Shape agent capabilities into your workflow.

Research Skills packages Claude Code workflows for medical-imaging literature reviews, PhD proposals, stylized paper slides, and editable academic presentations. Its writing workflows require collecting and verifying sources before drafting, auditing citations, and completing submission checks, while scholar-slides needs an additional Python and Node toolchain.

Equip supported coding agents with guidance for writing Terraform HCL, building modules, developing providers, running tests, and creating Packer machine images for AWS, Azure, or Windows with HCP Packer integration. Skills can be installed individually through the skills CLI or as Claude Code plugins.

sandboxd is a self-hosted engine for building apps with coding agents. A request creates an isolated container, runs an agent against the prompt, and exposes the app at a live preview URL. Teams can use the browser console for creation and file review or integrate the API into their product; idle sandboxes sleep and wake on demand. It primarily targets Linux servers with Docker Compose and Git; macOS via Docker Desktop is best-effort. The project is a 0.x beta using containers rather than VMs, so untrusted multi-tenant deployments need additional hardening.

UPskill is a command-line toolkit for creating standard Agent Skills from task descriptions, examples, existing skills, or recorded agent traces. It can generate tests, compare baseline and skill-assisted performance, refine weak skills from failures, and benchmark multiple models across repeated runs. Evaluations can run locally or through Hugging Face Jobs, making it useful for teams that want measurable evidence before distributing a skill.

Run Library Skills through uvx or npx inside a project and it scans installed dependencies for official agent skills shipped by their library authors. The tool reports status, installs new skills, repairs managed symlinks that point to older package locations, and removes managed links for dependencies that disappeared without touching hand-written skill folders. Because the skills live with the libraries, they update with the installed package version; Windows users can choose copy mode when real symlinks are impractical.

Salesforce Skills Library collects executable workflows for building Salesforce applications, including Agentforce agents, Lightning apps, Flow, Apex, SOQL, Lightning Web Components, objects, fields, and permission sets. Agentforce Vibes installs and updates the collection automatically, while compatible tools such as Claude Code, Codex, Cursor, and OpenCode can add it with the skills CLI. Each skill starts with a SKILL.md file and may include scripts, references, or assets. The library evolves quickly, so skills can be renamed, reorganized, or removed between releases.

Agent Sessions is a local-first macOS app for browsing and searching histories from Codex, Claude, OpenCode, Cursor Agent, Hermes, OpenClaw, Copilot CLI, and other supported tools. It shows transcripts and images, saves sessions, and can open resume commands in Terminal, iTerm2, or Warp. Session data stays on the Mac with no telemetry or history uploads; macOS 14 or later is required.

SWE-smith creates Docker execution environments from GitHub repositories, synthesizes tasks such as file localization and program repair, filters instances that break one or more tests, and generates issue text. The resulting tasks and trajectories can support SWE-agent training or evaluation. It requires Docker and was developed for Ubuntu 22.04; Windows and macOS are not planned targets.

This repository is a small collection of reusable skills for AI coding agents, currently centered on web-shader-extractor. The skill guides an agent through identifying WebGL, 2D Canvas, or shader-based effects on a website, separating them from the original framework shell, and porting them into a standalone native JavaScript project. Users can install the entire repository or select only that skill. It is a focused coding workflow rather than a general-purpose web scraper, browser extension, or visual editing application.

Install these skills in Claude Code, Cursor, or Codex to steer Rails work toward rich domain models, CRUD-oriented routing, Hotwire, fixtures, and vanilla framework features. Separate skills cover migrations, jobs, security, multitenancy, testing, and an opinionated DHH-style review mode. This is an unofficial community project, and much of the material was assembled through LLM analysis, so important guidance should be checked against real implementations.

This Claude Skill shapes conference talks, seminars, thesis defenses, and grant briefings around a clear argument rather than a collection of topic slides. It uses takeaway-style titles, keeps results slides focused on one exhibit, and applies in-slide citations plus a final references section. Claude's built-in PPTX capability handles the actual file generation, so code execution and file creation must be enabled.

This collection packages practical workflows for document and code interpretation, prompt and agent configuration review, diagramming, transcription, and operational troubleshooting. Users can install individual skills through the Claude Code plugin marketplace or a compatible skill installer, making it useful for people who want reusable, Chinese-oriented task guidance. The skill files use the CC BY-NC-SA 4.0 license, so commercial use requires separate permission.

Laravel’s official agent plugins cover several focused workflows: reviewing recent PHP and Laravel changes, selectively bringing improvements from starter kits into an existing project, deploying and managing Laravel Cloud resources, and configuring Nightwatch collection, sampling, filtering, and redaction. Skills can trigger from matching requests or be invoked explicitly. The starter-kit upgrade workflow applies one feature at a time and reruns tests, type checks, and builds rather than silently overwriting customized files.

Storybloq stores roadmap phases, tickets, issues, notes, lessons, and session handovers in a git-trackable `.story/` directory so Claude Code or Codex can recover project state in a new session. A CLI, MCP server, and `/story` or `$story` skill entry points support context loading, handover creation, scoped autonomous workflows, and multi-lens review. It requires Node.js 20 or newer and is designed to keep durable coordination data alongside the code rather than inside one chat client.

OpenContext adds a personal knowledge store to existing coding-agent CLIs such as Codex, Claude Code, and OpenCode, so project background, decisions, and documents can persist across repositories and sessions. Users manage the library through the oc CLI, a desktop app, or a local web interface, while generated skills, slash commands, and an MCP server let agents search and update it directly. It reuses an agent CLI the user already has rather than bundling a separate model subscription.

This collection turns Microsoft Learn guidance into on-demand skills for configuring, troubleshooting, and designing Azure workloads. It spans major service areas and offers role-based bundles, with plugin installation for several coding assistants and manual setup for others. Many skills still need network access to fetch the latest source documentation when used.

The Python orchestrator decomposes a coding goal, runs agents such as Claude Code, Codex, and Gemini CLI in isolated Git worktrees, and gates merges with tests, linting, and type checks. Scheduling decisions are deterministic, while HMAC-chained logs, signed records, and artifact lineage support offline verification and air-gapped operation. It targets multi-agent engineering and compliance-sensitive work, not simple pair programming or general research.

This agent skill organizes material derived from Ni Haixia's teaching on the Shanghan Lun, Jingui Yaolue, Huangdi Neijing, Shennong Bencao Jing, acupuncture, and clinical cases. It can help users discuss six-stage pattern reasoning, look up formulas and medicinal references, or retrieve related cases through a supported agent platform. The repository explicitly limits the material to study and research; it must not replace diagnosis or treatment by a licensed medical professional.