Move a tracked AI work thread to a different lifecycle stage on the thread registry/board. Use when the auto-classifier put a thread in the wrong stage (Funnel, Specify/Plan, Implement, Review/Ship, Waiting/Blocked, Done) and you want to correct it, or to manually advance a thread.

Use when deriving SDD specs from existing code or retroactively documenting implemented behavior. Triggers: "derive specs", "generate specs from code", "document this code in SDD", "retrofit specs", "spec out what's already built".

Operate the joelclaw event bus, gateway, observability, and agent loop infrastructure via the joelclaw CLI. Use for: sending events, checking runs, starting/monitoring/cancelling agent loops, debugging failed runs, checking health, restarting the worker, inspecting step traces, managing subscriptions, gateway operations, OTEL queries, semantic recall. Triggers: 'joelclaw', 'send an event', 'check inngest', 'start a loop', 'loop status', 'why did this fail', 'debug run', 'check worker', 'restart worker', 'runs', 'what failed', 'subscribe', 'gateway', 'otel', 'recall', or any Inngest/event-bus/agent-loop task.

Researches a company from its URL and produces a Brand DNA file covering positioning, audience, competitors, voice, and messaging. Use when starting work with a new brand or customer.

Refresh fact-based sections of crates/AGENTS.md (STRUCTURE, WHERE TO LOOK, COMPLEXITY HOTSPOTS, KNOWN BROKEN) from current codebase state. Use after refactoring, renaming files, adding crates, or when the agent notices AGENTS.md info is stale.

Discover what customers truly need by analyzing the "job" they hire your product to do. Use when the user mentions "customer discovery", "why customers churn", "what job does this solve", "competing against luck", "product-market fit", "switching behavior", "milkshake moment", or "functional vs emotional jobs". Also trigger when investigating why users choose competitors, designing features around real customer needs, or reframing a value proposition. Covers JTBD interviews, competition analysis, and jobs-oriented roadmaps. For product positioning, see obviously-awesome. For rapid validation, see design-sprint. For non-leading interview technique, see mom-test.

Design MVPs, validated learning experiments, and pivot-or-persevere decisions using Build-Measure-Learn. Use when the user mentions "MVP scope", "validated learning", "pivot or persevere", "vanity metrics", "test assumptions", "innovation accounting", "build-measure-learn", "minimum viable experiment", "should we pivot", "test a business idea cheaply", or "build the smallest version first". Also trigger when deciding what to include in a first version, measuring startup progress, or evaluating whether to change direction on a product bet. Covers innovation accounting and actionable metrics. For 5-day prototype testing, see design-sprint. For customer motivation analysis, see jobs-to-be-done.

Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making mistakes", "this is unintuitive", or "people cant figure out how to use it". Also trigger when reducing product complexity or feature creep. Covers the gulfs of execution and evaluation. For usability scoring, see ux-heuristics. For iOS-specific patterns, see ios-hig-design.

Check prose with Jev for narrow AI-writing patterns and revise from its feedback. Use when asked for Jev prose checks, AI-pattern cleanup, or an ongoing check-and-rewrite loop while writing sentences or paragraphs.

Selects, deploys, and customizes AI models on Amazon SageMaker. Training or Processing jobs, fine-tuning (SFT/DPO/RLVR/RLAIF), model selection, dataset preparation, evaluation, SageMaker or Bedrock deployment, inference optimization and endpoint diagnostics. Covers the full lifecycle from planning through production. Use when fine-tuning models on SageMaker, choosing which base model to customize, fine-tune, or deploy from SageMaker JumpStart or Hub, SageMakerPublicHub, or the SageMaker public model catalog, transforming or validating training data, evaluating model quality, deploying or optimizing endpoints, configuring IAM/S3 for training, or managing SageMaker Managed MLflow. Use for endpoint health, failures, latency, logs, metrics, errors. Covers Serverless Model Customization, Nova and OSS deployment paths, and PySDK v3. NOT for Ground Truth labeling, Feature Store, or general-purpose AWS infrastructure.

Maintain Chatto runtime documentation in docs/architecture/ when runtime structures change, or audit it when requested.

Audit backend tasks/spec coverage for Web, site, public agent interfaces, config, and extensibility impact. Use for contract, handler, CLI, extension/hook/tool/registry/bridge/MCP/workflow changes; excludes refactors without those impacts.

在当前仓库设置 Husky pre-commit hooks，集成 lint-staged (Prettier)、类型检查和测试。适用于用户想添加 pre-commit hooks、设置 Husky、配置 lint-staged，或在提交时运行格式化、类型检查和测试时。

创建包含章节、题目、答案和讲解的练习目录结构，并确保通过 linting。适用于用户想 scaffold exercises、创建 exercise stubs，或设置新的课程章节时。

Tally Claude Code session token usage and cost estimates from the raw JSONL conversation log. Trigger when the user asks about session cost, token usage, API spend, cache hit rate, input/output tokens, or wants a breakdown of how much a Claude Code session has cost. Also trigger for "how much have we spent", "show me token usage", "session summary", "cost so far", or any request to analyse or display per-turn metrics from the current or a past session. Do NOT auto-dispatch compare mode (--compare / --compare-prep / --compare-run / --count-tokens-only) from natural-language phrases. The skill body uses $ARGUMENTS[0] as the dispatch key — if the first positional argument is not literally "compare", "compare-prep", "compare-run", or "count-tokens", route to the default single-session report.

Use when you want to search for or download experimentally-determined 3D structures for biomolecules (proteins, nucleic acids, bound ligands). Supports searching by sequence similarity, structure similarity, chemical and other attributes. Also use to get metadata about biomolecular structure experiments.

为组织、产品、服务、场所、文化项目或个人创建、编辑、扩展、迁移或诊断品牌识别，交付一组以假乱真的品牌示例（官网首屏、门店、包装、名片、社媒等最终效果）和一个示例级品牌工具包文件夹（标志方向、色表、字体建议、图像调子、信息要素、参考设计、指南），让用户直接看到品牌做出来是什么样。用于名称与字标、图形标、核心识别、应用系统、品牌架构、焕新迁移与动态身份；强调最小系统、一致性与真实感。不用于单个功能图标、完整字体工程、一次性营销画面或把精致网页当作品牌本身。

为活动、促销、品牌 campaign 与倡导等传播任务创建、改版、扩展或诊断海报与营销图形，交付以假乱真的成品平面稿（单张海报、系列、社媒多尺寸套件、展示物与户外幅面）和一个能重出图的母版文件夹（HTML/CSS 画板母版、内容插槽、素材层、色与字规范、导出脚本、README）。基底是固定尺寸的分层版面：生图只产背景与主视觉素材，文字全部活字，系列只变内容不变容器。入口三判据同时成立才属本 Skill：输出是定尺寸单帧静态平面文件（PNG/JPG/PDF，不可滚动、不可交互、不分页）；一帧承载全部信息、一次扫读完；用途是传播。用于：海报、传单、KV、banner、社媒图、公众号头图与封面、灯箱、易拉宝、展板、广告图、单页邀请函、电商主图、节日贺图、视频封面、微信长图。不用于并须转出：PPT、报告、手册、杂志、学术海报与任何多页物→design-editorial-and-presentations；logo、VI、名片、品牌手册→design-brand-identities；网页、落地页、dashboard 与任何可交互界面→build-polished-visual-frontends；数据图表与重信息图→create-data-visualizations；单张无文字插画→create-illustrations-and-scenes；单个图标或图形元素→design-icons-and-symbols。

Add-on to the sniff-test skill that looks across many initiatives on a portfolio Kanban for board-level patterns — duplicate/shadowing initiatives, WIP clustering, stale-status sweeps, experiment scope creep, and portfolio risk balance (Explore/Discovery vs. Build & Deliver split). Use when reviewing a whole board or portfolio, prepping a sponsor/ELT portfolio review, or deciding where the portfolio is over- or under-invested. For sniffing a single initiative, use sniff-test.

Build convincing timber for Three.js as one procedural MeshPhysicalMaterial with growth rings, cathedral figure, pores, medullary rays, checks, tool marks, end grain, and oil, wax, or lacquer finishes, so the grain follows the form and survives macro close-ups without image textures. Use for wood boards, benches, carved panels, tool handles, joinery, floors, and any request to make 3D wood look real, detailed, or less like a tiled photo or plastic.