Capture current metric values for goal evaluation. Triggers: 'log metrics', 'update metrics', 'record measurements'.
Use when a spec exists and user wants implementation steps. Triggers: 'how to implement', 'create plan', 'plan this', 'what are the steps'.
Visual QA using Playwright as a browser automation library. --setup installs Playwright and creates ui-goals.json; default mode writes inline scripts to navigate, screenshot, and…
Review changes across 12 quality dimensions and report findings. Use after a chunk of work or before commit.
Audits production systems for scale readiness — observability, performance, reliability, and operational maturity. For teams with traction preparing to grow.
Semantic QA — define inputs/criteria, generate test scripts, Claude judges outputs or screenshots against criteria.
Use when user describes a feature to build. Triggers: 'spec this', 'create specification', 'define requirements', 'I want to build'.
Define project stage, scope constraints, and graduation criteria. Set mode configures the stage; evaluate mode assesses readiness for human approval.
Use when user needs to think through decisions, explore trade-offs, or challenge assumptions. Triggers: 'think with me', 'help me decide', 'what am I missing?', 'devil's…
Install or update Shipkit via npx. Detects existing installations, archives them safely, and intelligently merges user content with new version.
Use when defining project vision and strategic direction. Triggers: 'why this project', 'define vision', 'project goals', 'what are we building'.
Log session progress and save resume state. Infers from conversation and git. Triggers: 'log progress', 'session summary', 'checkpoint', 'save progress', 'end session'.
スクリーンショットの取得・加工を行う。ローカルスクショから最新画像を取得、 PlaywrightでWebページをキャプチャ、画像のトリミング・リサイズ、機微情報を黒塗りマスキング。 記事執筆、レポート作成、UI確認、画像加工時に起動。…
Generate high-engagement hosting scripts and voucher-drop routines for live stream shopping.
Open a tmux split running diffview.nvim so the user can review the agent's recent changes. Use proactively after non-trivial edits, or when the user asks to "show the diff", "open…
Explain the current topic or a proposed design visually with types and signatures, pseudocode, a call tree, a component tree, a file tree, a diff, a whole block, a Mermaid…
Prepare and route a document for e-signature — run a pre-signature checklist, configure signing order, and send for execution.
Use when the user wants to create, list, get, update, rename, or delete a SigNoz saved Explorer view.
On-demand parent-supervised delegation of a single real task to Claude TUI as a subagent — briefings, checkpoints, failure escalation, and completion evidence.
On-demand parent-supervised delegation of a single real task to Codex TUI as a subagent — briefings, checkpoints, failure escalation, and completion evidence.
On-demand parent-supervised delegation of a single real task to Cursor agent TUI (cursor-agent) as a subagent — briefings, checkpoints, failure escalation, and completion…
On-demand parent-supervised delegation of a single real task to OpenCode CLI as a subagent — briefings, checkpoints, failure escalation, and completion evidence.
On-demand parent-supervised delegation of a single real task to Pi CLI as a subagent — briefings, checkpoints, failure escalation, and completion evidence.
Turn vague ideas or requirements into a decision-ready brief for GSD discuss-phase.
Parent-only Silver Bullet orchestrator — reads intent and directive state, spawns Task workers per atomic flow, never implements directly
Lightweight cross-session context threads for tracking a specific topic, decision chain, or concern across multiple sessions without a full project handoff.
Generic review-finding triage across any artifact or scope — classifies findings, files valid issues via PM adapter, and routes fixes without reviewer self-triage.
Safe git revert for SB phase or plan commits. Shows recent commits, checks dependent phases, and requires confirmation before reverting.
Quick gut-check before implementing when the user directly asks you to do something (e.g. "add X", "fix Y", "change Z").
Agentic AI-driven multi-persona EventStorming simulation on Miro. Use when: 'simulate a workshop', 'run an EventStorming simulation', 'agentic EventStorming', 'multi-persona…
Discover and boot an iOS simulator. Use before any command that needs a simulator UDID.
Use when: making one review round complete instead of incremental, enumerating review dimensions up front, sweeping a whole diff per dimension, declaring review coverage and…
Six hats, thinking hats, explore all perspectives, de Bono. Analyze from multiple perspectives via Six Thinking Hats: Blue (process), White (data), Green (creativity), Yellow…
Kelly Criterion position sizing. Use when user says "size", "kelly", "how much to buy", "position size", "how many shares", "build portfolio", or "allocate".
Generate a repo-specific illustrator brief and AI image prompts for missing assets. Use when UI art is missing, placeholders exist, or the user asks for an asset brief or image…
SKEIN task 闭环入口 + exec 调度门。作 /skein-exec 命令: 有入参→请求强制作 task 走闭环 (委托 skein-flow: plan→exec→check→finish, 不 inline); 无入参→驱动 .skein 既有 ready/active task 各走闭环 (task 级并发 2)。作 skill: 被…
Přemění skeleton-app na reálnou web appku podle popisu uživatele. Zeptá se co chce, naimplementuje funkční MVP, lokálně commitne a deployne na Vercel přes CLI bez Git integrace.
Walk through sketches, pick winner + rationale, group by design area, write project skills to ./.claude/skills/design-
-conventions.md.
用于【都市悬疑】题材下的提纲审阅优化 SOP 编排。作为题材包装层、兼容入口与路由层，负责保留都市悬疑入口名，并明确要求加载并使用 `通用-大纲审阅优化闭环`，同时按总纲 / 分卷对象分流到对应题材审阅与设计 Skill。
用于围绕起点中文网或其他目标平台的同题材 TopN 榜单，锁定标杆作品并进行逐本深搜式竞对分析。适合搜索榜单、筛选强样本、阅读目录/公开正文/设定/书评/读者评论/读后感/拆解材料，并在 `竞对分析/` 中为每部作品分别落盘详细竞对分析报告。关键词：竞对分析、竞品分析、标杆作品拆解、TopN 榜单、同题材对标、榜单深搜、读者评论分析、单书竞对报告。
Distill a real boss into an AI skill, or generate a boss skill from a famous entrepreneur archetype such as Elon Musk, Steve Jobs, Jeff Bezos, or Jensen Huang.
用于对指定提纲执行"审阅→修改→复审"的闭环，直到双轴评分（技法分 ≥ 6.0 / 留存分 ≥ 5.0）加权的综合评分连续两轮独立审阅在保留两位小数后均严格大于 9.20。适合大纲审阅优化 SOP、报告复用、回炉循环、评分门槛控制与最终回执收口。关键词：大纲审阅闭环、回炉到 9.20 以上、双轴评分、复审循环、主报告覆盖、提纲优化 SOP。
创建异能志怪题材章节正文、作者有话说与章节后记。用于按分卷大纲、人物传记、设定与写作研究，直接新写、重写或扩写都市异术超能 / 志怪连载章节；作为题材包装层与路由层，负责保留异能志怪标准入口名，并要求生成的 `## 作者有话说` 保持读者向小剧场与轻微异感。
用于在选定平台（七猫/起点/番茄/晋江等）与题材（科幻/悬疑/职场/爱情等）之后、设计大纲之前，完成项目级的战略初始化。 唯一目标：在指定的平台和题材约束下，确定最能吸引读者和最能赚钱的小说应当具备哪些要素。 核心方法：从已有宏观市场分析（写作研究/）和竞对分析数据出发自主决策——用户无需了解"什么套路最火"，本 Skill 根据研究结论 — from…
用于将 `小说正文/` 目录内指定章节批量上传到起点中文网作者后台并保存为草稿。支持按 `小说正文/README.md` 读取账号、密码、起点书籍Id、书名与卷名校验，自动执行登录、进入新建/修改章节页、填写合并标题输入框、粘贴正文、添加作家的话、保存草稿，并在保存后从左侧章节列表反查章节Id并写回…
Distill a graduated lab senior into an AI Skill. Import chats, meeting notes, photos, and screenshots to build Group Memory + Persona with continuous evolution.
用于【都市悬疑】题材下搜索起点中文网等目标平台的同题材 TopN 候选池，先锁定榜单与样本池，再从中收束 3–5 本主样本做四层深拆式竞对分析。作为题材包装层与路由层，负责保留都市悬疑标准入口名，补充都市职业、现实针脚、证据/程序链、长线谜团等题材维度，并明确要求优先强制加载并使用 `通用-分析竞对作品`。关键词：都市悬疑竞对分析、都市悬 — from…
用于蒸馏一部成功小说的叙事架构 DNA，产出可被下游写/审/改 Skill 消费的"作品蓝本模板"。适合把一部作品的章首模式、钩子轮换、回报间隔、节奏分布、POV 规律、信息释放节拍等提炼为可参照的结构约束，并在目标项目根目录自动注册到 Agents.md。关键词：蒸馏作品蓝本、叙事架构DNA、钩子指纹、节奏分布、信息释放节拍、结构参照。
Distill an ex-partner into an AI Skill. Import WeChat history, photos, social media posts, generate Relationship Memory + Persona, with continuous evolution.
用于【都市悬疑】题材下的全书 / 分部 / 分卷 / 分章书评撰写、重写与审计。作为题材包装层、兼容入口与路由层，负责保留都市悬疑入口名、补充城市现实压迫、异常证据与人性代价的推荐话术，并明确要求加载并使用 `通用-撰写书评`。
用于在选定平台（七猫/起点/番茄/晋江等）与题材（科幻/悬疑/职场/爱情等）之后、设计大纲之前，完成项目级的战略初始化。 唯一目标：在指定的平台和题材约束下，确定最能吸引读者和最能赚钱的小说应当具备哪些要素。 核心方法：从已有竞对分析和写作研究数据出发自主决策——用户无需了解"什么套路最火"，本 Skill 根据研究结论决定一切。 产出物 — from…
用于从写作研究报告（题材×平台级）中提取可执行写作约束，产出"写作研究模板"，作为下游写/审/改 Skill 的题材×平台默认约束基线。蒸馏源默认扫描小说项目根"写作研究/"目录 + "通用skills/写作研究/"目录，可指定目录、文件或 URL。关键词：蒸馏写作研究、研究报告提取、题材平台约束、写作约束基线、规则提取。 — from…
用于【都市悬疑】题材下搜索起点中文网等目标平台的同题材 TopN 候选池，先锁定榜单与样本池，再从中收束 3–5 本主样本做四层深拆式竞对分析。作为题材包装层与路由层，负责保留都市悬疑标准入口名，补充都市职业、现实针脚、证据/程序链、长线谜团等题材维度，并明确要求优先强制加载并使用 `通用-分析竞对作品`。关键词：都市悬疑竞对分析、都市悬 — from…
用于【都市悬疑】题材下搜索起点中文网等目标平台的同题材 TopN 候选池，先锁定榜单与样本池，再从中收束 3–5 本主样本做四层深拆式竞对分析。作为题材包装层与路由层，负责保留都市悬疑标准入口名，补充都市职业、现实针脚、证据/程序链、长线谜团等题材维度，并明确要求优先强制加载并使用 `通用-分析竞对作品`。关键词：都市悬疑竞对分析、都市悬 — from…
World-class #1 expert 4PL and supply chain director specializing in AI-powered logistics optimization, digital transformation, warehouse automation, transportation manage — from…
用于蒸馏一部成功小说的叙事架构 DNA、故事线台账、套路指纹与读者吸引留存策略，产出可被下游写/审/改 Skill 消费的"作品蓝本模板"。蒸馏优先级：书名策略 > 内容简介 > 黄金三章 > 章标题/章首/章末模式 > 套路配置 >…
用于【都市悬疑】题材下搜索起点中文网等目标平台的同题材 TopN 候选池，先锁定榜单与样本池，再从中收束 3–5 本主样本做四层深拆式竞对分析。作为题材包装层与路由层，负责保留都市悬疑标准入口名，补充都市职业、现实针脚、证据/程序链、长线谜团等题材维度，并明确要求优先强制加载并使用 `通用-分析竞对作品`。关键词：都市悬疑竞对分析、都市悬 — from…
用于【都市职场】题材下的全书 / 分部 / 分卷 / 分章书评撰写、重写与审计。作为题材包装层、兼容入口与路由层，负责保留都市职场入口名、补充城市现实压迫、异常证据与人性代价的推荐话术，并明确要求加载并使用 `通用-撰写书评`。
用于【异能志怪】题材下的提纲审阅优化 SOP 编排。作为题材包装层、兼容入口与路由层，负责保留异能志怪入口名，并明确要求加载并使用 `通用-大纲审阅优化闭环`，同时按总纲 / 分卷对象分流到对应题材审阅与设计 Skill。
Distill a crush into an AI Skill. Import chat history, photos, social media, generate Relationship Memory + Persona, with continuous evolution.