Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
ClickUp from your terminal and git: plan the day, start/finish tasks, log every commit, see who works on what. Works with Claude Code.
SkillMITFew starsNo key
Claude mod: orchestrate subagents, route each task to the right model, and keep a live record of every task, cost and handoff note.
SkillMIT★ 1Few starsNo key
Knows which AI models you actually have, picks the right one for every task, routes it to a best-fit subagent, and proves what that saved. One open Agent Skills plugin for Claude Code, Codex, ChatGPT,
SkillMIT★ 1Few starsNo key
Claude Code plugin: run big work as a team. Your session orchestrates; Haiku, Sonnet and Opus subagents work in per-task git worktrees, escalate on failure, and an Opus QA pass reviews the whole chang
SkillMITFew starsNo key
Agent skill for Claude Code, Codex & OpenCode: proof over “done”, no blind retries, every number in the report counted by a command. Accurate final reports 20/20 vs 5/20 on a lossy bulk import. One-li
SkillMIT★ 1Few starsNo key
Role-based AI agents for Claude Code: the rules become checks, and a task is done when the checks pass
SkillMIT★ 1Few starsNo key
Wisdom for coding agents: risk before code, challenge before merge. A Claude Code plugin.
SkillMITFew starsNo key
Prepares meeting agendas, internal pre-reads, and decision briefs using Notion context and relevant research. Use for preparing the next or upcoming meeting, meeting preparation, recurring meeting con
OfficialSkillMIT★ 223 in collectionNo key
Prepares meeting agendas, internal pre-reads, and decision briefs using Notion context and relevant research. Use for preparing the next or upcoming meeting, meeting preparation, recurring meeting con
OfficialSkillMIT★ 223 in collectionNo key
Orchestrator mode for Claude Code: the main session plans and delegates the work to subagents.
SkillMIT★ 37No key
SkillMITFew starsNo key
A coding agent skill that routes each task to the cheapest model and effort that keeps the same quality
SkillMIT★ 4Few starsNo key
Think like a lead. Ship like a crew. Your coding agent plans and reviews; the other coding-agent CLIs on your machine write the code.
SkillMITFew starsNo key
Realistic build-time estimates for Claude Code: agent time vs your time, risk, and speed-ups. Learns from your own sessions, locally.
SkillMIT★ 1Few starsNo key
AI agent skill router + skill manager: auto-pick the right skills, subagents, plugins and MCP servers for every task in Claude Code, Codex, Cursor, Gemini CLI, Copilot and Antigravity, and audit dupli
SkillApache-2.0★ 3Few starsNo key
Agent skill that carries a goal end to end and delegates implementation and read-only review to paid DeepSeek Flash subagents through opencode, while the orchestrating agent plans, reviews every diff
SkillMITFew starsNo key
A local Markdown project board for teams of people and AI agents. Card decks, Runs and Journeys as plain files in your repository; no account, no cloud sync.
SkillAGPL-3.0★ 1Few starsNo key
Claude Code–style dynamic workflows for Pi: code-mode subagents with real model routing, journaled resume, git-worktree isolation, cost accounting, an interactive /workflows TUI, an /ultracode standin
SkillMIT★ 591No key
One engineering standard for every AI coding agent: Claude Code, Codex, Cursor, Copilot, Gemini CLI.
SkillMIT★ 1Few starsNo key
Agent Mode for Claude Code: delegate work to background subagents and keep the main session free.
SkillMITFew starsNo key
Subagents, background terminals, smart compaction, goals, task list, ask_user, image/video/audio understanding, WebP images, and web search for the Pi coding agent. Formerly shariq-pi-extensions.
SkillMIT★ 14No key
A CLI that benchmarks Agent Skills: baseline versus with-skill, LLM-graded and gated, on any harness.
SkillApache-2.0Few starsNo key
Agent skill that turns your main model into the manager: it fans work out to subagents with the roles and models you pick, then approves or sends back their results. Claude Code, OpenCode, Rayu, Antig
SkillMITFew starsNo key
Who stands behind it