All Skills
(19,001)Browse all AI agent skills for Claude Code, OpenClaw, Cursor, Windsurf, and more. Install them with a single command to extend what your agents can do.
next
brsbl/ottonomous
Pick or implement the next task or session. Use when continuing work, picking the next task, or implementing tasks from a task list.
authentication-patterns
athola/claude-night-market
'Authentication patterns for external services: API keys, OAuth, token
accessible-dev
deepakkamboj/claude-marketplace
A development assistant that enforces accessibility-first coding practices during code generation. Use this skill when writing new UI components, features, or interfaces to ensure WCAG 2.1 Level AA compliance from the start.\\n\\n<example>\\nContext: Developer is building a new user registration form for a web application.\\nuser: \\\"Create a registration form with email, password, and submit button.\\\"\\nassistant: \\\"I'll create an accessible registration form using semantic HTML, proper label associations, keyboard operability, and WCAG AA compliant structure.\\\"\\n<commentary>\\nThe accessible-dev skill generates accessible code by default. It uses semantic HTML elements, associates labels with form inputs, ensures keyboard navigation works, and follows WCAG 2.1 AA standards without requiring explicit accessibility requests.\\n</commentary>\\n</example>\\n\\n<example>\\nContext: Developer needs to add a modal dialog to display user settings.\\nuser: \\\"Add a settings modal that opens when clicking the gear icon.\\\"\\nassistant: \\\"I'll create an accessible modal with proper focus management, keyboard trapping, ARIA attributes, and an accessible close button. The modal will trap focus while open and return focus to the trigger button when closed.\\\"\\n<commentary>\\nAccessible-dev automatically applies accessibility best practices for complex UI patterns like modals, including focus management, keyboard interactions (Escape to close, Tab to navigate), and proper ARIA roles and states.\\n</commentary>\\n</example>\\n\\n<example>\\nContext: Developer has just completed building a dashboard component.\\nassistant: \\\"I've completed the dashboard component with accessible navigation, semantic landmarks, and keyboard shortcuts. Would you like me to run a comprehensive accessibility review using the accessibility-tester agent?\\\"\\n<commentary>\\nAfter completing a feature or component, accessible-dev proactively suggests running a comprehensive accessibility audit. This hybrid approach ensures code is accessible during generation and verified after completion.\\n</commentary>\\n</example>
tsqlapp-developer
rhodelta66/tsqlapp-skills
Generate production-ready T-SQL scripts for the TSQL.APP framework. Use when creating TSQL.APP action scripts, modal forms, data processing scripts, or any T-SQL code that runs within the TSQL.APP environment. This skill enforces 11 critical mandated practices and ensures procedure verification against the authoritative CSV catalog.
code-audit
speson/not-my-reforge
Multi-perspective code audit. Launches parallel security, quality, performance, and architecture analysis agents.
options-trading
marketcalls/openalgo-claude-plugin
Options trading with OpenAlgo - single leg orders, multi-leg strategies (Iron Condor, Straddle, Strangle, Spreads), options chain analysis, and Greeks calculation
portfolio
marketcalls/openalgo-claude-plugin
Portfolio management with OpenAlgo - funds, positions, holdings, order book, trade book, margin calculator, and account management
market-data
marketcalls/openalgo-claude-plugin
Market data retrieval with OpenAlgo - real-time quotes, historical OHLCV, market depth, option chains, WebSocket streaming, and symbol search
gemini-peer-review
slb350/gemini-peer-review
This skill should be invoked BEFORE presenting implementation plans, architecture recommendations, code review findings, or answers to broad technical questions. Use proactively when about to "recommend", "suggest", "propose", "design", "plan", or answer "how should", "what's the best way", "which approach". MANDATORY for multi-file changes, refactoring proposals, and security-sensitive recommendations.
Full Cycle
ConaryLabs/Mira
<!-- plugin/skills/full-cycle/SKILL.md --> --- name: full-cycle description: This skill should be used when the user asks for a "full review and fix", "find and fix issues", "review and implement", "end-to-end review", "audit and fix", "comprehensive review", "full-cycle review", or wants experts to
spec-writing
athola/claude-night-market
'Create clear, testable specifications with user stories and acceptance
checkpoint
synaptiai/agent-capability-standard
Create a safety checkpoint marker before mutation or execution steps. Use when about to modify files, execute plans, or perform any irreversible action. Essential for the CAVR pattern.
gap-analysis-workflow
synaptiai/agent-capability-standard
Identify capability gaps and propose new skills with prioritization. Use when analyzing missing capabilities, planning skill development, performing ontology expansion, or assessing coverage.
tensorslab-video
bob5-tensorslab/skills
Generate videos using TensorsLab's AI video generation models. Supports text-to-video and image-to-video generation with automatic prompt enhancement, progress tracking, and local file saving. Use for generating videos from text descriptions, animating static images, creating cinematic content, and various aspect ratios. Requires TENSORSLAB_API_KEY environment variable. Video generation takes several minutes.
Logic Ingest
NewJerseyStyle/plugin-logic-llm
# /logic-ingest Batch ingest documents into the symbolic knowledge base with automatic incremental updates. ## Description This skill processes entire directories of documents, converting them to logic programs and maintaining a coherent, non-redundant knowledge base. It handles incremental updat
debug-workflow
synaptiai/agent-capability-standard
Execute the Debug Code Change workflow end-to-end with safety gates. Use when debugging code changes, investigating issues, or performing root cause analysis with audit trail.
trading-core
marketcalls/openalgo-claude-plugin
Core trading operations with OpenAlgo - place orders, smart orders, basket orders, split orders, and order management across 25+ Indian brokers
generate
synaptiai/agent-capability-standard
Create a new artifact (text, code, plan, data) under specified constraints. Use when producing content, writing code, designing solutions, or synthesizing outputs.
Logic Query
NewJerseyStyle/plugin-logic-llm
# /logic-query Query symbolic knowledge bases using natural language or formal logic syntax. ## Description This skill enables querying knowledge bases that have been created through `/logic-convert` or manually. It translates natural language questions into formal queries and returns human-reada
Logic Register
NewJerseyStyle/plugin-logic-llm
# /logic-register Register and manage predicates, facts, and rules in the logic knowledge registry. ## Description This skill manages the central registry that tracks all predicates, facts, and rules across the knowledge base. It ensures naming consistency, prevents duplicates, and enables code r
otto
brsbl/ottonomous
Autonomous product development. Takes an idea and builds it end-to-end with subagents. Write a product spec, generate tasks from spec, implement each task while testing/reviewing changes, with final verification. Use when you want to build something from scratch.
detect
synaptiai/agent-capability-standard
Determine whether a specific pattern, entity, or condition exists in the given data. Use when searching for patterns, checking existence, validating presence, or finding signals.
Next Item
rjroy/vibe-garden
--- name: next-item description: This skill should be used when the user asks "what should I work on", "next item", "highest priority", "what's ready", or invokes /compass-rose:next-item. Recommends the highest-priority ready item with rationale. allowed-tools: Skill(compass-rose:gh-api-scripts),
Gh Api Scripts
rjroy/vibe-garden
# GitHub API Scripts Skill ## Overview This skill provides Python scripts for reliable GitHub Project API operations. It replaces embedded GraphQL guidance in command markdown files with tested, reusable abstractions. ## Configuration Operations require a configuration file at `.compass-rose/con