MCP servers and skills: search, filter by where they run, and compare.
Analyze, visualize, and reclaim storage used by OpenCode (v1 & v2) sessions, diffs, and reasoning tokens.
SkillMIT★ 5No key
using opencode for pod ( projectlibre )
SkillMIT★ 2Few starsNo key
A unified execution framework for AI agent skills
SkillMIT★ 2Few starsNo key
Delegate orchestrator-authored implementation plans to Claude Code, then review the resulting diff in a plan-execute-review loop.
SkillMIT★ 2Few starsNo key
Scan Claude Code, Codex, and Opencode sessions and visualize what eats your tokens — skills, thinking, tools, context.
SkillMIT★ 1Few starsNo key
An agent skill to evolve the quality of LLM-Wiki (Graphify) at test time.
SkillMIT★ 91No key
Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.
SkillMIT★ 36kNo key
Skill para analisar repositórios GitHub e auxiliar tradução sem modificar o projeto original
SkillMIT★ 2Few starsNo key
Copy or cut conversation context between Codex, Pi, DSH, OpenCode, Qwen, Claude and WorkBuddy. Local CLI + skill with native session index cleanup.
SkillMIT★ 6No key
Generate, cache, play, and control DashScope speech on macOS with Codex and OpenCode Skills.
SkillMIT★ 2Few starsNo key
One sentence per line, enforced as your AI agent writes it — a one-word edit stays a one-line diff. A post-edit hook checks code comments, doc comments, docstrings, and Markdown for semantic line brea
SkillApache-2.0★ 3Few starsNo key
Benchmark complete coding agent setups on your codebase
SkillMIT★ 3Few starsNo key
🚀 Give Claude Code&OpenCode an operating system — 9 specialized AI agents, 11 PDCA commands, 10 skills. Spec-driven development: your AI writes specs before code, runs TDD, never commits without gree
SkillMIT★ 1Few starsNo key
Make Gemini code like Claude Models. Forces it to inspect files before editing, plan changes, test its work, and back up every “done” with actual evidence.
SkillMIT★ 344No key
Test Agent Skills across Claude Code, Codex, and OpenCode with repeatable fixtures, output checks, and a live run dashboard.
SkillMITFew starsNo key
OpenBrowser is a framework for intelligent browser automation. It combines direct CDP communication with a CodeAgent architecture, where the LLM writes Python code executed in a persistent namespace,
SkillMIT★ 279No key
Playing-coach CLI: run Claude Code, Codex and Antigravity as parallel sub-agents and spend three separate quotas instead of one.
SkillMIT★ 4Few starsNo key
Re-debugging Solved Failures? No Way. 500+ Evidence-graded fix lessons, One MCP Call-->https://misakanet.org
SkillApache-2.0★ 543No key
SkillMIT★ 4Few starsNo key
SkillMIT★ 3Few starsNo key
An autonomous engineering team built on Claude Code, Codex and OpenCode.
SkillMIT★ 4Few starsNo key
QQ MCP Server - connect AI agents to QQ via NapCatQQ. Auto-wake, messaging, group management, file sharing, cross-platform.
SkillMIT★ 3Few starsNo key
Who stands behind it
