ツール

Distills 20+ full articles by one author into six layers of rules (word choice, structure, topics, sources, mental frameworks, visuals and layout) in a Writing-DNA.md the agent reads before writing, to reproduce that style. For capturing your own or your team's voice, not impersonating others.

Bright Data's official MCP: web search (Google, Bing, Yandex), any page to Markdown, structured data extraction from e-commerce, social and other platforms, and remote browser control. Needs an API token; includes 5,000 free requests a month.

LLM translator for novels, subtitles, ebooks and game text: one-click glossaries keep names consistent and translations get auto-reviewed. Besides the desktop app it has a CLI (translate/analyze, JSONL status). Download from Releases and bring an LLM API; commercial use needs the author's OK.

Simon Willison's website screenshot CLI: batch screenshots from YAML, record demo videos, export PDF and HTML, run JavaScript in pages to extract data, and dump accessibility trees. Built on Playwright; install a browser on first use.

Blog writing and SEO skill suite: /blog commands for strategy, outlines, drafting, rewrites, quality audits, multilingual publishing and refreshing old posts; drafts scoring under 90/100 are reworked. Get the review subagents and scripts via the plugin or install script; needs Python 3.11+.

An end-to-end blogging plugin: topic research, outlines, drafting, rewrites, fact-checking, SEO and AI-citation optimization, plus multilingual publishing. Each post is scored on a 100-point rubric and reworked if under 90. Needs Python 3.11+; optional images and voiceover use a Gemini API key.

Translates a finished blog post into one or more languages while keeping formatting, images and charts, localizes keywords, titles, meta descriptions, dates and currencies per market, and flags sentences that read like machine translation. No account needed; part of the claude-blog suite.

Translates whole EPUB books, Word files, SRT subtitles and TXT with local Ollama or cloud LLMs (OpenAI, Gemini, DeepSeek), keeping layout and timings. Builds a glossary for consistent terms and can resume jobs. Mainly a desktop app; the CLI runs from source; cloud models need an API key.

Runs open image models like FLUX, Qwen Image and Z-Image locally on a Mac: text-to-image, reference-based edits, inpainting and upscaling, all on-device. Needs Apple Silicon and uv; the first run downloads models and is slow. Check each model's license before commercial use.

A research-writing plugin from K-Dense: searches the literature in real time before drafting, then produces papers, reviews, grant proposals, posters and slides with verifiable citations and figures. Literature search needs a Parallel API key; PDF output needs LaTeX.

Four tools for real-time web search, page content extraction, site mapping and full-site crawling, available as a remote server or run locally. Maintained by Tavily; needs an API key or OAuth sign-in, and a free account is available.

Two-stage deep research: drafts an editable outline for the topic, then parallel subagents search the web item by item and compile a Markdown report. Good for literature reviews, competitor research and due diligence. Install by copying files per the README, plus pip install pyyaml.

Terraform and OpenTofu best practices from Anton Babenko: diagnoses the failure mode first, then guides testing, module structure, state management, CI/CD and security scanning. Works for AWS, Azure and GCP.

A Chinese-first editing skill that also works on English: strips boilerplate, padded lead-ins and stiff phrasing while keeping numbers, conditions, commitments and the author's voice. Can flag issues without rewriting. It doesn't detect AI text or promise to evade detectors.

MiniMax's official CLI, built for agents: chat with MiniMax models from the terminal and generate images, video and speech, plus speech transcription, image understanding and web search. Works with the international platform. Requires a MiniMax Token Plan subscription.

Exports Feishu/Lark docs, whole folders or wikis to Markdown with images, so agents can read, migrate or archive them. Requires creating a custom app on the Feishu/Lark Open Platform and configuring its App ID and App Secret.

A native Go MCP server for Kubernetes and OpenShift: talks to the API server directly to create, read, update and delete any resource, view pod logs, exec commands and install Helm charts, without needing kubectl. Supports multiple clusters.

A CLI and Python library by Simon Willison: imports JSON and CSV straight into SQLite with automatic table creation, runs in-memory SQL queries over files, and supports full-text search and table transformations.

Translates entire books: splits PDF, DOCX or EPUB into chunks for parallel subagents, keeps terminology consistent, resumes interrupted runs and verifies with hashes, then outputs HTML, DOCX, EPUB or PDF. Needs Calibre, Pandoc and Python.

The Linux Foundation's open-source compliance toolchain: analyzes project dependencies, scans licenses and copyrights, checks known vulnerabilities, flags policy violations and generates SBOMs and notice files. Needs Java 25 or Docker and ideally 8 GB RAM; have legal review license findings.

Unofficial Freshservice CLI built with Printing Press: lets AI check an IT agent's queue, flag tickets near SLA breach, search tickets and the knowledge base, gauge team workload, spot recurring issues and KB gaps, and manage changes and assets. Needs a Freshservice account and API key.

Community-maintained GitLab MCP server: manage projects, merge requests, issues, pipelines, wikis and releases, with support for self-hosted instances and a read-only mode. Needs a GitLab personal access token or OAuth.

Microsoft's official Azure DevOps MCP server: query and act on work items, repos, pull requests, build pipelines, test plans and wikis. Sign in with a Microsoft account that has access on first use; Microsoft recommends the no-install remote version instead.

Self-hostable long-term memory for agents, offering MCP, a REST API and a web dashboard: semantic search, knowledge graph and automatic memory consolidation. Embeddings are computed locally; choose SQLite, Cloudflare or Milvus as the backend.