Top Agent Skills

You are a data triager that answers data questions by routing them across a network of skills and agents. These questions may involve pulling data from a Snowflake warehouse, computing metrics, locating relevant tables or fields, diagnosing a metric change, or performing exploratory analysis. Your job is to determine how to answer a question and which skills and subagents to invoke.

Convex reactive backend expert: schema design, TypeScript functions, real-time subscriptions, auth, file storage, scheduling, and deployment.

Optimize content for AI Overviews, ChatGPT, Perplexity, and other AI search systems. Use when improving GEO, AI citations, llms.txt readiness, crawler accessibility, and passage-level citability.

Scan project dependencies for known vulnerabilities, generate software bills of materials, and enforce license compliance across the software supply chain. Use when the user requests dependency scanning or provides relevant inputs for this workflow.

Write compelling, persuasive marketing and sales copy using proven frameworks like AIDA, PAS, BAB, and 4Ps, with tone and voice customization, CTA optimization, and A/B variant generation. Use when the user requests copywriting or provides relevant inputs for this workflow.

Analyze datasets to answer defined questions through statistical methods, trend identification, hypothesis testing, and correlation analysis. Use when the user needs evidence-backed findings or decisions from data; use exploratory-data-analysis instead for open-ended first-pass profiling before questions are defined.

Set up webhook receivers with signature verification, idempotent event processing, retry handling, and dead letter queues for reliable event-driven integrations. Use when the user requests webhook setup or provides relevant inputs for this workflow.

Generate SQL queries from natural-language requirements using SELECT, JOIN, GROUP BY, window functions, CTEs, and subqueries. Use when the user needs a new query from a business question or schema; use query-optimization when an existing query or execution plan is slow.

Perform dynamic security testing against running web applications and APIs to discover vulnerabilities through active probing and fuzzing. Use when the user requests dynamic application security testing or provides relevant inputs for this workflow.

Define, deploy, and manage cloud infrastructure as code using tools like Terraform, Pulumi, CloudFormation, and CDK, ensuring consistency, repeatability, and version control. Use when the user requests infrastructure as code or provides relevant inputs for this workflow.

Industrial communication protocols for Zephyr RTOS. Covers Modbus RTU (serial), Modbus TCP (Ethernet/Wi-Fi), and CANopen basics. Trigger when building factory automation controllers, industrial sensors, or medical equipment interfaces.

Static human-browsable catalog of the Zephyr RTOS skill set. Skill selection is handled by the zephyr-agent-skills entry point and by zephyr-cli skills suggest; this index is a reference listing only, not a task skill.

IP networking fundamentals for Zephyr RTOS. Covers IoT protocol selection (LwM2M, CoAP, MQTT), IP stack configuration and trimming (IPv4/IPv6, UDP/TCP), and professional SDK integration as Zephyr modules using West manifests. Trigger when building cloud-connected applications, optimizing network memory usage, or integrating external cloud SDKs.

Testing and debugging for Zephyr RTOS. Covers the Ztest framework for unit and integration tests, the Twister test runner for automated HIL/SIM validation, and advanced tracing/debugging techniques (SystemView, Thread Analyzer, Stack analysis). Trigger when writing unit tests, setting up CI/CD pipelines, or analyzing system performance and latency.

Configure and use Honcho memory with Hermes -- cross-session user modeling, multi-profile peer isolation, observation config, dialectic reasoning, session summaries, and context budget enforcement. Use when setting up Honcho, troubleshooting memory, managing profiles with Honcho peers, or tuning observation, recall, and dialectic settings.

Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Hermes Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.

Scan a GitHub repository's contribution conventions and write them to a replaceable local instructions block. Use when joining, forking, or cloning a repository, when the user asks how issues, pull requests, base branches, or work branches should be handled, or when `AGENTS.local.md` / `CLAUDE.local.md` should reflect the repository's actual contribution rules.

지정한 포트에서 실행 중인 프로세스를 찾아 종료합니다.

같은 프로젝트에서 동시에 굴리고 있는 여러 tmux 세션의 상태를 한 번에 파악하고 필요한 지시를 각 세션으로 전파합니다. 세션 목록을 뽑아 pane 별로 병렬 수집·요약하고, 항상 같은 양식(상태표 + 세션 카드 + 교차 분석 + 전파 제안)으로 보고합니다. "세션 현황", "지금 어디까지 됐지", "다른 창들 뭐 하고 있어", "세션 점검", "전부 어떻게 돼가", "다른 세션에 알려줘", "전 세션에 전파", "/tmux-orchestrate" 요청에 씁니다. 워크트리라 경로가 달라도 같은 git 저장소면 한 프로젝트로 묶습니다. 새 tmux 세션을 만들거나 작업을 분배하는 일, 단일 세션 안에서의 구현 작업에는 쓰지 않습니다.

Validate, review, and compare DESIGN.md design-system files using the Google `@google/design.md` specification and CLI. Trigger this skill whenever the user asks to lint / validate / verify / check / review / diff a `DESIGN.md` (case-insensitive), mentions "design.md", "design system spec", "design tokens YAML", "WCAG contrast on tokens", or uses Korean phrases like "DESIGN.md 검증", "디자인 시스템 검사", "디자인 토큰 점검", "design.md 린트". Also fire when the user pastes a YAML front-matter block that looks like a design-token document (top-level `colors:` / `typography:` / `components:` keys) or when a DESIGN.md file appears in the workspace and the conversation turns to validating, comparing, or shipping it. Covers YAML front matter, markdown section order, token references, component property validity, WCAG contrast findings, missing primary colors or typography, orphaned tokens, and regressions between two DESIGN.md versions.

Send WhatsApp messages to other people or search/sync WhatsApp history via the wacli CLI (not for normal user chats).

腾讯云迁移平台（CMG/MSP）全流程能力。触发词：资源扫描、扫描阿里云/AWS/华为云/GCP资源、生成云资源清单、选型推荐、对标腾讯云、推荐规格、帮我推荐、给我推荐、ECS对应什么腾讯云产品、成本分析、TCO、迁移报价、询价、价格计算器、cmg-scan、cmg-recommend、cmg-tco

Deploy a single HTML document to Tencent EdgeOne Pages via mcporter with no login or API key, returning a public URL. Use when a user wants generated HTML published quickly as a live webpage.

TikTok Shop e-commerce data assistant. Search products, find trending items, analyze influencers, explore shops, track video performance, and get ad insights via ecomseer.com. Triggers: 找商品, 搜商品, 爆品, 带货, TikTok电商, 达人分析, 视频带货, 店铺分析, 广告素材, 销量榜, 跨境电商, search products, find trending, TikTok Shop, influencer analysis, shop data, ad creatives, sales ranking, e-commerce analytics, product research.

Publish HTML or Markdown to a public URL instantly with ShipPage. Use when a user wants to share, preview, host, or deploy generated pages, reports, dashboards, prototypes, docs, or product listings.

Comprehensive GLSL shader techniques for creating stunning visual effects — ray marching, SDF modeling, fluid simulation, particle systems, procedural generation, lighting, post-processing, and more.

Build, preview, and deploy websites, web apps, and APIs using Vercel, Railway, GitHub Pages, or local Canvas environments. Use when a user needs general web deployment guidance across common hosting targets.

Distill a real boss into an AI skill, or generate a boss skill from famous entrepreneur archetypes (Elon Musk, Steve Jobs, Jeff Bezos, Jensen Huang). Use when user wants boss analysis, managing-up guidance, persona extraction, or entrepreneur-style decision simulation.

腾讯云 COS 向量桶全功能管理技能。覆盖向量桶、索引、向量数据的全生命周期管理，包括创建/删除/查询向量桶、创建/管理索引、插入/查询/搜索/删除向量数据、策略管理等 16 个核心能力。Trigger phrases: vector bucket, vector index, vector search, 向量桶, 向量索引, 向量搜索, 向量存储, 插入向量, 相似度搜索, COS vector.

Publish a single self-contained HTML page to htmlcode.fun and return live URLs. Use when generated HTML needs quick public sharing, demos, reports, landing pages, or QR-share pages.

Build applications powered by GitHub Copilot using the Copilot SDK. Use when creating programmatic integrations with Copilot across Node.js/TypeScript, Python, Go, or .NET. Covers session managemen...

Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design.

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmaticall...

Jest testing framework. Covers unit tests, mocking, and snapshots. Use for testing React and Node.js projects. USE WHEN: user mentions "jest", "jest test", "snapshot test", asks about "jest.fn", "jest.mock", "toMatchSnapshot", "React testing" DO NOT USE FOR: E2E tests - use `playwright` or `cypress`; Vite projects - use `vitest` instead; React component testing alone - combine with `testing-library`

Flutter cross-platform development with Dart. Widgets, state management (Riverpod, BLoC), navigation, platform channels, and production patterns. USE WHEN: user mentions "Flutter", "Dart", "flutter widget", "Riverpod", "BLoC", "flutter build", "pubspec.yaml" DO NOT USE FOR: React Native - use `react-native`; Expo - use `expo`; native iOS/Android

Vitest testing framework. Covers unit tests, mocking, and coverage. Use for testing Vite-based and Node.js projects. USE WHEN: user mentions "vitest", "vite test", "unit test", asks about "vi.fn", "vi.mock", "test coverage", "mock functions", "test vite project" DO NOT USE FOR: E2E tests - use `playwright` instead; React component testing - combine with `testing-library`; Jest projects - use `jest` instead

Cypress E2E testing framework. Covers commands, assertions, and component testing. Use for end-to-end testing. USE WHEN: user mentions "cypress", "e2e test", "cy.get", "cy.visit", asks about "cypress intercept", "component testing", "cypress commands" DO NOT USE FOR: Unit tests - use `vitest` or `jest`; Multi-tab scenarios - Cypress doesn't support; Native mobile apps - use Appium; Performance testing - use dedicated tools

Unity XR — XR Interaction Toolkit 3.x (Interactor/Interactable/Manipulation), AR Foundation (planes, anchors, image tracking, body tracking), OpenXR, hand tracking on Quest/Vision OS. USE WHEN: VR/AR/MR projects, integrating XR controllers, AR plane detection, XR locomotion, hand tracking, eye tracking, OpenXR features. DO NOT USE FOR: regular 3D gameplay (use `unity-physics-anim`); rendering pipeline (use `unity-rendering` — XR has URP-specific considerations).

Python language (3.10-3.14). Covers typing, async, and modern patterns. Use when writing Python applications. USE WHEN: user mentions "python", "type hints", "dataclasses", "async/await", asks about "asyncio", "context managers", "match statement", "walrus operator", "PEP 695", "type parameter", "generic" DO NOT USE FOR: FastAPI framework - use `backend-fastapi` skill instead DO NOT USE FOR: Django framework - use Django-specific skill DO NOT USE FOR: Package management - use `python-packaging` skill DO NOT USE FOR: Linting/type checking config - use `python-quality` skill

Security controls for RAG. Indirect prompt-injection via retrieved documents, PII detection/redaction (Microsoft Presidio, AWS Comprehend), multi-tenant isolation, ACL-aware retrieval with row-level/metadata filtering, data-leakage prevention, jailbreak hardening on retrieved context, GDPR right-to-be-forgotten in vector DBs. USE WHEN: user mentions "prompt injection RAG", "indirect prompt injection", "PII redaction", "Presidio", "ACL RAG", "row-level security", "multi-tenant RAG isolation", "GDPR vector DB", "right to be forgotten", "jailbreak", "data leakage RAG" DO NOT USE FOR: hallucination detection - use `rag-guardrails`; tenancy scaling patterns - use `rag-production`; audit tracing schema - use `rag-observability`

Pre-meeting research and talking points generator. Researches the person and company, pulls CRM history, and generates a structured briefing with agenda, talking points, objection handlers, and recommended asks.

Define and refine ICP segments with persona cards and validation

Full website audit for ICP alignment, messaging clarity, conversion optimization, and trust signals

Extract brand visual system from a website or brand assets into a structured style guide

Full daily team standup across all 6 verticals: Sales, Social Media, Content, SEO, Creative, and Strategy. Spawns all vertical agents in parallel, collects reports, and presents a unified standup summary. Run at 9 AM daily.

Monitor social platforms and forums for brand mentions, category discussions, and competitor activity

Search the web for companies showing buying signals matching the agency ICP. Enforces 75/25 geo split and 20 gig + 5 company daily targets.

Builds drip email campaigns for leads not ready to buy. Determines segment and buying stage, selects content per stage, and generates a complete 5-7 email sequence over 30 days with timing and content.

Analyze conversion funnel drop-offs and identify biggest leak points with impact-ranked recommendations

Extract warm prospects from competitor and industry post engagers across LinkedIn, Twitter, and blogs

Repurpose one piece of content across six formats while maintaining brand voice

Generate conversion-focused landing page copy section by section using proven frameworks

Reallocate ad budget across campaigns and channels using ROAS and marginal return analysis

Transform raw transcripts, notes, or topics into polished long-form articles in the founder's voice

Research top-performing LinkedIn content in your niche and generate a content playbook

Generate structured call scripts by persona and lead context

Outreach triggered by funding events with post-funding needs analysis and personalized drafts

Generates contextual replies to comments, mentions, and DMs on social posts. Classifies engagement as lead signal, customer question, partnership opportunity, or troll/spam. Uses brand voice from agency.config.json.

Working Backwards PRFAQ challenge to forge product concepts. Use when the user requests to 'create a PRFAQ', 'work backwards', or 'run the PRFAQ challenge'.

Product manager for PRD creation and requirements discovery. Use when the user asks to talk to John or requests the product manager.