1,007 tagged Productivity, measured the same way as everything else here.
Browse within: claude-code-plugin 120ai-coding-assistant 63agentforce 48apex 48agentic-workflow 33ai-coding 30claude-ai 29vibe-coding 29ai-assistant 25ai-skills 25builders 24grid-view 24obsidian 24profiles 24
Agent
Expert in AI/ML pipelines, LLM integration, RAG systems, embeddings, and intelligent automation. Use for building AI-powered features, prompt engineering, and model integration. Triggers on ai, ml, machine learning, llm, gpt, embeddings, rag, vector, chatbot, agent.
Agent
Expert in Trilium Notes management. Use this agent for complex note organization, searching, refactoring, and data ingestion into Trilium.
Agent
Agent "growth-pulse-workflow" from Treevu-ai/cli-market-world, covering por qué es distinto de price pulse, arquitectura, fuentes de datos (todas públicas, sin auth), cómo ejecutar and verificado (2026-07-12).
Agent
The single entry point for the presentation generation pipeline. Manages state, planning, retry control, and delegation to other agents.
Agent Claude Code
Read/write GTD task manager for Kevin's personal Todoist account. Use to review tasks, projects, sections, labels and comments, and to add/update/complete/reschedule tasks and add projects/sections/labels/comments. Cannot delete anything (deletion is a manual, human-only operation) and has no…
Agent
OpenWork default agent (safe, mobile-first, self-referential).
Agent Claude Code
Agent "task-orchestrator" from TICnine/autotask-mcp, covering core responsibilities, operational workflow, initial assessment phase, executor deployment phase and coordination phase.
Agent
Research assistant for PubMed Search MCP plus Zotero Keeper MCP. Uses collaboration-safe search, duplicate-check, and import workflow.
Agent
Stateful tmux operator for Project BareMetal-Tmux. Use when: dispatching shell commands into the persistent tmux workspace session, reading terminal scrollback output, breaking stuck or blocking processes with SIGINT, or running long-lived jobs (servers, watchers, REPLs, test loops) that must survive agent restarts…
Agent Claude Code
An email classifier that processes batches of messages using rules, language-model categories from a categories file, and fixed routing decisions. It returns messages marked as confident or uncertain.
Agent Claude Code
Use this agent to record, list, or delete session notes and to-dos via the mcp-starter notes tools. Invoke when the user wants something written down, recalled, or removed from the local notes store.
Agent Claude Code
Agente inteligente para gerenciamento e organização de emails do Gmail. Capaz de triar, classificar, limpar, resumir e responder emails automaticamente com base em políticas configuráveis.
Agent Claude Code
Note: Use the current date from the active host context. Use this when weighting external sources and dating artifacts.
RaNDoM6913/claude-code-superkit
Agent
Clean AI-generated code anti-patterns — redundant comments, one-use abstractions, over-engineering, template slop — via behavior-preserving edits verified by compile/lint.
Agent
Reviews always-on background software — launch agents, daemons, login items, menu bar apps, VPNs, sync clients — and says which ones are worth removing or disabling for battery. Needs judgment about what an app is for — runs on a mid-size model.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: