agent-evaluation
Design and implement comprehensive evaluation systems for AI agents. Use when building evals for coding agents, conversational agents, research agents, or computer-use agents. Covers grader types, benchmarks, 8-step roadmap, and production integration.
agentic-development-principles
Universal principles for agentic development when collaborating with AI agents. Defines divide-and-conquer, context management, abstraction level selection, and an automation philosophy. Applicable to all AI coding tools.
agent-email-cli
Operate the agent-email CLI to create disposable inboxes, poll for new mail, retrieve full message details, and manage local mailbox profiles. Use when the user needs terminal-based email inbox access for LLM or agent automation workflows.
ab-test-setup
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," or "how long should I run this test." Use this whenever someone is comparing two approaches and wants to measure which performs better. For tracking implementation, see analytics-tracking. For page-level conversion optimization, see page-cro.
agentic-workflow
Practical AI agent workflows and productivity techniques. Provides optimized patterns for daily development tasks such as commands, shortcuts, Git integration, MCP usage, and session management.
agent-tools
Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok
Agent Browser
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
agent-browser
Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video
refine-plan
Refines an existing implementation plan through discussion with the user. Takes a GitHub issue number. Use when the user wants to refine a plan, discuss a plan, change a plan, or says "refine plan X" or "let's discuss the plan for issue #Y".
worktree
Manages git worktrees for parallel development. Creates isolated working directories for tickets/branches, lists active worktrees, and cleans up after merging. Use when starting work on a ticket or cleaning up completed work.
review-pr
Review a pull request using Google's code review principles. Takes a PR number or auto-detects from current branch. Use when the user wants to review a PR, check PR changes, or says "/review-pr 123".
review-codebase
Review overall codebase health, architecture, and patterns using Google's engineering principles. Takes optional focus area. Use when the user wants to review code quality, assess architecture, or says "/review-codebase" or "/review-codebase 'API layer'".
setup-python-lib
Sets up a new Python library project using uv in the current directory. Creates project structure, installs dev dependencies, and optionally configures git remote. Use when the user wants to initialise a Python library, package, or project with uv.
setup-django
Sets up a new Django project with RAPID architecture using uv. Creates horizontal layer structure with DRF, Docker/PostgreSQL support, and environment-based configuration. Use when the user wants to initialise a Django web application.
codebase-map
Generate a structural overview and dependency diagram of the codebase. Use when the user wants to understand codebase structure, visualise architecture, or says "/codebase-map".
create-ticket
Creates GitHub issues to capture work that needs to be done. Records intent with context about the codebase, not implementation plans. Use when the user wants to track work, create a ticket, log a task, or says "we want to do X" or "we need to X".
plan-ticket
Creates an implementation plan for an existing GitHub issue and adds it as a comment. Takes a GitHub issue number. Use when the user wants to plan a ticket, plan an issue, or says "plan ticket X" or "how should we implement issue #Y".
implement-ticket
Implements a planned GitHub issue by following the implementation plan. Takes a GitHub issue number. Use when the user wants to implement a ticket, work on an issue, or says "implement ticket X" or "do issue #Y".
edit-and-commit
IMPORTANT - Use this skill proactively whenever you need to edit files and commit changes. Automatically runs roborev pre-commit review and creates atomic commits. Use this instead of Edit+Bash for git operations. Required for all file modifications that should be committed.
address-pr-comments
Addresses PR review comments by making code changes and posting replies. Takes a PR number or auto-detects from current branch. Use when the user wants to address review feedback, respond to PR comments, fix PR feedback, or says "address comments on PR X".
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
prd-writer
>
hotfix
>
diario-sesion
>
spec-writer
>
sdd-protocol
>
airflow-debugging
>
mozilla-query-writing
>
mozilla-probe-discovery
>
skillsmp-search
Search and discover AI skills from the SkillsMP marketplace using keyword search or AI-powered semantic search. Use this skill when users want to find specific skills, explore available capabilities, or search for solutions to particular problems using natural language queries.
gpt-image-1-5
Generate and edit images using OpenAI's GPT Image 1.5 model. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports text-to-image generation and image editing with optional mask. DO NOT read the image file first - use this skill directly with the --input-image parameter.
feature-plan
Creates phase-based feature plans with quality gates and incremental delivery structure. Use when planning features, organizing work, breaking down tasks, creating roadmaps, or structuring development strategy. Keywords: plan, planning, phases, breakdown, strategy, roadmap, organize, structure, outline.
landing-page-guide-v2
Create distinctive, high-converting landing pages that combine proven conversion elements with exceptional design quality. Build beautiful, memorable landing pages using Next.js 14+ and ShadCN UI that avoid generic AI aesthetics while following the 11 essential elements framework.
nano-banana-pro
Generate images using Google's Nano Banana Pro (gemini-3-pro-image-preview). Use when user asks to create, generate, or draw images, infographics, visualizations, diagrams, charts, illustrations, or any visual content. Excellent for data-accurate infographics and text rendering.
ga4-event-tracking
Add, review, or update GA4 event tracking on HTML websites using data attributes and a reusable JavaScript tracker. Use when wiring gtag or GTM dataLayer events, choosing event names/parameters, or extending a base GA4 tracking snippet for clicks and simple interactions.
taskwarrior
Track work items using Taskwarrior. Use when managing tasks, tracking PRs, or organizing work. Always use UUID instead of task ID.
oracle
Run long AI queries with Oracle CLI. Use for code reviews, summarization, or analysis that takes time. Always run in tmux.
zrok
Share local services publicly or privately via secure tunnels. Use when needing to expose localhost ports, share dev servers, create public URLs for local services, or set up secure tunnels between machines.
ts-library
Use when authoring TypeScript libraries or npm packages - covers project setup, package.json exports, build tooling (tsdown/unbuild), API design patterns, type inference tricks, testing, and publishing to npm. Use when bundling, configuring dual CJS/ESM output, or setting up release workflows.
writer
Iterative writing loop. Gemini 3 Pro writes, Claude Agent SDK reviews autonomously. Use for blog posts, docs, technical content needing quality iteration.
write-a-prd
Conversational PRD writer - interview, scope, write, then create Linear/GitHub issue. Use when planning a new feature or product requirement.
web-animation-design
Design and implement web animations that feel natural and purposeful. Use this skill proactively whenever the user asks questions about animations, motion, easing, timing, duration, springs, transitions, or animation performance. This includes questions about how to animate specific UI elements, which easing to use, animation best practices, or accessibility considerations for motion. Triggers on: easing, ease-out, ease-in, ease-in-out, cubic-bezier, bounce, spring physics, keyframes, transform, opacity, fade, slide, scale, hover effects, microinteractions, Framer Motion, React Spring, GSAP, CSS transitions, entrance/exit animations, page transitions, stagger, will-change, GPU acceleration, prefers-reduced-motion, modal/dropdown/tooltip/popover/drawer animations, gesture animations, drag interactions, button press feel, feels janky, make it smooth.
vueuse
Use when working with VueUse composables - track mouse position with useMouse, manage localStorage with useStorage, detect network status with useNetwork, debounce values with refDebounced, and access browser APIs reactively. Check VueUse before writing custom composables - most patterns already implemented.
vue
Use when editing .vue files, creating Vue 3 components, writing composables, or testing Vue code - provides Composition API patterns, props/emits best practices, VueUse integration, and reactive destructuring guidance
vitest
Use when writing unit/integration tests for Vite projects - provides Vitest configuration, test APIs, mocking patterns, and coverage setup
vite
Use when setting up Vite projects - provides dev server, HMR, build configuration, library mode, and plugin authoring patterns
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends an agent's capabilities with specialized knowledge, workflows, or tool integrations.
unslop
Remove AI-generated "slop" from codebases by deleting redundant comments and unused code, tightening formatting, and normalizing styling patterns (e.g., Tailwind class consistency, Nuxt UI color tokens). Use when a user asks to clean up code, remove unnecessary comments, reduce unused imports/variables, or align Tailwind/Nuxt UI conventions.
todoist
Todoist CLI (sachaos/todoist). Use when user mentions: todoist, tasks, todos, adding/listing/completing tasks, creating projects, filtering by date/priority/label, natural language task entry, recurring tasks, or task management workflows.
tsdown
Use when bundling TypeScript libraries - provides tsdown configuration, dual ESM/CJS output, .d.ts generation, and plugin authoring
Page 1517 of 1561 · 78017 results
