Productivity plugins

Multi-LLM integration for second opinions and task delegation

4 skills · 8 commands

Publish academic papers as AI agents

10 skills

A shared, governed brain for Claude Code. Claude checks your team's versioned notes on each prompt and updates them when you correct something.

1 skill · 3 commands · 3 agents · hooks

Bionic reading for Claude's responses that bolds the leading part of each word to guide your eyes and enable you to read faster.

1 skill · 6 commands · hooks

Export Claude Code session logs as standard LLM conversation JSON and human-readable TXT transcripts. Compact sessions into resumable context files. Recap recent sessions for quick context recovery. Identify current session, export individual sessions, batch-export all project sessions, or report token usage statistics.

7 skills

Stop hooks that terminate a Claude Code session when the agent's final message contains a kill phrase. Two scripts: single-kill (ends Claude) and double-kill (ends Claude plus the terminal shell that launched it), each bound to its own phrase. Installs at local (project) or global (user) scope; scripts require LOCAL or GLOBAL arg and exit 1 if missing. Contains-match (robust to model preambles), case-sensitivity configurable, and a kill path that walks the process tree to the owning claude (and, for double-kill, the top-most shell ancestor) and never signals pid <= 2. Install, remove, update, info, and whendone skills via a router; composes safely with existing Stop hooks.

6 skills

Codex skills adapted from the PEPFlow Claude command workflows for PEP convergence analysis and Lyapunov proof discovery.

5 skills

Dream-briefing for AI coding agents: a cognitive checkpoint at session end, a 'while you were away' briefing at session start.

2 skills · 1 MCP server · hooks

Diagramming toolkit for Claude Code. A router skill dispatches diagram requests to format-specific skills: ascii-art (diagrams drawn with extended ASCII box-drawing characters from CP437 — single ┌─┐, double ╔═╗, shading ░▒▓█ — never + - | /, capped at 80 chars with strict row/column alignment), mermaid (flowcharts, sequence, and other Mermaid diagrams), and wardley (Wardley maps in the WTG2 / wardleyToGo DSL, emitted as .wtg2 for rendering to SVG via wtg2svg). Extensible — add a new skill per diagram format and a row to the router table.

4 skills

Auditable, version-controlled long-term memory workflows for Claude Code

4 skills

Persistent memory system for Claude Code - Go implementation with SQLite and ChromaDB

1 command · 1 MCP server · hooks

Business analysis with data storytelling and KPI dashboards

2 skills · 1 agent

Adds lightweight reflection prompts to long-running Codex turns.

1 MCP server · hooks

BYOK SEO workflows for Codex powered by DataForSEO APIs.

1 skill · 1 MCP server

BoondManager ERP/CRM — 180 outils, 11 prompts, 22 resources

1 MCP server

Create README banners with the existing GitHub Repo Banner service.

1 skill

使用 SYSURedHead 创建、编译并检查中文党政机关公文 LaTeX 草稿。

1 skill

Rebuilds ComfyUI workflows into a form people can read (Readable Node).

1 skill

See what you paste into Claude Code: image thumbnails and long-text previews above the prompt

See the images you paste into Claude Code as big previews above the prompt instead of bare [Image #1] tags

Full catalog: every Agent Toolkit skill in one opt-in plugin (experimental stability — install deliberately, not by default).

107 skills · 18 agents

Portable academic research and writing workflows.

7 skills · 36 commands · 11 agents · hooks

Helder Berto's 🛠️ Battle-tested software engineering skills for AI coding agents 🤖, from idea to PR.

41 skills · 4 agents

Spec authoring, review, matrix, and planning skills for Agent IX.

22 skills

Manage Spotify ad campaigns, audiences, measurement, account access, assets, and reporting with natural language and OAuth.

20 skills · 1 agent

Live web data for sales, research and monitoring. Find and qualify B2B companies and people, enrich and score your CRM, catch buying signals and draft outreach; research markets, competitors, investors and people across professional networks, social media, reviews and the web; and get regular reports on what changed. The full anysite skill suite, with the anysite connector.

18 skills · 1 MCP server

Full set of AI agent personas: architect, code-reviewer, security-reviewer, planner, and 12 more

18 agents

Lightweight AI-assisted build loop: scaffold + tasks + acceptance + living roadmap + decision log + mandatory plan/spec gate + verify gate + deploy/rollback. Six-phase loop with ANSI-colored phase banners and explicit memory confirmation.

7 skills · 9 commands · hooks

Efficient, Evidence-based, Opinionated vibe-coding pipeline

14 skills · hooks

Agentic PR review: гибридный RAG + граф кода через MCP, скиллы review-pr/solve-task/sync-tasks

14 skills