Discovery skill for the Native SDK, the complete toolkit for building native desktop applications. Apps are authored in TypeScript + declarative Native markup (.native) by default and compiled to native code with no JS runtime in the binary; Zig cores are an explicit alternative, and WebViews are the optional web-content path. Use when the user asks what the Native SDK is, how to build a Native SDK app, author native UI, scaffold an app, configure app.json or legacy app.zon, add bridge commands, embed web content, package an app, test a running app, or automate a Native SDK app.

When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ad copy,' 'ad creative,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' or 'audience targeting.' This skill covers campaign strategy, ad creation, audience targeting, and optimization.

When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome sequence," "re-engagement emails," "email automation," or "lifecycle emails." For in-app onboarding, see onboarding-cro.

Cut an OpenSEO release — bump the version, draft user-facing release notes from commits since the last tag, run a review + subagent-verification pass, and open a "release: vX.X.X" PR. Use when the user asks to prepare a release, bump the version, or write release notes.

Evaluate verified findings from merge-ready, Greptile, pull-request, CI, security, billing, and other code reviews, then promote durable review gaps into the version-controlled .greptile configuration. Use when a review uncovers a recurring or high-risk repository invariant that Greptile does not capture, when Greptile repeatedly produces a false positive, or when asked to audit or update OpenSEO's Greptile rules and context.

闲鱼（goofish.com）商品搜索、查看详情、私信会话管理与回复。通过 forked camoufox-cli 挌久化 session xianyu 完成。当用户要求在闲鱼上搜索商品、查看宝贝、读取或回复私信时触发。

当执行 IR（投资人关系）任务·模式 2 时使用。帮 OPC / 中小微企业老板准备和跟踪各类外部申报 项目：高新技术企业认定、加速器申请、政府补贴、资质认证（软著 / 商标 / 专利 配套）、行业奖项。涵盖材料生成 + 时间线管理 + 状态跟踪。

撰写投资人触达邮件、暖介绍请求、跟进邮件、投资人更新等融资沟通文案。 当用户需要向天使投资人、VC、战略投资人、加速器发起接触，或需要精简、个性化的投资人沟通文案时触发。

创建和更新融资路演材料：Pitch Deck、One-Pager、投资人备忘录、加速器申请、财务模型、资金用途表、里程碑计划。 当用户需要投资人面向的文档、财务预测、BP 更新、路演 PPT 时触发。

Analyze a product from documentation, websites, PDFs, articles, release notes, pricing pages, app listings, reviews, filings, or related links; save separate intermediate analyses from seven roles (user, investor, product manager, market operator, brand operator, competitor, partner), then synthesize a sourced illustrated Markdown report. Use when the user asks for product analysis, product teardown, multi-role evaluation, investment/product/marketing/brand/competitive/partnership perspectives, or a report with assumptions, boundaries, verification signals, and scenario updates.

Create and maintain a Markdown knowledge base that any AI agent can read, search, and update. Use when the user wants to start a knowledge base, add or update notes, organize docs/notes for an agent or LLM to consume, build an index of notes, or run a cleanup/maintenance pass on an existing MD knowledge base. Triggers include "knowledge base", "KB", "notes for the agent", "index of notes", "second brain", "docs for AI context", "add a note", "update the KB".

Create AI videos with HyperFrames in Hermes using HTML, CSS, and JavaScript compositions, then validate and render them to MP4. Use for short video intros, cinematic trailers, product promos, subtitle animations, HUD/tech visuals, web-to-video work, and motion graphics.

Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging norm stats and GPU memory issues.

Drive the Rerun URDF API (rerun.urdf.UrdfTree) to ingest a URDF as a Transform3D layer on a robot recording. Read when logging a robot model, running forward kinematics from joint states, composing a fixed chain for sensor extrinsics, or when the transform tree will not connect from the data alone. Builds on rerun-chunk-processing (stream/lens mechanics) and rerun-data-model (entity paths, timeline, base-vs-layer).

Ingest MCAP files into Rerun chunk streams with rerun.experimental.McapReader. Read when converting an MCAP recording, selecting topics or decoders, decoding custom protobuf messages, or when an MCAP-derived stream comes out empty. Builds on rerun-chunk-processing (stream mechanics) and rerun-data-model (what the topics should become).

Performance patterns and gotchas for querying a Rerun catalog from Python. Reach for this when a CatalogClient/dataset query is unexpectedly slow, or when shaping a per-segment / per-episode pipeline that hits the catalog from many places.

Design a Rerun blueprint from the data, then iterate on it from headless screenshots. Read this when laying out a recording or dataset in the viewer, designing a default blueprint, or deciding which views show which entities. Covers archetype-to-view mapping, layout reasoning, the rrb construction API, the contents grammar, and the screenshot loop.

Turn an uploaded PDF, paper, book chapter, document, URL, or user-provided topic into a structured, interactive learning course. Use when the user wants to learn, study, understand, master, review, or practice a subject chapter by chapter; asks for a tutorial or curriculum from source material; wants exercises, quizzes, answer grading, hints, spaced review, or a final assessment; or says "teach me this", "learn this PDF", "分章节教学", "带我学", or similar; or returns to continue a previous course ("continue my course", "接着上次学") or supplies a saved course-state file or state block. Adapt explanations and practice to the learner's level, preserve page or section references for documents, and teach incrementally rather than dumping all content at once.

Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version, or publish a new Hindsight version.

Generates a comprehensive milestone progress review including feature completeness, quality metrics, risk assessment, and go/no-go recommendation. Use at milestone checkpoints or when evaluating readiness for a milestone deadline.