Use when the user wants Codex to inspect, edit, version, render, or quality-check a DaVinci Resolve project through Resolve Studio Control. Keep the workflow local-first, preflighted, auditable, and safe.
When the user says “fix this”, “what is wrong”, or “debug this”, use visible terminal/editor context to create a structured debugging command for Codra / Codex / OpenCode.
Use when the user wants Codex to inspect local video footage, understand narration, create or revise an AI-authored cut plan, or render a local editable video project with CutPilot.
Safely summarize Mattermost channels and threads, search posts, resolve Mattermost team/channel names, and draft or publish reviewed posts through the bundled local Mattermost MCP server or another compatible connected server. Use for Mattermost conversations, decisions, action items, incident context, post search…
Use when the user explicitly requests Claude, Sonnet, Fable, or Opus, or when an independent Claude perspective would materially improve a coding task, review, or diagnosis.
A skill that adapts ProjectFlow MCP commands for automatically executing engineering task graphs. It follows the server’s execution protocol and records task results and verification evidence.
Add Free2PA provenance and local trust checks to an agentic application. Use when a developer asks to protect an agent, OpenClaw project, ChatGPT app, MCP server, Agents SDK workflow, skills, prompts, SOUL.md, AGENTS.md, policies, or other control files from unnoticed changes or outside-group publishers.
Report meaningful Codex task progress, decisions, blockers, artifacts, and final outcomes to Loomscope. Use whenever a task has multiple phases, several tool calls, or a result worth tracing later.
Drive a Windows or Linux host running agentic-remote-pc over its authenticated MCP runner. Use when the user asks to run commands on a remote PC, drive a coding-agent CLI (claude, cursor, aider, opencode, gemini, codex, copilot, goose, amp, qwen, crush) on a host, inspect health, or validate a local…
Install Veta, sync or resume saved X bookmarks through the current agent-controlled browser, organize them in the local database, and answer questions from the library. Use when the user mentions Veta, X or Twitter bookmarks/saves, importing saved posts, resuming a bookmark scan, or querying their saved-post knowledge…
Use the AppMarquee MCP tools to inspect uploaded app screenshots and create, revise, or validate App Store and Google Play screenshot decks without needing the app source directory. Trigger for store screenshots, screenshot copy, device decks, localization, App Store creatives, or Google Play creatives.
Extract timestamped transcripts and top-liked public comments from YouTube URLs, then turn them into grounded summaries, key ideas, highlights, chapter timelines, comment excerpts, or notes. Use when a user pastes a YouTube, youtu.be, Shorts, embed, or live URL and asks what the video says, requests highlights or…
Guide an incremental, evidence-aware discussion that turns an AI, product, model-strategy, competition, or implementation topic into durable personal cognition. Use when the user wants to discuss, learn, explore, compare, challenge, or deeply understand such a topic, including a recommended daily topic. Ask one…
Convert user-provided documents, PDFs, notes, or transcripts into polished private Spotify podcast episodes. Use when the user asks to turn written source material into private Spotify audio. This integration composes the external $save-to-spotify production skill with local Kokoro narration and optional placement in…
Anchor this session to a named Chat Across environment and auto-sync a compacted context brief both ways. Use when the user says "chat-across " or asks to connect/anchor to a Chat Across environment.
Use when an engineering task may benefit from an independent Claude Code investigation, review, or alternative implementation and the value of delegation must be weighed against cost and risk.
A workflow for finding and maintaining papers from China’s Communication University on wireless communications and closely related topics. SCI-EXPANDED is a research index used to track scholarly publications, and a DOI is a permanent identifier for a paper.
Use for every task that requires interacting with a website or browser. Controls the user's existing authenticated Chromium browser through Chromium Bridge.
Delegate any substantial local task to Grok Build as one durable logical job, in a repository or a non-repository workspace, and retrieve its genuine final result across turn, token, context, and caller-session boundaries. Use when the user asks for Grok/Grok Build, an independent builder/tester/reviewer/researcher…
★not rated 0 15d agoA90 tokens
originalMIT
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: