MCP servers and skills: search, filter by where they run, and compare.
Add EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Open-source Claude Code skills — 6 cognitive firewalls block AI hallucination, bias & sloppy reasoning. npx skills add
SkillMIT★ 41No key
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
Step-by-step guide for capturing key application requirements for NoSQL use-case and produce Azure Cosmos DB Data NoSQL Model design using best practices and common patterns, artifacts_produced: "cosm
OfficialSkillMIT★ 40k in collectionNo key
Provides data-retrieval best practices, tool selection guidance, and performant SQL query syntax for BigQuery telemetry across INFORMATION_SCHEMA, Cloud Monitoring, and the REST API. Use when the tele
OfficialSkillApache-2.0★ 21k in collectionNo key
Evaluate, configure, and migrate workloads to AWS Lambda Managed Instances (LMI). Triggers on: Lambda Managed Instances, LMI, capacity provider, multi-concurrency Lambda, dedicated instance Lambda, EC
OfficialSkillApache-2.0★ 918 in collectionNo 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
SkillMIT★ 8No key
Claude plans & verifies, Codex executes — an orchestrator/executor split for Claude Code.
SkillMIT★ 6No key
SkillMIT★ 2Few starsNo 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
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
Who stands behind it
