ツール

Drives a local ClipForge (open source) to turn product images, links or a one-line topic into vertical short videos with script, footage, voiceover, captions and music, plus a QA pass. Self-host it with Node.js and FFmpeg; scripts need an LLM (Ollama works); AI visuals need a paid key.

The standard machine translation scorer: computes BLEU, chrF and TER with significance tests and downloads public test sets such as WMT, to compare engines or prompts. Needs Python 3.9+ and reference translations; automatic metrics are a rough screen, so final copy still needs human review.

Experimental open-source generative media MCP servers from Google Cloud: Nano Banana images, Veo video, Gemini TTS and Chirp voices, Lyria music, and AVTool for compositing. Each registers separately; needs a billing-enabled Google Cloud project and gcloud login; AVTool needs FFmpeg.

Pre-submission review for CS conference papers (CVPR, ACL, NeurIPS and more): polish, translate or condense on request, or let AI reviewers raise issues and a jury rule on them. Only wording fixes are drafted, with your approval; missing experiments go back to you, never invented. Needs Node.js.

Batch-translates SRT, ASS, VTT and LRC subtitles, handling a whole season at once, with bilingual output and 120+ languages. The default free translation API needs no setup, or connect DeepL or various LLMs. The CLI runs from a cloned repo with yarn and needs Node.js 24+.

Creates and edits local CapCut (JianYing) drafts from the terminal: rough cuts on silence, styled subtitles and multilingual versions, still editable track by track in CapCut. Needs Node 18+ and desktop CapCut; subtitles need Whisper, translation an Anthropic key. No encrypted drafts. Unofficial.

Skills Sentry's engineering team uses itself: code review, bug finding, security review, writing commits and PRs, and iterating on a PR until CI passes. Maintained by Sentry; some skills follow its internal conventions.

Salesforce's official skill that sets up Service Cloud Omni-Channel routing from the CLI instead of Setup clicks: agent and supervisor users, queues, presence statuses, permissions and routing flows. Read-only preview; writes only to sandbox, trial or dev orgs. Needs Service Cloud, sf and jq.

Salesforce's official plugin that helps service admins configure Service Cloud web chat, messaging, WhatsApp and Email-to-Case channels, connect Agentforce service agents to them and set up handoff to humans. Needs Salesforce org admin rights, a logged-in Salesforce CLI (sf) and Python.

Atlassian's official plugin: connects the cloud Atlassian MCP to search and create Jira issues, read and write Confluence pages and manage sprints, with skills that turn meeting notes into tasks and generate status reports. Needs an Atlassian Cloud account with OAuth or an API token.

Atlassian's official hosted remote MCP: access Jira, Confluence, JSM, Bitbucket, Loom and more with OAuth or an API token. Works with Atlassian Cloud sites only.

Alibaba Cloud's official CLI (aliyun): manage ECS, OSS and other services through OpenAPI, with structured output, JMESPath filtering, waiting on resource states, product plugins and a built-in MCP proxy. Configure credentials first; OAuth sign-in works locally.

Google's official Gemini CLI extension with a built-in MCP server: Nano Banana image generation and editing, photo restoration, icons, textures, step-by-step storyboards and diagrams. Needs Node.js and a Gemini API key; for Claude Code or Codex, clone and build the repo first.

Turns ComfyUI workflows into MCP tools with no code, covering generation and conversion across text, image, speech and video; works with local ComfyUI or RunningHub in the cloud. Start the server with uvx pixelle and configure an LLM first.

Open-source video translation and dubbing: transcribes lectures, courses and other videos, translates them into one of 33 languages, synthesizes a dub aligned to the picture, and can export SRT subtitles. Needs Python 3.10+, FFmpeg, the violin CLI and a pay-as-you-go Together AI API key.

ComfyUI's official CLI: install and launch ComfyUI in one step, manage custom nodes and model downloads, and run image and video workflows, with --json output on every command for agents. Can also submit jobs to paid Comfy Cloud.

Sentry's official CLI: upload source maps and debug symbols, manage releases, and view issues and logs. Needs a Sentry account or self-hosted instance; a newer official CLI is replacing it, so this repo mainly gets bug fixes.

ChatCut's official plugin: edit ChatCut video projects by chat from Claude Code or Codex: import media, adjust the timeline, transcribe and caption, generate voiceover, music and motion graphics, and export. Needs a ChatCut account (free tier available); sign in via browser on first use.

MiniMax's official skill that expands a short style prompt (optionally with section-tagged lyrics) into the structured caption Music 3 expects: overall style, vocal details and per-section arrangement. Local templates only, no API calls; making music requires self-hosting Music 3 (two CUDA GPUs).

Graph database MCP server from Neo4j Labs: reads the graph schema and runs read and write Cypher queries, with read-only mode, query timeouts and response token limits. Needs a Neo4j instance with the APOC plugin enabled.

Turns Manim animations into step-through slide decks: mark slide breaks in scene code, render, then present with manim-slides or export to HTML, PDF or PPTX, for math and science classes and talks. Scenes are Python (agents can write them); needs Manim, plus LaTeX for formulas.

Sentry's official remote MCP: lets coding agents query errors, issues, stack traces and performance traces, and call Seer for root-cause analysis. Sign in with OAuth, or connect to self-hosted Sentry over stdio.

250+ human-reviewed legal skills from practicing lawyers, in-house counsel and academics, mostly US and EU law: compliance, GDPR, legal research, litigation, contract review and drafting, the EU AI Act. Install all or pick one; output is a draft for a lawyer to review.

Lets agents manage Google Cloud resources in natural language through the gcloud CLI, blocking interactive and other agent-unfriendly commands by default, with configurable allow and deny lists. A preview release from Google, not an officially supported product; install gcloud and sign in first.