MCP servers and skills: search, filter by where they run, and compare.
Enterprise Distributed Microservices Platform for Social Media Growth & AI Virality Analytics
SkillMITFew starsNo key
High-performance Win32 disk allocation analyzer & space cleanup CLI for Windows and AI agents. Native C++17, zero dependencies, NTFS cluster-accurate, reparse-safe.
SkillMIT★ 5No key
Triage desk for Claude Code: auto-pick the right model and thinking effort for each request, with an explainable triage slip. / 为 Claude Code 自动选择合适的模型与思考深度
SkillMIT★ 1Few starsNo key
A lightweight, single-binary Agent Skills CLI manager written in Go
SkillMIT★ 10No key
Claude Code skill: benchmark LLM inference on Hygon DCU (海光DCU) — preflight OOM-safe matrix, vLLM deploy, input-length & concurrency sweeps, auto test report
SkillMIT★ 4Few starsNo key
Go-first framework for dependable AI agents: typed dependencies and outputs, explicit tools, composable models, observable runs
SkillMIT★ 7No key
Agent skill that makes a coding agent verify before it claims done — no stubs, no fabricated test results, evidence-backed completion reports.
SkillMIT★ 4Few starsNo key
Behavior discipline for coding agents: read-before-write enforcement, failure convergence, write verification with auto-rollback, and a high-risk command gate. Ships FULL plugin/hook adapters for DSH,
SkillMIT★ 5No key
Claude plans & verifies, Codex executes — an orchestrator/executor split for Claude Code.
SkillMIT★ 6No key
StructAI offers a robust toolkit for LLM interaction—such as structured outputs, context management, and parallel execution.
SkillMIT★ 8No key
⛵️ High-performance Rust orchestrator for Claude Code agents. Runs concurrent agents in git-isolated branches with retry loops, priority queuing, SQLite memory, pattern mining, scheduled tasks, and li
SkillMIT★ 3Few starsNo key
The AI agent framework Go deserves — composable, interface-driven, and built for where AI is going.
SkillAGPL-3.0★ 2Few starsNo key
Agent Skills for Fortytwo Network — the first collective super-intelligence owned by its participants. These skills enable AI agents to query Fortytwo Prime for high-confidence answers.
SkillMIT★ 5No key
AI agent skill for Redux-Saga — 25 rules: effects, fork model, channels, RTK integration. Works with Claude Code, Cursor, Codex, Windsurf.
SkillMIT★ 2Few starsNo key
LeanRigor is an open-source control plane that classifies coding-task risk, selects a Fast, Standard, or Rigorous workflow, and enforces planning, approvals, validation evidence, review and safe integ
SkillMIT★ 1Few starsNo key
Let Claude Code pick the reasoning effort for each task - a plugin that routes hard work to high/max-effort subagents.
SkillMITFew starsNo key
Structured memory system and behavioral guardrails for AI agents. Reduce hallucinations, preserve technical decisions, and enforce Explore→Execution workflow boundaries during vibe-coding with OpenCod
SkillMIT★ 1Few starsNo key
OpenAI Codex skill and plugin for reliable long-running, high-risk refactors and migrations, with durable plans, recovery across context compaction, one fixed executor, evidence-backed completion, and
SkillMIT★ 1Few starsNo key
Claude Code as commander of a mixed elite AI team — Codex (GPT-5.5) + official Grok Build as fan-out workers. Dynamic-workflow concurrency, quota pooling, each engine to its strength. One-command inst
SkillMIT★ 2Few starsNo key
7-phase feature development workflow with 4-round cross-verification for Claude Code — catches concurrency, idempotency and cross-service bugs before production
SkillMIT★ 2Few starsNo key
Council-planned GPT-5.6 Sol/Luna Codex Skill with adaptive k=0..7 execution
SkillMITFew starsNo key
A Claude Code plugin and marketplace providing a skills library for high-quality Java development.
SkillMITFew starsNo key
A transferable working method for high-stakes autonomous coding: diagnose before you build, ship the smallest verified slice, make no claim without a failable check.
SkillMIT★ 2Few starsNo key
Who stands behind it
