도구

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.

AWS Labs' official plugin marketplace: deploy-on-aws (architecture recommendations, cost estimates and IaC deployment), aws-serverless, aws-amplify, databases-on-aws, sagemaker-ai and more. AWS suggests Agent Toolkit for AWS for new projects.

HashiCorp's official plugin marketplace: the terraform plugin has 16 skills (configuration, modules, provider development, testing, import, Stacks and policy), and the packer plugin has 4 image-build and HCP Packer skills.

HashiCorp's official Terraform and Packer skills: write HCL in the official style, refactor modules, terraform test, provider development, Stacks and policy, plus AWS and Azure image builds.

Jina AI's official remote MCP: converts web pages and PDFs to Markdown, searches the web, arXiv, SSRN and images, and offers screenshots, reranking and semantic dedup. Reading tools work without a key (rate-limited); search and rerank need a Jina API key.

Runs SQL queries against ClickHouse and browses databases and table schemas, read-only by default; can also enable embedded chDB to query data directly in files and URLs. Maintained by ClickHouse.

Lets agents drive a local Adobe After Effects: create compositions, add text, shape, solid and camera layers, and set keyframes and expressions, for batch intros, lower thirds and motion graphics. Needs After Effects 2022+ and Node.js; build from source and open the bridge panel in AE.

Lets agents drive a local Photoshop: remove backgrounds, retouch portraits, color grade, batch-watermark, and export or split carousels at social media sizes; multi-step edits undo in one step. Needs Photoshop and Node.js 18+. Unofficial; sends anonymous telemetry by default (opt-out).

Drives local Premiere Pro projects with 280+ operations: import, sequences, timeline cuts, transitions, effects, color, captions, audio ducking, export. Needs Premiere Pro 2020+, Node.js 20+ and the MCP Bridge (CEP) panel open; anonymous telemetry is on by default and can be turned off.

Calls image and video models such as FLUX, Veo and Seedance through inference.sh's belt CLI to generate images, video, avatars and voiceovers, plus guides for thumbnails, storyboards, press releases and social copy. Needs belt and a free inference.sh account; model calls are billed per use.

Unbabel's machine-translation quality metric: comet-score rates translations per sentence and overall, XCOMET marks error spans and severity, and CometKiwi works without a reference. Good for spot-checking MT. Needs Python 3.8+; models download from Hugging Face, some need a license; GPU helps.

Skill pack for YouTube creators with 14 subcommands: channel audits, video SEO, retention-focused scripts, hooks, thumbnail briefs, content calendars, and Shorts and cross-platform repurposing. Works with data you provide; add a YouTube API key or DataForSEO for live data.

dbt Labs' official plugin marketplace with dbt and dbt-migration plugins: write models and unit tests, build semantic-layer metrics, govern with dbt Mesh, debug failed jobs, and handle version upgrades and cross-platform migrations. Most skills need an existing dbt project.

dbt Labs' official skills: write and edit dbt models, add unit tests and docs, set up the MetricFlow semantic layer, debug failed jobs, and handle dbt version upgrades and cross-platform migrations. Most skills need dbt installed and an existing project.

A research plugin for Claude Code: commands like /omp:survey, /omp:experiment and /omp:write chain literature review, topic selection, experiments, writing and self-review, with 5 specialized agents and 34 research skills that remember project progress across sessions. Experiments lean toward ML.

Lets agents work in Photoshop, Premiere, InDesign, Illustrator and After Effects through UXP/CEP plugins and a local proxy: edit layers, lay out pages and cut timelines. A proof of concept, not made by Adobe; install from source.

YouTube channel assistant: lets agents upload videos, edit titles, descriptions and thumbnails, and manage playlists, captions, comments and live streams; also works as a CLI. Requires enabling the YouTube Data API in Google Cloud and creating OAuth credentials; daily API quotas apply.

The five-agent PaperOrchestra pipeline (outline, figures, literature review, section writing, polishing) as skills: turns research ideas, experiment logs and a conference template into a LaTeX paper and checks citations via Semantic Scholar. Needs Python; verify the draft yourself.

Helps agents write geospatial SQL for PostGIS, DuckDB, BigQuery and Snowflake: inspect schemas and keep query costs in check, then render results as interactive maps to review and correct. Needs Python and your own database or warehouse; maps use Dekart, which can run locally in Docker.

Official Firecrawl skill: drives the Firecrawl CLI to search, scrape, map site URLs, batch-crawl, interact with pages and monitor changes, returning LLM-ready Markdown. Search and scrape have a rate-limited free tier; crawling and monitoring need an account or self-hosted instance.

Firecrawl's official CLI: scrape, search, map and crawl sites and interact with pages in a browser from the terminal, with Markdown output; can also install companion skills for coding agents. Needs a Firecrawl account or API key, or point it at a self-hosted instance.

Turns a prompt or still image into a looping animated icon with real transparency, output as animated WebP. It generates one still with GPT Image or Nano Banana, waits for approval, animates it via Seedance on OpenRouter, then mattes and encodes it. Needs Python, ffmpeg and paid API keys.

Two prompt skills: video writes storyboard-style prompts for Seedance, Kling, Veo and more like a director, writer and editor; image writes art-director prompts for Nano Banana and GPT Image, recommending a model per task. Prompts only, generate on the platforms; no API key.

Uses an LLM to translate SRT, ASS and VTT subtitles into any language in batches, convert formats and transcribe audio or video. Install the CLI from source (Python 3.10+); needs an API key (e.g. OpenRouter) or a local model, and subtitles go to that provider.