Shape agent capabilities into your workflow.

Shopify Admin Skills is a collection of installable agent workflows for merchandising, inventory, orders, marketing, support, fulfillment, finance, and other store operations. Each skill works through the Shopify Admin GraphQL API, previews mutations with a dry run, and waits for confirmation before execution. Scheduled routines can monitor areas such as stock, fraud, fulfillment, and business health, while the smart installer helps choose only the routines that fit a store.

asta-skill is an optional instruction layer for Ai2’s Asta MCP server. It maps requests for paper search, identifier lookup, authors, citation traversal, batch queries, or full-text snippets to appropriate tool calls with safer defaults and workflow guidance. Access still requires the Asta MCP server and an API key; the tools work without installing the skill.

Canvas MCP gives students and educators more than ninety tools for Canvas LMS, covering assignments, to-do items, course information, grades, teaching workflows, and bulk grading. Five Agent Skills package common student and educator routines. It can be installed as a Claude Desktop extension or a standard MCP server and requires the institution's Canvas API URL plus a personal access token.

Install it in a project to generate agent instructions, reusable skills, a dependency graph, and Git hooks for tools such as Claude Code, Cursor, and Gemini. The setup helps agents answer structural questions and enforces rules around commits, file headers, and complexity; in-agent skills need no separate API key, while standalone CLI features may require one.

This command-line scanner reviews third-party Claude Skills before installation for suspicious network access, sensitive file operations, dangerous commands, dynamic execution, and injection patterns. It can produce HTML, console, or JSON reports and supports custom rules and allowlists, while performing static analysis without executing the skill code. Its findings are a review aid rather than a guarantee that every security risk will be detected.

This repository packages Agnes free-model access as three independently installable skills for text, images, and video. Local Python helpers cover chat and streaming responses, image generation and transformation, and asynchronous video creation with status polling and downloads. An Agnes API key must be supplied through environment variables, while the repository deliberately excludes real credentials, generated media, and local outputs. Users can install only the capability they need.

softspark ai-toolkit distributes a broad set of skills, 44 specialist agents, lifecycle hooks, shared rules, personas, and optional plugin packs across many AI coding environments. It supports planning, debugging, review, TDD, commits, pull requests, documentation, orchestration, and parallel workflows, with adapters for Claude, Cursor, Windsurf, Gemini, Copilot, Codex, OpenCode, and others. Executable hooks can block selected destructive operations and enforce quality or session policies, although platforms without hook support receive guidance rather than equivalent machine enforcement.

agent-qa lets teams describe web and mobile tests in natural language, then re-observes the interface and tries another path when an action drifts or fails. It learns from previous runs, exposes a CLI and dashboard, supports MCP and multiple model providers, and can run setup or teardown hooks inside Docker containers. Docker is required for those hooks, and the harness remains an aid to a team's own release checks.

VitaBench evaluates agents in real-world service scenarios such as delivery, in-store operations, and OTA, using databases, API tools, and 100 tasks per domain. Configure the models, run the vita command, save simulations under data/simulations, and re-evaluate existing runs when needed. The current release updates datasets, tools, evaluator models, and metrics, so scores should be interpreted alongside the chosen configuration.

SkillX combines a web marketplace, command-line client, and semantic-plus-keyword search for discovering agent skills. Users can browse more than 500 entries, compare ratings, reviews, usage statistics, and leaderboards, and save favorites. The current MVP includes authentication, API keys, filters, and pagination, while payments, MCP server mode, and a skill execution sandbox remain future work.

Agentic Engineering Framework packages requirements clarification, system design, code generation, testing, and review as reusable commands, skills, and specialist agents. Teams can add project knowledge and coding standards, while smaller fixes can invoke only the troubleshooting, implementation, or performance workflow they need. The files are installed into supported coding-agent directories such as Claude Code or Codex CLI.

These OKX Agent Skills give Claude Code, Cursor, Codex, and other compatible clients guided workflows for market data, order placement, positions and P&L, transfers, grid bots, DCA bots, and earn products through the okx CLI. Public market queries do not require authentication, while trading, account, portfolio, and earn operations require credentials configured through OAuth or an API key.

spring-boot-skills provides parallel skill sets for Spring Boot 3 and 4, covering architecture, REST APIs, JPA, migrations, caching, transactions, security, Spring AI, MCP, batch jobs, and testing. Developers copy the relevant skills into a Claude Code or Codex project so the agent reads version-specific patterns and team conventions before changing code. These are adaptable development instructions and templates rather than a library that becomes part of the application's runtime.

Install the skill, authorize Baidu Netdisk, and ask a compatible agent to upload, download, search, transfer, or share files. Operations stay inside the app-specific storage directory, deletion is unavailable, and potentially destructive changes require confirmation. The project is still in beta and supports macOS, Linux, and Windows through WSL rather than native Windows.

make-no-mistakes packages two Cursor agent skills, a standard version and a stronger variant. Once copied or linked into the Cursor skills directory, they add behavioral instructions intended to keep model output coherent, accurate, and less prone to cascading logic errors. The project is a prompt-level steering layer rather than a standalone test runner or formal verification system, so it can encourage a more careful coding workflow but does not itself prove that output is error-free.

Readme.skill analyzes local usage records from Claude Code, Codex CLI, Kiro, Cursor, and other supported tools to create an AI-collaboration profile and a vertical SVG poster, with optional monthly or custom date-range reports. Processing is read-only and local by default, and project names, private repositories, and secret-like strings are anonymized; only the optional GitHub contribution lookup uses the network. Because conversation content may be analyzed to infer working patterns, users should still review the generated files before sharing them.

@workersio/skills gives coding agents a risk-focused workflow for finding valuable test gaps, choosing an appropriate strategy, writing tests, generating replayable workloads, and reviewing existing cases. Its keep, redo, or remove gate asks whether a test would catch a failure that matters to users or operators rather than merely increasing coverage. It is packaged for Codex and Claude Code, while the Markdown-based workflow can be adapted to other skill-aware agents.

Claude Coach uses training history, event goals, injuries, travel, and equipment constraints to create plans for marathons, triathlons, and other endurance events. Users can enter fitness data manually or connect Strava, then edit, move, and complete workouts in a browser-based plan that stores data locally. Workouts can be exported to calendars, Zwift, Garmin, or TrainerRoad formats. It requires Claude.ai or Claude Code with network-enabled Skills, and Strava access requires user-created API credentials.