Shape agent capabilities into your workflow.

any2pdf lets an AI coding assistant convert Markdown into a styled PDF through a conversational workflow. The agent can ask about themes, frontispieces, watermarks, and back covers, then produce documents with covers, a clickable table of contents, bookmarks, headers, and footers. Its main distinction is handling mixed CJK and Latin text, system font discovery, formulas, images, and Obsidian callouts across macOS, Windows, and Linux. It uses Python with reportlab and can also be run directly from the command line.

These skills let coding agents use context captured by Entire, including sessions, Checkpoints, prompts, and git history. Ask an agent to find earlier work, explain why code changed, review a branch, or prepare a session handoff without memorizing CLI commands. They are most useful in repositories with substantial captured history, and some indexed searches require the Entire CLI and login.

FFUF Skill for Claude Code connects the ffuf web fuzzer to natural-language requests for discovering hidden paths, files, subdomains, and API endpoints. It helps choose wordlists and analyzes results while using rate limits and other safer defaults. You must install ffuf and a supported Claude client, and only test systems you own or are explicitly authorized to assess.

This Agent Skills collection covers a video subtitle workflow from audio transcription to publishing support. It converts common audio formats into SRT files, can refine wording and proper nouns against an `origin.md` transcript without changing timestamps, adds card annotations, and generates platform-specific summaries for Facebook, Threads, and YouTube. Each stage can be invoked separately or combined into the provided workflow. Users need to prepare the expected files in the same working directory and install the dependencies required by the individual skills.

TanStack Agent Skills gives coding agents structured rules for Query, Router, and Start. The guidance covers cache keys and invalidation, mutations, error handling, type-safe routes, loaders, search parameters, navigation, server functions, middleware, authentication, SSR, and security. Install the skills into a project with the cross-agent command, then compatible assistants can load them for relevant development or review tasks. The repository is a best-practice reference; it does not install or run the TanStack libraries or application.

This documentation library packages agents, instructions, and skills for UI, API, end-to-end, regression, accessibility, and flaky-test work. Teams can embed the material into projects using GitHub Copilot, Claude, Cursor, or similar assistants, with guidance for Playwright TypeScript, Selenium Java, and ISTQB-aligned planning. The repository is a knowledge base and has no build, lint, or test system of its own.

Abu Cowork is a local-first desktop AI agent that can plan multi-step work, read and write files, run commands, control a real browser, and create documents or web pages from natural-language requests. Risky actions such as deletion, overwriting, sending, or installation can be placed behind a reviewable plan and explicit approval. Each conversation can use its own model and permission mode. The app also supports installable skills, MCP connectors, schedules, and team messaging channels for broader automation.

Give Image2 UI Skill a screenshot, design mockup, or app reference and it guides Codex to produce a working clickable demo. Text, buttons, navigation, forms, icons, and interaction states are implemented in code, while complex photography, textures, illustrations, or product imagery are generated with image2. Those assets are saved inside the project and wired into the interface, so the result is a usable prototype rather than a disconnected set of generated images.

Pin multiple skill repositories as flake sources, recursively discover their SKILL.md directories, namespace duplicate IDs, and select exactly which skills enter a bundle. Home Manager integration can sync that bundle to global or project-local destinations for Codex, Claude, Cursor, OpenCode, and other agents. Targets are opt-in rather than automatically installed, making the project best suited to Nix users who want reproducible skill management.

OpenZeppelin Skills gives agents structured workflows for secure contract development using the OpenZeppelin Contracts ecosystem. The available skills cover project setup and contract upgrades across Solidity, Cairo, Stylus, and Stellar, while the secure-development workflow can use the OpenZeppelin Contracts CLI to generate reference implementations. Users can install the collection through the Skills CLI, a Claude Code plugin, or manual copying, making it most relevant to teams already building with OpenZeppelin libraries.

Apple Bento Grid is an agent skill that generates self-contained HTML presentations from stats, achievements, launch data, or year-in-review content. The workflow can choose a layout, light or dark theme, chart and card types, and output orientation. It supports horizontal, square, and vertical compositions suited to project showcases, dashboards, portfolios, and social posts.

Install individual Skywork skills to create or edit documents and presentations, build or analyze spreadsheets, generate images, search current web content, or make music. The collection works with several Agent Skills-compatible hosts, including Claude Code, Codex, and OpenClaw, using platform-specific installation paths. Some workflows call Skywork, Mureka, or related external APIs and therefore require the appropriate credentials.

This Claude Code collection supports computational designers across architecture, engineering, and construction. Eighteen connected modules cover parametric and generative design, geometry, structures, environmental analysis, facades, fabrication, BIM, interoperability, optimization, meshes, automation, and AEC machine learning. A foundation skill routes requests and loads references on demand. Seven Python calculators handle geometry, structural checks, solar conditions, panels, mesh quality, materials, embodied carbon, fabrication time, and cost.

UI Craft installs a design-engineering system into Claude Code, Cursor, Codex, Gemini, OpenCode, and related coding tools. Its CLI can wire in the main skill, focused commands, design and accessibility reviewers, MCP quality gates, and design memory, with backups and rollback around configuration changes. The project separates judgment from deterministic checks: skills and reviewers handle hierarchy and composition, while MCP tools scan for generic AI styling, token drift, and acceptance requirements. It is a workflow layer, not another component library.

hands-on-deck gives AI agents one CLI, deck.py, for inspecting, editing, creating, and verifying PowerPoint files. Agents can read shapes and formatting, change text, styles, themes, images, geometry, notes, and slide settings, or create new slides through the same writer. Changes arrive as atomic JSON patches: every operation is prevalidated, errors report actionable slide details, and a rejected patch leaves the deck untouched. HTML and CSS can be used as a layout-measurement source, then compiled into patches that share the same lint, render, diff, and repair workflow.

sports-skills gives SKILL.md-compatible agents structured access to public data for football, the NFL, NBA, F1, and other sports, with workflows that can compare ESPN, Kalshi, and Polymarket information. Read-only sports queries require no API key or signup. Premium licensed feeds and some real-time odds workflows instead route through the optional Machina service.

Extract the archive and launch Portable Hermes Agent on Windows without admin rights, a system Python installation, or Docker. Its GUI and CLI can use cloud providers or local models through LM Studio, with tools for automation, custom workflows, runtime tool creation, and optional speech, music, or ComfyUI extensions. It supports Windows 10 and 11 only, and local model use generally requires an NVIDIA GPU with at least 8 GB of VRAM.

Graph of Skills indexes a directory of SKILL.md files into an offline skill graph, then returns a small ranked bundle for each task together with prerequisites and related capabilities. It can be used through its CLI, an MCP server, or Claude Code integration, with either prebuilt workspaces or an index built from your own library.