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.
Requirement derivation tree and evidence-gated closure as your single source of truth — zero-dependency Python CLI + AI-agent skill
SkillMITFew starsNo key
The repo map your coding agent is forced to use — ~98% fewer tokens (up to 99.9% per task) to understand a TS/JS or PHP/Laravel codebase. PageRank hubs, Aider-style symbol ranking, token-budgeted dige
SkillMIT★ 3Few starsNo key
Visualize how your code files connect — imports, calls, inheritance, implements, comment-links, ADRs, and tests — as an interactive graph alongside your Obsidian notes.
Skill0BSD★ 9No key
Agent skill for discovery tree task management
SkillMIT★ 3Few starsNo key
Edit an existing workflow Scene or task contract. Use for assets, layout, cameras, randomization, task text, or success rules; do not use to create a new workflow.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
A lightweight, universal AI coding methodology in a single SKILL.md. Covers task sizing (XS→XL), strategy selection, code analysis, user interaction, and execution discipline — distilled from Superpow
SkillMIT★ 1Few starsNo key
tda (like "trouble de l'attention") is a local first TODO tree application for human & AI agent
SkillApache-2.0★ 2Few starsNo key
Long-horizon autonomous mode for Claude Code — a /goal command inspired by OpenAI Codex. Hierarchical Sprint→Epic→Task plan-tree, evidence-mapped acceptance criteria, declarative review-gates, and a t
SkillMIT★ 3Few starsNo key
VS Code sidebar tree of every running Claude Code session: project → session → subagent → task.
SkillMITFew starsNo key
A Claude Code skill that gives your todo list a world model. Forks every decision, simulates 10 steps ahead, scores branches, emits a human-editable decision tree. The constructive answer to LeCun's w
SkillLink only★ 1Few stars
A collection of agent skills for task tracking, focus enforcement, debugging, and complex feature planning. Designed to work with any AI coding agent.
SkillMIT★ 1Few starsNo key
Local subagent orchestration for Codex and Claude, with persistent task state, reusable teams, and interruption recovery.
SkillMIT★ 190No key
See which subagents your coding agent ran, with which model, for which task.
SkillMIT★ 2Few starsNo key
A Rust CLI that runs multiple coding agents in parallel on one repo. A planner splits the task into file-disjoint lanes, lanes run as ACP sessions in one agent process, and pact verifies the result ag
SkillMIT★ 3Few starsNo key
Platform-neutral Agent Skill and protocol for one-shot task-to-task handoffs
SkillMITFew starsNo key
Mubu (幕布) outline CLI & AI Agent Skill — import/export Markdown with true round-trip fidelity, plus OPML/FreeMind export.
SkillMIT★ 18No key
Generate interactive mind maps in Claude — with a knowledge atlas, Markmap export, and Claude Code plugin
SkillMIT★ 19No key
Task-scoped workflow skills for coding agents — entry, state, verification, recovery and cleanup discipline. 17 skills, one command to 20+ agents via skills.sh.
SkillMIT★ 3Few starsNo key
A Codex skill for Linux embedded learning, bringup, debugging, source reading, and performance work. This skill is designed as a broad Linux embedded development companion rather than a narrow single-
SkillMIT★ 5No key
Five Claude Code plugins, Python stdlib + git. ar-board: judge agent proposals one by one on a local board; the agent keeps your reasons. publish-check: scan a repo's history for personal data before
SkillMIT★ 31No key
Local, host-agnostic adversarial code review for Claude Code -- auto-triggers on every prompt and task-list update, patches critical flaws in place, ignores nits.
SkillMIT★ 1Few starsNo key
Non-destructive recovery for Superpowers plan execution interrupted mid-task (Claude Code plugin)
SkillMITFew starsNo key
Reasonix-native launchers for GSD: renders the GSD workflow set as Reasonix slash commands driven by Reasonix's own task/fleet, ask, todo_write and complete_step tools.
SkillMIT★ 1Few starsNo key
Who stands behind it