evo
claudecodexStructured experiment-driven code optimization using tree search and parallel subagents
7 skills · 2 commands · 3 agents · hooks
Claude Code and Codex plugins their authors filed under "productivity". All categories.
Structured experiment-driven code optimization using tree search and parallel subagents
7 skills · 2 commands · 3 agents · hooks
Give Claude the ability to watch and understand videos — extracts frames via ffmpeg and processes audio via Gemini API, local Whisper, or OpenAI API. Multimodal perception layer for Claude Code.
1 skill · 2 commands · 1 agent · 1 MCP server
Control the live draw.io canvas through draw.io's own graph API so users can watch scientific illustrations appear step by step, then save, validate, and export them.
1 skill · 2 MCP servers
知らない分野を、原文にたどりつくまで芋づる式に掘るスキル
1 skill
Spins up 100 sub-agents on the exact same task, each with a different strategy card, and runs them through an attack, defend and judge bracket until one answer survives.
1 skill
Voice conversations with Claude Code using local speech-to-text and text-to-speech. Includes support for remote agents via mobile, web and CLI.
1 skill · 1 agent · 1 MCP server
Visual context sharing between AI and users - display files/URLs/commands with 'show', observe screen context with 'look'
2 skills
Privacy-first Voice of Customer: query self-hosted customer feedback with cited evidence.
1 skill · 1 MCP server
All OMA skills and specialist teams
41 skills · 3 MCP servers · hooks
Universal Claude Code workflow with specialized agents, skills, hooks, and mode commands for any software project. Includes orchestrator, code-reviewer, debugger, docs-writer, security-auditor, refactorer, and test-architect agents.
14 skills · 26 commands · 7 agents · hooks
Self-evolving second brain with 43 AI agent skills, 10 agents, and people CRM. Closed-loop harness release: a V-model verification lifecycle (spec to evidence, criterion-traced checkpoints), read-only verifier agents that observe artifacts instead of trusting worker summaries, risk lanes, multi-session ultragoals with a north-star acceptance gate, plus craft skills for writing, visual work, and a paired anti-slop design system for marketing and product UI. Inspired by Garry Tan's gstack specialist sessions, gbrain knowledge patterns, and dwarves-kit closed-loop execution. Works with Claude Code, Antigravity, Cursor, Kiro, Gemini CLI, Codex, and any markdown-reading agent.
43 skills
Read your team's Commonly pod and post handoffs, decisions and files back to it.
1 skill · 1 MCP server
Bring your coding agent into a Commonly team pod with shared context and handoffs.
1 skill
Mine your SpecStory coding histories into a persistent corpus and forge your repeated workflows into installable agent skills.
1 skill
Cron-like daemon that runs Claude prompts on a schedule
3 skills · 10 commands
AI-powered deep research with multi-agent source verification, 7-phase pipeline, and structured report generation.
Draft-first PRD generator — probe the real problem, draft 4 design documents immediately, confirm assumptions in one batch
Natural language team builder for Claude Code — choose Agent Teams or Workflows and select Fable (default), Opus, Sonnet, or per-role models. Preserves approved model assignments; Haiku is opt-in.
Aprovar ou recusar pelo Habblaud os pedidos de permissão do Claude Code e responder as perguntas do agente (hook PermissionRequest).
hooks
Mod do Habblaud: uso do plano (5h e semanal) para o escritório, aviso embaixo do prompt quando outra sessão precisa de você e o comando /habblaud.
Mandar mensagens pelo Habblaud: o que você digita no escritório entra na sessão como se você tivesse digitado no terminal.
Writes, reviews, and fixes CCManager configuration files (.ccmanager.json and the global config.json): command presets, status/worktree hooks, worktree auto-directory patterns, merge arguments, shortcuts, and auto-approval.
1 skill
Your coding agents, one team — and proof for every step. The most complete team skill for Claude Code, Codex and Cursor.
2 skills
Complete .NET development toolkit with 39 skills and 6 specialized agents covering Akka.NET, Aspire, testing, and modern C# patterns
39 skills · 6 agents
Design and build expressive 3D scenes, explainers and interactive models with grounded subject knowledge.
1 skill
Persistent cloud memory for Claude Code with automatic recall, transcript ingest, and on-demand setup, recall, and store skills.
3 skills · hooks
5–10x faster browser operations: Jev clicks, Codex thinks and verifies. Built at EZCollegeApp.
1 skill
Read app usage and search traffic before and after releases with API-backed CLIs.
2 skills
Build, evolve and explore evidence-grounded ontologies from analytical goals and project tasks.
3 skills · 1 MCP server
Build, validate, sign, and archive macOS/iOS Shortcuts directly from Claude Code. Ships a full knowledge base, a build agent (/shortcuts-playground:build) and a remix agent (/shortcuts-playground:remix), a PostToolUse auto-validation hook, and the validate/resolve-icon/sign-shortcut wrappers.
1 skill · 2 commands · 2 agents · hooks