Tools

Parses PDF, DOCX, PPTX, XLSX, HTML, images and audio, recovering layout, reading order, tables and formulas, and exports Markdown, HTML or lossless JSON. Started by IBM Research, now hosted by the LF AI & Data Foundation; runs fully locally.

Fast regex search across directories (command rg) that respects .gitignore, skips hidden and binary files by default and filters by file type. A go-to command for coding agents searching a codebase.

Command-line toolkit for transcoding, cutting, joining, frame extraction and streaming of audio and video, including ffmpeg, ffprobe and ffplay. A core dependency for agents handling media. The GitHub repo is the official mirror.

Generates self-contained HTML+SVG diagrams in an editorial style: architecture, flowcharts, sequence, swimlane, Gantt and dozens more types. Can match brand colors from a website and redraw imported Mermaid, draw.io and Excalidraw sources.

Upstash's official Context7 CLI (ctx7): search libraries and pull up-to-date docs from the terminal, or set up the Context7 MCP and rules for Claude Code, Cursor and other agents in one step. Docs lookup needs no login; signing in raises rate limits.

Community-maintained simplified command help with example-first pages for common CLI tools, easier to read than man. Install an official client (Python, Rust or Node.js), then run tldr followed by a command name.

Packs a web page, local HTML or dist folder into a lightweight desktop app with one command (built on Rust Tauri; macOS, Windows, Linux), with --json output and llms.txt for agents. Needs Node.js; installs Rust automatically if missing.

Official MCP for the open-source design tool Penpot: through the Penpot plugin API, agents can query, modify and generate designs, supporting design-to-code and code-to-design. Run npx -y @penpot/mcp@latest first and load the MCP plugin in Penpot to connect.

A cat replacement with syntax highlighting, line numbers and Git change markers, plus --line-range to print specific lines. Falls back to plain text in pipes and other non-interactive use, and pairs with git diff or tail -f for code and logs.

'rsync for cloud storage': sync and copy files across dozens of providers such as S3, Google Drive, OneDrive and Alibaba Cloud OSS, with encryption and mounting. Set up remotes with rclone config before use.

Creates a local CA with one command and issues development HTTPS certificates trusted by your system and browsers, for localhost, IPs and wildcard domains, with no extra configuration. Run mkcert -install once first to add the root certificate to the trust store.

AI search optimization (AEO/GEO) skill from the marketingskills collection: checks whether ChatGPT, Perplexity and Google AI Overviews cite your content and suggests rewrites and structure that AI can extract and cite more easily, including llms.txt and structured data.

Marketing skill collection: 50 skills covering SEO audits, conversion optimization, landing page copy, pricing, paid ads, email and social media, all sharing a common product marketing context. Supports Claude Code, Codex and more.

Writes or rewrites marketing copy for homepages, landing pages, pricing pages and more: first clarifies page goals, audience and selling points, then produces headlines, value propositions and calls to action. From the marketingskills collection.

Writes B2B cold emails and multi-step follow-up sequences, refining subject lines, openers, body and calls to action so they feel personal and human. Suited to SDRs and founders doing outbound. From the marketingskills collection; no extra account needed.

Diagnoses website SEO issues: checks crawling and indexing, Core Web Vitals, metadata and on-page content, and gives prioritized, actionable fixes. From the marketingskills collection.

Edits and refreshes existing marketing copy in seven sweeps: clarity, voice, value, proof, specificity, emotion and objection handling, keeping the meaning and author's voice. Can also audit and update stale pages. Complements the copywriting skill; from marketingskills.

From HKU's Data Intelligence Lab: plugins or skills for Claude Code, Codex and other agents generate agent-callable CLIs for apps like GIMP, Blender and LibreOffice, and the cli-hub package manager finds and installs ready-made community CLIs. Needs Python 3.10+.

Modern markup-based typesetting system, a LaTeX alternative for papers, reports and resumes. Fast incremental compilation; typst compile outputs a PDF in one command and watch mode recompiles automatically.

Teaches agents standard single-cell RNA-seq analysis with Scanpy: QC, normalization, PCA/UMAP, clustering, differential expression and plots, with ready-to-run pipeline scripts and guidance on converting Seurat and other R objects to h5ad. Needs Python 3.12+; by K-Dense.

Open-source crypto trading framework: download market data, backtest and optimize strategies, and paper trade from the CLI while agents iterate on strategies. Docker recommended; strategies need Python and live trading needs exchange API keys. Backtests don't guarantee returns.

Drafts, revises and reviews research manuscripts, tying every fact and number to verified evidence and covering reporting guidelines, authorship, AI disclosure and confidentiality; explicitly forbids fabricated citations or data. Includes offline check scripts; no API key needed.

Unified database lookup skill from K-Dense's scientific collection: reproducibly queries about 80 public database APIs such as PubChem, UniProt, ChEMBL, ClinicalTrials.gov and FRED, returning traceable results with endpoints, parameters and count checks. Some need API keys.

Guides agents to the right statistical method for research data: t-tests, ANOVA, chi-square, regression and Bayesian analysis, checking assumptions, computing effect sizes and power, and reporting results in APA format. Python-based (pingouin, statsmodels); by K-Dense.