writing Actions workflows in Markdown that AI agents execute, compiled into standard Actions. Choose engines like Copilot, Claude Code or Codex; runs in a read-only sandbox by default. Requires gh.

Interviews you to design an agentic control loop for your codebase in control-theory terms: a set point, a sensor built from existing tooling, a controller that picks small low-risk changes, and a coding agent that opens PRs. Builds each part to run locally before wiring a scheduled CI workflow.

Turns a repeatable agent task into a repo-local skill plus a GitHub Actions workflow that runs a coding agent (Claude Code, Codex, OpenCode or CodeLayer) on a schedule, with a prompt, memory file and one-open-PR bound. Reads the repo first, then walks you through cadence, scope and validation.

Lets agents operate Home Assistant: control devices, query state and history, create and debug automations and edit dashboards, with 80+ tools. Community-maintained (unofficial); requires your own Home Assistant instance, and running via uvx needs a long-lived access token.

Opens HTML, Markdown or localhost pages in the browser via npx human-review so you can edit text directly and leave anchored comments, then sends every edit and comment back to the agent in one batch to apply to the source.

ComfyUI's official CLI: install and launch ComfyUI in one step, manage custom nodes and model downloads, and run image and video workflows, with --json output on every command for agents. Can also submit jobs to paid Comfy Cloud.

Health-checks Linear projects for targets at risk of slipping, In Progress issues with no comment in over 7 days, orphan issues without milestones, and common anti-patterns. Reads and comments only, never mass-creates or restructures. Can run from a Cursor Automation. Needs the Linear MCP.

Bootstraps Linear tracking for a repo: checks for an existing project, anchors milestones to a North Star, backfills Done work only with evidence from the CHANGELOG, roadmap or git log, wires blockedBy links, and writes the protocol into CLAUDE.md, AGENTS.md or Cursor rules. Needs the Linear MCP.

Syncs, audits or rescues an existing Linear project against repo reality: enumerates issues, milestones, labels and docs, scores it on a 20-point rubric with a gap list, asks per category before any write, fixes orphans, milestones and dependencies, then re-scores. Needs the Linear MCP.

Keeps agent sessions honest in repos with a Linear tracking protocol: search before creating issues, move them to In Progress at start and Done only when shipped, and close the loop before ending. In untracked repos it asks once whether to run linear-setup. Needs the Linear MCP.

Finishes installing the Linear tracking pack: writes an always-on rule that makes Linear the source of truth into Cursor user rules or global files such as ~/.claude/CLAUDE.md and AGENTS.md, then verifies Linear MCP auth. On Cursor it can also set up a weekly health-check automation.

Entry point of the Linear tracking pack: anchors tracking to the project's North Star and real roadmap, routes requests to linear-setup, linear-sync, linear-monitor or linear-finish-install, and applies linear-discipline throughout the session. Needs the Linear MCP.