Productivity plugins

Eleven skills and one /cold command that run cold outreach end to end from a cold.md file in your repo. Sends through FoxReach.

11 skills · 1 command

The in-session surface of archeus: recall this project's memory, check its health, and review the current diff without leaving the conversation.

8 skills · 3 commands

Turn Claude into your TikTok Shop affiliate outreach and affiliate operations assistant — 9 skills + Crevideo Reach MCP (79 tools, OAuth sign-in). Works with Claude Code, Claude.ai web, WorkBuddy, and OpenAI Codex.

9 skills · 1 MCP server

Spec-driven delivery pipeline: grill a topic into ratified decisions, write and validate a spec against it, split the spec into dependency-ordered tasks, then implement them in isolated worktrees with batched validation.

5 skills · 2 commands · 3 agents

DIY your own multi-agent workflow with Claude Code and Codex: /setup-dkitchen walks you through the roles, house rules, and repo scripts for your repo.

10 skills

Formally verify programs against their specifications.

10 skills

Markdown-based task management with daily/weekly views, archiving, and idea tracking

1 skill · 8 commands

PhotonForge PCell, layout, routing, circuit/time-domain simulation, project versioning + cloud-GUI (photonforge-server), serialization, GUI automation, LiveViewer, variation-aware yield/DFM, and documentation guidance for AI coding agents.

8 skills · 1 MCP server

The complete Olano Singapore MCP suite with all eight Agent Skills.

8 skills · 1 MCP server

Local Speak Swiftly speech, playback, runtime operation, MCP, and Codex final-reply TTS hooks.

6 skills · 1 MCP server · hooks

Easily create hooks to prevent unwanted behaviors by analyzing conversation patterns

2 skills · 4 commands · 1 agent · hooks

Your agent draws the architecture. Creates and edits native, editable Draw.io (.drawio) and Excalidraw (.excalidraw) diagrams - cloud and system architectures, data pipelines, agentic systems, network views and flow diagrams - with 6,000+ bundled icons, a learned house style, and everything running locally.

6 skills · hooks

Build, run, and validate Tray workflows in natural language. Research connectors, configure authentication, and test integrations without leaving your AI IDE.

5 skills · 1 agent · 1 MCP server

The LLM Wiki suite and learning workflows from the Tiro team: bootstrap a personal LLM-maintained wiki, ingest sources, query it, keep it healthy, learn Socratically, and (optionally) keep it in sync with your Tiro notes.

7 skills

Unified code review that fans out parallel scanners over a change — one per active lens, up to eleven per run — and merges them into one per-file report. Eleven lenses: comment quality, four quality/craft lenses (readability & tests, naming & module, objects & patterns, simplicity & types), an always-on correctness lens (wrong conditions, unhandled cases, off-by-one, swallowed errors, races, broken call contracts), an always-on narrow security lens (secrets, injection, access checks, boundary validation, insecure settings, IaC exposure, access widening, plus access policies and CI workflows), an always-on coherence lens (docs, contracts, migrations, config and sibling listings that disagree with the code or each other, code breaking a rule an accepted ADR or CONTEXT.md states), an always-on assumptions lens (code relying on library, runtime, CI or platform behaviour the installed source or the locked version contradicts, test doubles the real dependency would not match), a performance lens for executable source (N+1, unbounded fetch, blocking-in-async, wasted renders, missing indexes), and a spec lens via --spec <path> or a spec file the diff carries. Explicit rules in a root CODING_STANDARDS.md (plus a gitignored .local.md overlay) generate standards findings. The standalone comment-review and quality-review skills stay invocable for a single-lens pass. Reviews the current branch diff by default (or explicit paths / --base, or a GitHub PR with --pr). Quality findings are tagged family · rule · severity; comment verdicts are R1–R12 · KEEP/REMOVE/REWRITE/MOVE/ADD, shown side by side and applied through a single risk-cut menu. Successor to the comment-review and quality-review plugins.

5 skills · 1 command · 1 agent

A knowledge graph of machine learning and AI research: 2.3 million papers from arXiv, OpenReview and major ML venues, 215,000 authors, 6,200 venues and 28,000 research directions. Use it for literature reviews, related-work sections, and finding out who is working on what.

6 skills · 1 MCP server

Knowledge-ops plugin: stable kb-management + kb-setup skills, the kb-operator agent, and setup-proposed kb-roadmap/kb-journeys skills.

4 skills · 1 command · 1 agent

Apple Creator Studio workflows for production and delivery.

6 skills

Real-time web search, news, business and place lookup, image and video search, and URL extraction for coding agents, powered by Octen.

6 skills

A private writing operating system for Arielle Shipper: Every-style ops writing, article development, editorial review, and durable writing memory.

6 skills

GitHub issue lifecycle: brainstorm design approaches, create structured issues for LLM agent teams, triage and recommend next issues, audit and clean up stale backlogs, and deep-validate individual issues against the codebase

5 skills

Compile, export, import, and sync harness configurations across Claude Code, Cursor, GitHub Copilot, Codex, OpenCode, Windsurf, Gemini CLI, and Junie

5 skills

Four focused OpenAI Codex Skills for inspectable change, review, project guidance, and setup.

4 skills · hooks

Project skills, repository context, and opt-in Ponytail implementation, review and debt.

5 skills

透過 MCP 在 Codex 中使用 Documa 的文件理解、repository graph 與動態 skill 載入能力。

4 skills · 1 MCP server

Session presence hooks, an MCP server and a progress skill for issue-graph: show which issue Claude Code is working on, tell a session which workstream and stage it is in, and give an agent tools over the workstream pipeline

1 skill · 2 commands · 1 MCP server · hooks

Expert-level Wagtail and Django knowledge for AI agents. Best practices and recipes for critical tasks

5 skills

Create, edit, inspect, compile, render, and verify local PowerPoint presentations through PPJ.

4 skills

Slash commands for the Toolpath path CLI: /path:share uploads an agent session to Pathbase, /path:query runs jaq queries over your local session cache. Installs the path binary globally on first use

4 commands

Tidy3D simulation, API, and documentation guidance for AI coding agents.

2 skills · 1 MCP server · hooks