Top Agent Skills

Plan backend domains, services, jobs, integrations, and failure handling for a product or major feature. Use when UX and product scope are defined and the team needs a production-minded backend design without defaulting to premature microservices.

Evaluate a raw app, startup, SaaS, internal tool, marketplace, or AI product idea before planning features. Use when the user shares a vague concept and needs pain analysis, market realism, feasibility, differentiation, risks, or a build/no-build recommendation.

Plan screens, views, and page responsibilities for a product flow. Use when user journeys already exist and the team needs a screen inventory, screen purpose, key states, and component-level responsibilities without jumping into visual styling too early.

Use this when reviewing whether an app, service, worker, CLI, or serverless system is ready for its target environment with respect to config, secrets, migrations, dependencies, observability, rollback, and runtime constraints.

Use when context window is filling up, sessions are getting slow, or you need to preserve state across sessions. For context compression, state snapshots, search-first discipline, and cross-session memory management.

Use when creating React/TypeScript components, pages, or features. For modern patterns including Suspense, useSuspenseQuery, lazy loading, MUI v7 styling, TanStack Router, and performance optimization.

Use when the user wants to create a new Antigravity skill pack or add a focused skill folder with SKILL.md, references, examples, or scripts. Trigger on requests to generate a skill, scaffold a skill, or expand the local skill library.

Use this when reviewing or designing Firebase security rules for Firestore or related client-accessed Firebase data. Trigger on requests about Firebase rules safety, access constraints, auth-claim checks, or client data exposure.

Use this skill when the user is working with Supabase and needs help with Edge Functions, SQL schema or migrations, Auth, Row Level Security, database functions, local CLI workflows, or deployment. Use it for building features, reviewing Supabase code, creating migrations, writing policies, implementing auth-aware server logic, and debugging full Supabase app flows.

Use this when a Supabase app needs file or object storage design, bucket strategy, signed URL handling, metadata patterns, upload trust boundaries, or storage access controls.

Use when the team needs pricing, packaging, free-tier, trial, usage metering, or business-model guidance for a software product. Trigger on requests to design how the product should make money or control value access.

Plan the frontend application structure for a product or feature. Use when the team needs route structure, feature modules, state boundaries, design-system needs, and frontend delivery sequencing based on defined screens and flows.

Review whether a product, MVP, or feature is actually ready to launch. Use when the team needs a production-minded check across product quality, UX edge cases, auth and security, observability, support readiness, pricing readiness, and post-launch measurement.

Write an implementation plan from an approved architecture and MVP scope. Use when the team needs milestones, workstreams, dependency ordering, acceptance criteria, and execution sequencing that connect product intent to shippable engineering work.

Extract the core product philosophy, strategic posture, and design principles from a raw concept or founder brief. Use when the team needs a crisp product promise, guiding principles, product point of view, or a philosophy statement before scope and UX planning.

Design pricing, packaging, and monetization strategy for a software or AI product. Use when the team needs plan structure, free-tier logic, usage vs seat pricing tradeoffs, paywall timing, or monetization guardrails tied to product value and costs.

Use this skill for code review and PR review tasks. Covers review methodology, what to flag, what to skip, and output structure.

Use this skill to write and run SQL queries, pull data, build metrics, or answer analytical questions. Always use this skill when you need to query data.

Use this skill for any data or analytics task — querying databases, analyzing metrics, exploring data warehouses, processing datasets, or creating visualizations.

Creates a git commit and pushes to remote. Use -a to amend. Optionally accepts a commit message.

Use this skill for any coding task that involves working with repositories, writing code, creating branches, or opening pull requests. Covers the full development workflow from cloning to PR.

Expert jq usage for JSON querying, filtering, transformation, and pipeline integration. Practical patterns for real shell workflows.

Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infrastructure security for any project.

Fetch any X/Twitter post as clean LLM-friendly JSON. Converts x.com, twitter.com, or adhx.com links into structured data with full article content, author info, and engagement metrics. No scraping or browser required.

Cirq is Google Quantum AI's open-source framework for designing, simulating, and running quantum circuits on quantum computers and simulators.

Build ultra-fast web APIs and full-stack apps with Hono — runs on Cloudflare Workers, Deno, Bun, Node.js, and any WinterCG-compatible runtime.

Convert human-written CLAUDE.md into AI-native structured-label format. Battle-tested across 4 models. Same rules, fewer tokens, higher compliance.

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

Build content-focused websites with Astro — zero JS by default, islands architecture, multi-framework components, and Markdown/MDX support.

Documentation and capabilities reference for Daily

Unified Diary System: A context-preserving automated logger for multi-project development.

Connect to MAXIA AI-to-AI marketplace on Solana. Discover, buy, sell AI services. Earn USDC. 13 MCP tools, A2A protocol, DeFi yields, sentiment analysis, rug detection.

Vector-powered CLI for semantic file search with a Claude/Codex skill

Optimize content for AI search and LLM citations across AI Overviews, ChatGPT, Perplexity, Claude, Gemini, and similar systems. Use when improving AI visibility, answer engine optimization, or citation readiness.

ALWAYS use this skill when committing code changes — never commit directly without it. Creates commits following Sentry conventions with proper conventional commit format and issue references. Trigger on any commit, git commit, save changes, or commit message task.

Use the `gh` CLI for issues, pull requests, Actions runs, and GitHub API queries.

Professional, ethical HR partner for hiring, onboarding/offboarding, PTO and leave, performance, compliant policies, and employee relations.

AI image generation skill powered by Google Gemini, enabling seamless visual content creation for UI placeholders, documentation, and design assets.

Guide for continuous improvement, error proofing, and standardization. Use this skill when the user wants to improve code quality, refactor, or discuss process improvements.

Interactive visualization library. Use when you need hover info, zoom, pan, or web-embeddable charts. Best for dashboards, exploratory analysis, and presentations. For static publication figures use matplotlib or scientific-visualization.

Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1-100GB datasets, ETL pipelines, faster pandas replacement. For larger-than-RAM data use dask or vaex.

Clinically informed wisdom companion blending psychology and philosophy into a structured thinking partner

Scanpy is a scalable Python toolkit for analyzing single-cell RNA-seq data, built on AnnData. Apply this skill for complete single-cell workflows including quality control, normalization, dimensionality reduction, clustering, marker gene identification, visualization, and trajectory analysis.

---

6-layer AI governance: safety gates, evidence-based debugging, anti-slack detection, and machine-enforced hooks. Makes AI safe, thorough, and honest.

Expert C4 Code-level documentation specialist. Analyzes code directories to create comprehensive C4 code-level documentation including function signatures, arguments, dependencies, and code structure.

Write idiomatic C++ code with modern features, RAII, smart pointers, and STL algorithms. Handles templates, move semantics, and performance optimization.

Generate favicons from a source image

Five-phase pipeline (triage → clarify → research → PRD → plan) that turns a raw idea into four linked files: clarifying questions, deep research, a PRD with non-goals and metrics, and a phased execution plan with mermaid user journey and kill criteria.

Inngest expert for serverless-first background jobs, event-driven workflows, and durable execution without managing queues or workers.

Algorithm-first discipline: state Big-O, data structure, and algorithm family BEFORE writing loops, queries, or recursion. Catches O(n^2), N+1, and brute-force defaults.

CRITICAL: Use for MolyKit AI chat toolkit. Triggers on: BotClient, OpenAI, SSE streaming, AI chat, molykit, PlatformSend, spawn(), ThreadToken, cross-platform async, Chat widget, Messages, PromptInput, Avatar, LLM

Write idiomatic PHP code with generators, iterators, SPL data structures, and modern OOP features. Use PROACTIVELY for high-performance PHP applications.

Seaborn is a Python visualization library for creating publication-quality statistical graphics. Use this skill for dataset-oriented plotting, multivariate analysis, automatic statistical estimation, and complex multi-panel figures with minimal code.

Audit a StyleSeed-based component or page for WCAG 2.2 AA issues and apply practical accessibility fixes where the code makes them safe.

Scaffold a new mobile-first page using StyleSeed Toss layout patterns, section rhythm, and existing shell components.

Generate UX microcopy in StyleSeed's Toss-inspired voice for buttons, empty states, errors, toasts, confirmations, and form guidance.

Video and audio perception, indexing, and editing. Ingest files/URLs/live streams, build visual/spoken indexes, search with timestamps, edit timelines, add overlays/subtitles, generate media, and create real-time alerts.

Answer repository questions grounded entirely in source code evidence. Use when user asks a question about the codebase, user wants to understand a specific file, function, or component, or user asks "how does X work" or "where is Y defined".

Master of defensive Bash scripting for production automation, CI/CD pipelines, and system utilities. Expert in safe, portable, and testable shell scripts.