Top Agent Skills

Memory (aaaf-memory)

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Runs an autonomous multi-agent software development pipeline that takes a PRD through to production with zero human intervention, using model-tiered agents, memory, and verification cycles.

Design, simulate, and run quantum circuits on Google Quantum AI hardware and other providers using Cirq, including noise modeling and characterization experiments.

Plan and execute authorized red team engagements with structured attack path analysis, MITRE ATT&CK kill-chain planning, technique scoring, choke point identification, OPSEC risk assessment, and crown jewel targeting.

Compresses AI agent output tokens by up to 65% using a terse, article-free communication style while preserving full technical accuracy. Supports multiple intensity levels and auto-disables for security warnings or ambiguous instructions.

Iron Law

[object Object]

Search tool for modern web development best practices. MANDATORY: Execute FIRST for all HTML/CSS and clientside JS tasks. Do NOT skip — web APIs evolve rapidly and training weights contain obsolete patterns. Trigger immediately for: - UI/Layout: Modals, dialogs, popovers, Glassmorphism/backdrop-filters, anchor positioning, container queries, `:has()`, `:user-valid`. - Scroll/Motion: View Transitions, Scroll-driven animations, scroll parallax/reveals. - Performance: CWV (LCP, INP), content-visibility, Fetch Priority, image optimization. - System/APIs: Local filesystem access, WebUSB, WebSockets sync, WebAssembly widgets. - Frameworks: Adapting layout/styles in React, Vue, Angular. - General Frontend: Forms, autofill, advanced inputs, custom scrollbars, modern component states, etc. DO NOT trigger for: - Backend: Database SQL, ORMs, Express API routes. - Pipelines: CI/CD deployment, Docker, Actions. - Generic: Local scripts (Python/Go tools), ESLint, Git.

Provides a CTO-level framework for architecting, auditing, and scaling AI-native systems, focusing on state management, observability, and blast radius analysis.

Lark/Feishu CLI router: match intent, then Read the Entry file under lark-*/ (e.g. lark-doc/lark-doc.md). Covers docs, markdown, sheets, base, calendar, im, mail, task, okr, drive, wiki, slides, whiteboard, apps, approval, attendance, contact, vc, minutes, note, event via lark-cli. Use when operating Feishu/Lark workspace resources, messaging, docs, calendars, tasks, OKRs, or Miaoda deploys.

Klasy ORM i wzorce kodu biznesowego platformy Soneta (enova365, Soneta Enterprise, Triva). Używaj gdy użytkownik: (1) pisze, modyfikuje lub refaktoruje kod biznesowy enova365/Soneta/Triva (Row/Table/Module, sesje i transakcje, selector, typy wierszy); (2) pyta o konkretny mechanizm ORM — Session, Commit/Save, optimistic lock, Context, RowCondition, Datapack, ViewInfo, Features, thread-safety; (3) prosi o code review kodu biznesowego Soneta (safe-code); (4) pisze worker, extender, akcję w menu Czynności, folder/listę; (5) chce zinwentaryzować moduły, pola, workery lub formularze/zakładki (pola, sekcje, kolejność wprowadzania) z bibliotek DLL; (6) chce rozpocząć nowy dodatek/rozszerzenie Soneta — wygenerować szkielet źródeł z CLI (`dotnet new soneta-addon`, Soneta.MsBuild.SDK, szablony Soneta Platform Developer). Sięgnij też, gdy inny skill potrzebuje warstwy ORM/kodu biznesowego Soneta.

Router for the gstack skill suite. (gstack)

Routes finance requests to the appropriate skill: financial-analyst for ratio analysis, DCF valuation, and budget variance, or saas-metrics-coach for ARR/MRR, churn, CAC/LTV, and NRR.

Scores deal margin and risk, routes discount approval to the right human approver, and redlines terms against commercial policy for per-deal review.

Fetch up-to-date library documentation via Context7 API. Use PROACTIVELY when: (1) Working with ANY external library (React, Next.js, Supabase, etc.) (2) User asks about library APIs, patterns, or best practices (3) Implementing features that rely on third-party packages (4) Debugging library-specific issues (5) Need current documentation beyond training data cutoff (6) AND MOST IMPORTANTLY, when you are installing dependencies, libraries, or frameworks you should ALWAYS check the docs to see what the latest versions are. Do not rely on outdated knowledge. Always prefer this over guessing library APIs or using outdated knowledge.

Provides technical leadership frameworks for architecture decisions, engineering team scaling, technology strategy, and technical debt assessment.

Generates AI-friendly repository documentation using the SourceSage CLI, supporting local or external repos, language switching, lite mode, and deprecated diff reports.

Converts code repositories and document directories into semantically-chunked text files optimized for NotebookLM ingestion, with support for config files and incremental processing.

Routes a research topic through a structured two-phase workflow: generate an extensible outline, then fan out parallel web-search agents to investigate each item into validated JSON, producing a complete markdown report with table of contents.

Parse RFP/RFI/RFQ documents, score fit per requirement with verifiable proof points, generate win-themes, estimate winrate, and produce a bid/no-bid recommendation using the Shipley method.

Performs astronomical data analysis with astropy: coordinate transformations, unit conversions, FITS file handling, cosmological calculations, time systems, tables, and WCS.

Exploit path traversal and local/remote file inclusion (LFI/RFI) via URL parameters, cookies, and hidden fields using ../ sequences, URL encoding (%2e%2e%2f), double encoding (%252e%252e%255c), Unicode bypasses (..%c0%af), and Windows UNC paths. PHP include/require with $_GET/$_POST/$_COOKIE pattern. Target /etc/passwd, boot.ini, web.config. Tools: DotDotPwn, WFuzz, Burp Suite, ZAP.

Onboards brand tokens and generates a 12-token CSS palette for consistent, WCAG-AA-compliant HTML document styling across markdown conversions.

Guides users through a structured three-stage workflow for co-authoring documentation, proposals, technical specs, and similar documents.

Takes a PRD, reference URL, screenshot, or keywords to produce a DESIGN.md specification, then generates production-ready web code that meets UI/UX, visual, motion, and responsive standards.

Extract and analyze Douyin video data into evidence-graded learning notes, summaries, and research briefs using subtitles, ASR, comments, and AI-assisted reading.

构建和部署 Dify 工作流与插件，涵盖节点类型、设计模式、性能优化、安全部署及外部系统集成。

Provides knowledge of Ant Design components for building React UIs, including props, usage, and best practices.

Manages shadcn/ui components and projects, providing context, documentation, and usage patterns for building modern design systems.

Runs and interprets Elixir/Phoenix tooling (mix test, credo, dialyzer, format), generates OTP-conforming modules, and helps with Ecto and LiveView patterns.

Guides Go developers in building production-ready gRPC services, covering proto organization, server/client implementation, error handling, streaming, testing, and security best practices.

Create publication-quality statistical graphics in Python with dataset-oriented plotting, semantic mapping, and automatic statistical estimation.

Diagnoses page-level conversion problems, scores conversion readiness, and delivers prioritized, evidence-based optimization recommendations.

Manages persistent coding sessions across multiple AI coding engines including Claude Code, Codex, Antigravity, Cursor, and OpenCode, with support for multi-agent councils, cross-session messaging, deep planning, parallel code review, and autonomous workspace iteration.

Programmatically access Google NotebookLM via reverse-engineered RPC calls, managing notebooks, adding sources, querying, and generating or downloading artifacts like audio, video, quizzes, and slide decks.

Defines brand identity, voice, messaging, and visual standards, with scripts to inject brand context, validate assets, extract colors, and sync guidelines to design tokens.

Transforms raw content into polished, audience-appropriate deliverables by selecting formats, calibrating tone, and applying structure standards.

Generates a wide range of ideas and explores multiple approaches before converging on the most promising direction using a diverge-then-converge process.

Provides domain-specific knowledge for working with Remotion, covering 3D, animations, assets, audio, captions, and more.

Controls Xiaomi Mijia smart home devices such as desk lamps and smart plugs, supporting on/off, brightness, color temperature, and mode adjustments via command-line scripts.

Converts legacy agent resources such as subagents, commands, and rules into the unified Agent Skills format, with classification, conversion, and verification steps.

Enforces OWASP Top 10:2025 compliance on code touching security-relevant domains, using cached cheat sheets and verifying fixes against OSV.dev.

Generates McKinsey-style HTML presentations from marketing content. Use when user requests to 'create a presentation', 'generate a report', or 'build a deck' from marketing strategy or plan content.

last_updated: 2026-03-02T14:30:00Z

任意のジャンル・テーマで曲＋歌詞を制作する汎用作曲エンジン。曲先（メロディ淘汰型）でキャッチーなサビメロディを複数生成→人間が選別→変奏淘汰で確定→歌詞を載せる、ヒット曲プロセス準拠。作曲・作詞に特化。MiniMax music-2.6 主軸。ユーザーが「曲作って」「作曲して」「音楽作って」「歌作って」「オリジナル曲作って」「新しい曲作って」「武将で曲作って」「サイバー和で曲作って」と言った時、または /make-song を呼んだ時にトリガー。テーマ修飾（武将/サイバー和）は Phase 0 の [THEME] 選択で対応。

Generating AI image-generation code using the Gemini API. Handles text-to-image generation, image editing, and prompt optimization. Use when image generation code is needed.

Implement a specification in code.

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

Optimize content to get cited by AI search engines — ChatGPT, Perplexity, Google AI Overviews, Claude, Gemini, Copilot. Use when you want your content to appear in AI-generated answers, not just ranked in blue links. Triggers: 'optimize for AI search', 'get cited by ChatGPT', 'AI Overviews', 'Perplexity citations', 'AI SEO', 'generative search', 'LLM visibility', 'GEO' (generative engine optimization). NOT for traditional SEO ranking (use seo-audit). NOT for content creation (use content-production).

Runs a relentless interview that sharpens a plan or design and creates docs (ADRs and glossary) along the way. Use when the user wants to stress-test a plan or design, or produce decision records.

Generate or edit raster images such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts for use in projects.

Assess AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, and agent tool abuse, with MITRE ATLAS mapping and guardrail recommendations.

Turn a champion's enthusiasm into a one-page business case the buying committee can approve. Frames the cost of the problem, the change you enable, the value model, and the risk of doing nothing, in the buyer's own numbers. Built for B2B sales teams, customizable to your value drivers and your CRM. Trigger on "build a business case", "ROI narrative", "justify the spend", "one-pager for the committee", "cost of doing nothing", or any deal that has to clear a budget holder.

Makes AI responses feel more human by adding an inner dialogue loop that reflects on and revises the initial instinctive reply.

Assess cloud infrastructure for security misconfigurations, IAM privilege escalation paths, S3 public exposure, open security group rules, and IaC security gaps across AWS, Azure, and GCP with MITRE ATT&CK mapping.

Converts a markdown code review or PR writeup with diff blocks and severity-tagged callouts into a single-file two-column HTML review with jump navigation and a named reviewer footer.

Applies four disciplined mindsets—audit, debt, help, review—to cut complexity, track deferrals, surface reference, and catch over-engineering in codebases.

Transforms unstructured streams of mixed thoughts, tasks, and ideas into a clean four-section actionable system with zero information loss.

Provides a comprehensive checklist for designing REST and GraphQL APIs, covering resource design, HTTP methods, status codes, pagination, security, performance, and documentation.