AI Ml AI Skills

Initialize and configure the Operator User Partition.

专业评估故事大纲，从市场潜力、创新属性、内容亮点维度判断评分。适用于故事大纲质量评估、IP改编潜力判断、项目立项决策

梳理人物生平、关键事件与时间节点，制作带人物照片的生平时间线或人物志海报。适用于传记梳理、人物专题与历史人物介绍。

Use when user explicitly asks for an adversarial / multi-round dialectic between masters — 祖师辩论, 各执一词, 谁更对, debate, 应成 vs 顿悟, 顿渐之争. Differs from /compare-masters (parallel single-round) by being…

Design, implement, debug, and review industrial recommendation-system architecture or algorithms using the released book PDFs, curated examples, and runnable templates.

Turn the current work into one polished, self-contained HTML visual page — a recap of a branch's changes, a plan, a map of a folder, endpoint set, or architecture, or an interactive drill-down map of…

Andorra payroll and CASS social security for tax year 2026. Covers resident employee IRPF withholding, non-resident employment and the elected frontier or seasonal method, ordinary employee and…

Use when turning an academic paper PDF/arXiv/OpenReview page/local LaTeX source into a single-file Chinese HTML deep-reading page, especially when the user wants a Cheat-Sheet style explanation, KaTeX…

Web2 recon pipeline — subdomain enum, URL crawling, JS analysis, temp emails, directory fuzzing. Trust-first asset discovery.

Workflow and best practices for writing Apache Airflow DAGs. Use when creating a new DAG, write pipeline code, handling questions about DAG patterns and conventions or extending an existing DAG with a…

QA 工程师 Agent — 测试策略、测试用例设计、自动化测试、性能测试、安全测试

Universal discipline for any LM-driven loop — agent retries, plan-act-observe, multi-agent handoffs, optimiser passes, test-fix cycles. Encodes the one rule every framework documents quietly and every…

Headless end-to-end / web-app testing for the Foreman e2e stage. Derive end-to-end tests from the PRD's User Flows, drive the real application the way a user would (browser flows, screenshots,…

Repurpose source assets into platform-native social content.

Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt ...

This skill should be used when the user asks to "validate a finding", "check if a vulnerability is real", "triage a security finding", "confirm a vulnerability", "determine if a finding is a true…

Follows Airbnb's design-led development and Figma's craft quality standards. Use when building user-facing features, making UI/UX decisions, determining when details matter, or applying design system…

PostgreSQL-specific development assistant focusing on unique PostgreSQL features, advanced data types, and PostgreSQL-exclusive capabilities. Covers JSONB operations, array types, custom types,…

Reach for this when structured YouTube data is the goal: video metadata, transcripts for analysis, channel upload history, search results or playlist contents, with no Google Cloud project and no…

用户用自然语言描述币种、回测时间区间和策略风格时，自动创建加密货币交易 Bot，读取内置 Hyperliquid CSV 覆盖并运行本地回测/进化；若币种、时间区间或策略风格缺失，则主动询问缺失项并展示 CSV 解析出的可用回测区间。也可在回测后上传平台 verify 或创建模拟实盘 Bot。适用于创建bot、交易策略、回测、backtest、evolve、upload verify、live…

生成精美的纯 HTML+CSS 信息图 — 时间线、流程、对比分析、SWOT、金字塔、漏斗、数据卡片、组织架构等。无需外部依赖，在沙箱 iframe 中渲染。适合将结构化信息以海报级视觉效果呈现。

Use when auditing a specific page's SEO performance, content quality, and competitive position. The agent fetches the URL, Googles the primary keyword, reads the top 3 competitors, and produces a full…

Use this skill when writing custom shaders, uniforms, filters, batchers, or low-level draw code in PixiJS v8. Covers Shader.from({gl, gpu, resources}), GlProgram/GpuProgram, UniformGroup with typed…

This skill should be used when researching a technical question, checking current API facts, comparing documented capabilities, or gathering primary-source evidence for a decision.

Map slice dependencies using DSM matrix and prioritize by risk

Web fingerprinting and WAF detection using wafw00f, whatweb, nuclei, and httpx. Use this skill when user needs to identify web technologies, detect WAF/CDN, analyze server headers, or fingerprint web…

Decide when to delegate to Honey's read-only subagents (hive-scout, hive-reviewer) instead of working inline, so the expensive tokens — large file reads and review passes injected back into the…

Structure a dev-tool homepage that converts developers into champions. Use when the landing page is written for the buyer instead of the developer, reads as salesy, buries what the product does, or…

Use when ryugi:executing-specs or ryugi:test-driven-development sends you here before the first implementation edit, when uncommitted work has to move to or be committed on a branch other than the one…

从 references/quiz_bank.json 抽取本章题目并按标准答案判分，支持选择、主观、画图、填空、判断、代码； 主观题按 keywords 要点覆盖判分，连续错两次提供提示/跳过/归档。禁止现场编题。用于阶段检查或模考。

Download videos and audio from 1500+ websites including YouTube, Bilibili, TikTok, Twitter/X, Instagram, Vimeo, and more using yt-dlp. Use when the user wants to download videos, save media from…

Review an implemented RFC in a fresh context against its acceptance criteria, RULES.md and the test plan, and save the review to reviews/.

Prevent and diagnose hanging or long-running Gradle unit tests (> 30s) in Android/Kotlin coroutines codebases. Use when running tests, when a test execution takes unexpectedly long, when background…

Knowledge comic creator supporting multiple styles (Logicomix/Ligne Claire, Ohmsha manga guide). Creates original educational comics with detailed panel layouts and sequential image generation. Use…

Use when claims must be checked against concrete evidence before reporting a conclusion.

Use for marketing, social, replies, product copy, launch copy, and writing in the user's voice when their Emulo writing profile should guide the task. Do not use for unrelated execution or UI/UX…

Map an unfamiliar codebase, feature, architecture, data flow, or operational path with file-backed evidence. Use when a request asks how a system works, where behavior lives, what changed, which…

Generate lorem ipsum placeholder text. This skill should be used when users ask to generate lorem ipsum content, placeholder text, dummy text, or filler text. Supports various structures including…

Generate comprehensive API documentation including endpoint descriptions, request/response examples, authentication guides, error codes, and SDKs. Creates OpenAPI/Swagger specs, REST API docs, and…

Design purposeful classroom activities, inquiry tasks, discussion prompts, questioning chains, group work, experiments, demos, warm-ups, exit tickets, peer instruction, and interactive learning…

Propose skills from wiki patterns and traces (WikiSkill).

Audit Docker, Compose, Kubernetes, Terraform, and cloud configuration for exposed services, privileged runtime settings, hardcoded secrets, and risky infrastructure defaults.

Simple task management using a shared TASKS.md file. Reference this when the user asks about their tasks, wants to add/complete tasks, or needs help tracking commitments.

把当前这次对话压缩成一份交接文档，供另一个代理接手。

Deep competitive moat analysis, market position assessment, and industry dynamics for one company against its direct rivals. To map an industry's supply / value chain and find chokepoints, use…

Run a 3-hour Hyperloom Qwen3-8B FRAMEWORK_AGENT (OPTIMIZE) session without the Kernel Agent. Use when the user wants a short, framework-only Hyperloom demo on the local AMD ROCm environment.

Design and document a ai content pipeline with structured process, quality checks, and system integration

Use when user asks to create/edit/query Online reports, SQL reports, data reports, or says "创建报表", "生成报表", "新建报表", "查询报表", "online报表", "SQL报表", "数据报表", "统计报表", "create report", "generate report",…

审阅AI科幻小说分部大纲、分卷大纲、章清单与单元案执行版。核心要求是：分部/分卷大纲必须把上一级分配给本层的内容切实、全量、保质落地。分部审阅要核查总纲层文件组分配给本部的全部内容是否已落地；分卷审阅要按是否存在分部，分别核查其是否完整落地总纲层或分部层分配内容。关键词：分部审阅、分卷审阅、单元案审阅、节奏布点、钩子策略、章清单审阅。

Use when constitution, spec, plan and tasks all exist and you want them cross-read against each other before any code is written — the rsc-sdd pre-implementation gate. Reports coverage gaps,…

Investigate a specific test failure to its root cause and document the why. Detects whether a failing test is flaky (intermittent) or a deterministic bug during reproduction. Use when a test fails and…