Explore
MCP servers and skills: search, filter by where they run, and compare.
ade-bench-plugintypedef-ai
LocalClaude Code plugin that generates ADE-Bench benchmark tasks from your own dbt project
SkillMIT★ 3Few starsNo key
gcloudgoogle
Local
MCP servers and skills: search, filter by where they run, and compare.
Claude Code plugin that generates ADE-Bench benchmark tasks from your own dbt project
SkillMIT★ 3Few starsNo key
Provides safety-critical validation, guardrails, and data reduction for gcloud CLI operations across Google Cloud Platform (GCP) services and infrastructure. Use when planning, generating, constructin
OfficialSkillApache-2.0★ 21k in collectionNo key
A structured multi-agent orchestration stack for Roo Code - hierarchical pipeline of specialized AI modes from strategic planning to atomic execution, with automated semantic versioning and releases.
SkillApache-2.0★ 4Few starsNo key
Evidence-backed pathfinder planning, task pyramids, audit gates, lifecycle management, and interactive visualization for AI agents.
SkillMIT★ 2Few starsNo key
A Codex and Claude Code plugin for shaping and running long autonomous engineering work organized by epics/phases/tasks, without losing the plot
SkillMIT★ 3Few starsNo key
A local-only Kanban state dashboard for AI agent swarms - real-time task tracking via HTTP API and SSE
SkillMIT★ 6No key
AI Software Factory for Codex. Intelligent task routing, contextual orchestration, and automated Kanban workflows. Transform AI-powered development into a structured, scalable software production pipe
SkillMIT★ 6No key
Twelve Greek gods. One command. A working SaaS. 98 skills + 49 agents + 13 hooks for Claude Code + Codex CLI + Gemini CLI. Cross-CLI persistent memory, zero-interaction full pipeline (design → build →
SkillMIT★ 7No key
the repo uses a simple harness scoring mechanism deployed as a skill, cli and a python package ( all under work ). The skill is currently accessible as a dashboard mcp + skill with claude. This helps
SkillMIT★ 8No key
Adversarial multi-agent pipeline for Claude Code and Codex CLI: planning, plan review, implementation, cross-model code review, QA. Installable skills, no runtime.
SkillMIT★ 6No key
PRD-to-Implementation pipeline — 14 Claude Code skills for automated planning, task generation, parallel batch dispatch, and milestone verification
SkillMIT★ 1Few starsNo key
Harness-agnostic multi-agent delivery pipeline — plan → implement → review → QA → ship. Stack-neutral roles plus one project profile, with artifacts and outcome data from 20 real runs.
SkillMIT★ 6No key
A local, read-only progress board for AI-assisted development: reads tasks.md / ADRs, GitHub PRs and Claude Code / Codex sessions to show where every task stands.
SkillApache-2.0★ 2Few starsNo key
A skill for evidence-linked paper figures, editable sources, and revision-ready delivery. | 关联证据、制作可编辑论文图件并支持返修交付的技能。
SkillMIT★ 1Few starsNo key
RealityGate: prove your AI-written code is real. Reality Score (0–100) for vibe-coded apps, a CI gate that blocks stubs, fake data, hallucinated npm packages & leaked secrets, a malware scanner for AI
SkillMIT★ 4Few starsNo key
Spec-driven development scaffold for Claude Code — workflow pipeline, memory system, sub-agent orchestration, and quality gates using Claude Code's native features
SkillMIT★ 2Few starsNo key
Dependency-aware test data builder for Go that resolves foreign-key DB relationships automatically.
SkillMIT★ 2Few starsNo key
Your AI agents write code; SPS makes sure it ships. An AI-driven dev pipeline orchestrator built on Claude Code - kanban-driven, persistent memory, per-project Wiki.
SkillMIT★ 3Few starsNo key
Claude Code plugin: multi-agent TDD pipeline with hook-enforced discipline — portable across projects via a per-project profile
SkillMIT★ 1Few starsNo key
Autonomous engineering pipeline for Claude Code — /drive runs the task lifecycle (plan → implement → review → harden → finalize → ship) with two human gates, gstack planning, and codex cross-model rev
SkillMIT★ 6No key
Five-stage shipping pipeline for Claude Code: plan, adversarial review, parallel worktree implementation, per-task review gate, branch review.
SkillMIT★ 1Few starsNo key
A comprehensive 6-phase development pipeline that turns Claude into a senior engineering team. From idea to production-ready, tested, documented code — using structured AI skills.
SkillMIT★ 1Few starsNo key
A Claude Code plugin bundled with skills and hooks to establish a pipeline to iterate the loop of planning, execution, and code review.
SkillMIT★ 5No key
Who stands behind it
