Shape agent capabilities into your workflow.

Skill Doctor scans project, global, and system skill roots to show what is installed, which definition wins, where names or triggers collide, and where risky patterns appear. It offers a local browser UI, CLI reports, and immutable scan history while binding to localhost by default. Static analysis works locally, with optional model-assisted analysis available through a configured compatible endpoint.

This repository offers a set of agent skills for improving visual parts of a product, including animation, typography, layout, and color. It can be installed with `npx skills add jakubkrehel/skills` and then used from an agent host that supports skills. The available project description does not enumerate the individual skills, workflows, or framework requirements, so it is best treated as a collection to inspect and invoke selectively for interface-polish work.

This marketing skill collection packages repeatable workflows for A/B testing, analytics tracking, competitor pages, content strategy, copy editing, landing-page conversion, email sequences, and SEO audits. It is a fork of coreyhaines31/marketingskills that adds prebuilt `.skill` files for easier installation in Claude Code and other Agent Skills-compatible tools.

Greptile Skills provides workflows for checking unresolved review comments and status failures, running a Greptile CLI review on the current checkout, and repeatedly reviewing and fixing a change. The skills can detect GitHub, GitLab, or Perforce from the environment, but you must install and authenticate the matching gh, glab, p4, or Greptile CLI first.

Robotics Agent Skills supplies focused guidance for ROS1, ROS2, testing, bringup, perception, design patterns, containers, and security. Loading the relevant SKILL.md files helps agents account for issues such as QoS compatibility, lifecycle nodes, bounded callbacks, health checks, and safe shutdown rather than generating syntax-only ROS code. The skills can be copied into Claude Code, Cursor, or custom agent frameworks.

Dr JSkill is an Agent Skill for creating Spring Boot applications according to a defined set of Java development practices. It guides compatible coding assistants through generating projects from start.spring.io and configuring Java 25, PostgreSQL, REST APIs, monitoring, Docker builds, and a choice of Vue, React, Angular, or vanilla JavaScript. The repository also includes references for databases, testing, deployment, and a hands-on workshop. It is not a standalone scaffolding application and must be loaded by a supported agent such as GitHub Copilot CLI or Claude Code.

AgentRL separates agent reinforcement-learning training from environment deployment. Rollout, actor, and reference workers run on Ray to generate trajectories, update the policy, and maintain a frozen KL baseline, while a controller and task workers manage multi-turn environments over HTTP or gRPC. It is suited to reproducing the paper’s experiments or adding tasks, but training requires Ray, suitable CPU/GPU resources, and model configuration.

This agent skill gives coding assistants 70 Playwright guides with TypeScript and JavaScript examples for authoring tests, debugging failures, CI, CLI automation, page objects, and migrations. You can install the whole repository or only the relevant skill pack, and the agent loads the appropriate guidance on demand. Its documented coverage targets Playwright 1.61 and recent releases.

Use TanStack Intent to generate and validate Agent Skills for a library, then ship them alongside the related npm package. The skills are auto-discoverable, versioned with the code, and compatible with the open Agent Skills standard, helping maintainers keep agent guidance aligned with each library release.

claude-cmd gives Claude users one CLI for maintaining custom commands, project-specific CLAUDE.md files, security profiles, MCP servers, and settings. It can search local or GitHub-backed command collections and install selected entries, making it useful when several projects share reusable workflows.

Daiso MCP exposes Korean retail, local-information, and cinema lookups through a remote MCP server, the `npx daiso` CLI, and a Codex skill. It can search stores, products, and stock across Daiso, convenience chains, Olive Young, and major retailers, compare selected prices, find nearby venues or fuel stations, and check movie schedules and remaining seats. End users can access the supported services without preparing separate API keys.

AgentSkillsHub continuously collects Agent Skills, MCP servers, Codex skills, and other agent tools from GitHub. Its web directory and API provide search, filtering, quality scores, security grades, trending lists, rising projects, and related-project views. The classifications and scores are generated through scheduled synchronization, deduplication, enrichment, and multi-dimensional rule-based analysis.

Devo is a model-neutral coding agent with both a desktop application and a terminal TUI/CLI backed by the same local Rust runtime. It connects to OpenAI-compatible or Anthropic-compatible APIs, DeepSeek, Qwen, Kimi, private gateways, and local endpoints, while adding semantic code search, MCP servers, reusable skills, and multi-agent work. It is designed for private and intranet environments as well as normal local use. Current macOS desktop builds are unsigned and require manually removing the quarantine attribute after installation.

MagicSkills keeps reusable `SKILL.md` directories in one local pool and lets users compose named subsets for different agents or workflows. Runtimes that read `AGENTS.md` can receive a synchronized skill section, while agent frameworks can use the same collection through a command-line or Python tool interface. It is aimed at multi-agent projects that want to avoid copying and drifting skill folders, and requires Python 3.10–3.13 plus Git.

Mini-Kode is an educational coding assistant that presents modern agent architecture in a compact but complete terminal project. Its code shows how tools, model calls, permission approval, streaming, and the agent loop fit together, with file operations, search, command execution, and MCP integration available for developers to study and modify.

This kit helps creators choose AI video models, translate prompts between model formats, and reuse tested workflows for storyboarding and debugging. It combines a large prompt library with Claude skills, methodology guides, and automated monitoring of official endpoints, making it useful for comparing or moving work among Seedance, Kling, Sora, Veo, and related systems.

mizchi/skills packages practical engineering guidance into independently installable skill directories covering frontend reviews, Node.js, AWS, Cloudflare, SQL, DevOps, languages, and related tooling. Each skill follows the open Agent Skills format and can be installed with APM, the skills CLI, or a direct folder copy. Compatible agents such as Claude Code, Codex, Cursor, opencode, and Gemini CLI can consume the same skill files.

Qt AI Skills is the official agent-skill collection for Qt development and quality assurance. It covers Qt C++ and QML reviews, QML best practices, UI design, documentation generation, profiling, test creation and execution, Figma token and component conversion, and Qt 6 CMake projects. Selected review workflows combine deterministic linting with parallel AI analysis, and an official Qt documentation MCP server provides API lookup. The skills support Claude Code, Codex, Gemini CLI, and GitHub Copilot, but results still require careful review.