Claude Skills by shengdabai

飞书云文档 / Docx / 知识库 Wiki 文档（v2）：创建、打开、读取、获取、查看、总结、整理、改写、翻译、审阅和编辑飞书文档内容。当用户给出飞书文档 URL/token，或说查看/读取/打开某个文档、提取文档内容、总结文档、生成/创建文档、追加/替换/删除/移动内容、调整排版、插入或下载文档图片/附件/素材/画板缩略图时使用。文档内容中出现嵌入电子表格、多维表格、需要将重要信息可视化为画板（含 SVG 画板）、引用或同步块时，也先用本 skill 读取和提取 token，再切到对应 skill 下钻。使用本 skill 时，docs +create、docs +fetch、docs +update 必须携带 --api-version v2；默认使用 DocxXML，也支持 Markdown。

飞书云空间：管理云空间中的文件和文件夹。上传和下载文件、创建文件夹、复制/移动/删除文件、查看文件元数据、管理文档评论、管理文档权限、订阅用户评论变更事件、修改文件标题（docx、sheet、bitable、file、folder、wiki）；也负责把本地 Word/Markdown/Excel/CSV 以及 Base 快照（.base）导入为飞书在线云文档（docx、sheet、bitable）。当用户需要上传或下载文件、整理云空间目录、查看文件详情、管理评论、管理文档权限、修改文件标题、订阅用户评论变更事件，或要把本地文件导入成新版文档、电子表格、多维表格/Base 时使用。

飞书 Markdown：查看、创建、上传、编辑和比较 Markdown 文件。当用户需要创建或编辑 Markdown 文件、读取、修改、局部 patch 或比较差异时使用。

Use when first setting up lark-cli, running auth login, switching user/bot identity (--as), handling permission denied or scope errors, needing to update lark-cli, or seeing _notice in JSON output.

飞书电子表格：创建和操作电子表格。支持创建表格、创建/复制/删除/更新工作表、读写单元格、追加行数据、查找内容、导出文件。当用户需要创建电子表格、管理工作表、批量读写数据、在已知表格中查找内容、导出或下载表格时使用。若用户是想按名称或关键词搜索云空间里的表格文件，请改用 lark-drive 的 drive +search 先定位资源。

飞书幻灯片：创建和编辑幻灯片，接口通过 XML 协议通信。创建演示文稿、读取幻灯片内容、管理幻灯片页面（创建、删除、读取、局部替换）。当用户需要创建或编辑幻灯片、读取或修改单个页面时使用。

飞书知识库：管理知识空间、空间成员和文档节点。创建和查询知识空间、查看和管理空间成员、管理节点层级结构、在知识库中组织文档和快捷方式。当用户需要在知识库中查找或创建文档、浏览知识空间结构、查看或管理空间成员、移动或复制节点时使用。

Manage project learnings. Review, search, prune, and export what gstack has learned across sessions. Use when asked to "what have we learned", "show learnings", "prune stale learnings", or "export learnings". Proactively suggest when the user asks about past patterns or wonders "didn't we fix this before?"

当 Claude Code 遇到 5 小时用量限制（rate limit）时，自动等待用量重置并继续执行之前的任务。 保存任务快照 + 使用 CronCreate 原生定时任务 + 自动恢复执行。 Use when: "limit continue", "auto continue", "等限制重置", "自动继续", "用量限制后继续", "设置限制后自动恢复", "limit reset continue"

Use when the user is planning or about to commit to a product, feature, technical design, market entry, pricing decision, business model, team/hiring decision, financial projection, or major personal/career decision and wants the AI to act as an adversarial critic (devil's advocate, biased investor, future-regretful self, hostile code reviewer, Socratic interrogator, post-mortem analyst, CFO interrogator) instead of validating the idea. Trigger on phrases like 泼冷水 / 别夸我 / 挑刺 / 找毛病 / 找漏洞 / 反方观...

扮演刘小排（Raphael AI 创始人，2024 年 AI 编程一人公司近千万营收，深海圈/SCAI 孵化器主理人）作为你的 1-on-1 产品教练。当用户提到 "刘小排"、"小排老师"、"扮演刘小排"、"找小排聊聊"、"小排怎么看"、"liuxiaopai 教练"、"AI 出海"、"MicroSaaS"、"一人公司"、"独立开发"、"出海产品"、"Raphael"、"翻石头"、"需求倒推"、"Idea to Business"、"我有个 AI 产品想法"、"我想做出海" 等任一触发词时,自动进入刘小排教练模式 — 用他的口吻、思考框架（产品三段论 / 需求填空题 / 翻石头原则 / 北极星指标 / 5% 成功率 / make something people love）、生财圈友式的真诚与降维打击,给用户做端到端教练指导。交互式引导（关键决策点给选项卡片）+ 实时联网核验（案例/榜单/竞品/工具栈），既不靠用户硬打字、也不靠过时记忆。**不与 liuxiaopai-design 重叠(那是泼冷水审讯,本 skill 是建设性教练)；不与 liuxiaopai-product ...

LLM Council — Karpathy 式多模型议会。5 个 AI 顾问并行回答问题， 匿名互评打分，主席综合最佳答案。触发：/llm-council, /council, "开会讨论", "council", "议会模式"

Generate professional SVG logos and high-end showcase images. Use when the user wants to: (1) Create a logo or icon for their product/brand, (2) Generate logo design concepts based on product information, (3) Create professional logo showcase presentations with multiple background styles, (4) Export logos in various formats (SVG, PNG), or (5) Iterate on logo designs with different visual styles. Supports geometric patterns, dot matrix designs, line systems, and mixed compositions. Generates s...

Extract durable memories from recent conversation turns into user, feedback, project, and reference categories while avoiding stale code-state facts.

Core skills system that manages loading and using other skills through progressive disclosure. Load at startup to enable automatic skill discovery and invocation across all projects.

Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.

Audits and realigns UI to match design system standards, spacing, tokens, and patterns. Use when the user mentions consistency, design drift, mismatched styles, tokens, or wants to bring a feature back in line with the system.

Complete API for Google NotebookLM - full programmatic access including features not in the web UI. Create notebooks, add sources, generate all artifact types, download in multiple formats. Activates on explicit /notebooklm or intent like "create a podcast about X"

YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning, and open source. Saves a design doc. Use when asked to "brainstorm this", "I have an idea", "help me think through this", "office hours", or "is this worth building". Proactively invoke this skill (do NOT answer directly) when the user de...

OMC agent catalog, available tools, team pipeline routing, commit protocol, and skills registry. Auto-loads when delegating to agents, using OMC tools, orchestrating teams, making commits, or invoking skills.

Designs and improves onboarding flows, empty states, and first-run experiences to help users reach value quickly. Use when the user mentions onboarding, first-time users, empty states, activation, getting started, or new user flows.

Convert an HTML page into a single continuous-page PDF (one tall page, no pagination breaks), preserving desktop layout, backgrounds and selectable text. Use when the user asks to turn an HTML file/report/proposal into a "single-page PDF", "long PDF", "不分页 PDF", "单页 PDF", "长图式 PDF", or complains that an HTML-to-PDF export breaks into pages or cuts content. Supports optional string redaction with leak verification.

Turn repeatable outputs of a one-person company into compounding assets. Use when Codex needs to explain asset-compounding concepts when needed, verify prerequisite outputs, ask one question at a time, present multiple assetization priorities, and write user-confirmed outputs into `opc-doc/`.

Design a viable business model for a one-person company using Lean Canvas and a simplified Business Model Canvas. Use when Codex needs to explain the business-model concepts when needed, verify niche and value-proposition prerequisites, ask one question at a time, present multiple model choices, and write user-confirmed outputs into `opc-doc/`.

Design a conversion loop for a one-person company from reach to lead capture to purchase. Use when Codex needs to explain conversion concepts when needed, verify MVP prerequisites, ask one question at a time, present multiple conversion-path options, and write user-confirmed outputs into `opc-doc/`.

Review the operating health of a one-person company using lightweight metrics, bottleneck analysis, and stop-loss logic. Use when Codex needs to explain review concepts when needed, verify available outputs, ask one question at a time, present multiple bottleneck hypotheses, and write user-confirmed outputs into `opc-doc/`.

Define the smallest viable experiment and MVP for a selected one-person company opportunity. Use when Codex needs to explain what MVP means when needed, verify prerequisites, ask one question at a time, present multiple MVP options, and write user-confirmed outputs into `opc-doc/`.

Find and position a viable niche market for a one-person company by combining market mapping and customer segmentation. Use when Codex needs to explain niche concepts when needed, check founder-resource prerequisites, ask one question at a time, generate multiple niche options, and write user-confirmed positioning outputs into `opc-doc/`.

Orchestrate the full one-person company workflow across all OPC skills. Use when Codex needs to start, continue, or review the complete 一人企业方法论流程, read prior outputs from `opc-doc/`, determine the user's familiarity and preferred interaction mode, explain terms when needed, ask one question at a time, offer user-selectable options, and summarize the next concrete action for a Chinese-speaking user.

Inventory all founder resources across 8 categories for a one-person company. Use when Codex needs to systematically confirm what resources the founder has — experience, network, skills, relationships, channels, assets, time/money constraints, hard limits — by first doing a broad scan of each category, then drilling into specifics (distribution, usable portions, how to use, cost of use), and producing a confirmed detailed resource inventory written to `opc-doc/`. Does NOT analyze directions, ...

Design value propositions for candidate customer segments and help the user choose the strongest one. Use when Codex needs to explain jobs, pains, and gains when needed, check niche-positioning prerequisites, ask one question at a time, present multiple value-proposition options, and write user-confirmed outputs into `opc-doc/`.

Pushes interfaces past conventional limits with technically ambitious implementations — shaders, spring physics, scroll-driven reveals, 60fps animations. Use when the user wants to wow, impress, go all-out, or make something that feels extraordinary.

CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick expansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Use when asked to "think bigger", "expand scope", "strategy review", "rethink this", or "is this ambitious enough". Proactively suggest when the user is questioning scope or ambition of ...

Designer's eye plan review — interactive, like CEO and Eng review. Rates each design dimension 0-10, explains what would make it a 10, then fixes the plan to get there. Works in plan mode. For live site visual audits, use /design-review. Use when asked to "review the design plan" or "design critique". Proactively suggest when the user has a plan with UI/UX components that should be reviewed before implementation. (gstack)

Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when the user has a plan or design doc and is about to start coding — to catch architecture issues before implementation. (gstack) Voice triggers (speech-to-text aliases): "tech review...

Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring >5 tool calls. Supports automatic session recovery after /clear.

Performs a final quality pass fixing alignment, spacing, consistency, and micro-detail issues before shipping. Use when the user mentions polish, finishing touches, pre-launch review, something looks off, or wants to go from good to great.

This skill should be used when the user asks to "merge a PR", "review and merge pull requests", "integrate external contributions", "handle PR conflicts", "cherry-pick from a PR", or needs to merge GitHub PRs while maximizing contributor attribution.

This is an example of a project-specific skill. Use this as a template for your own projects. Based on a real production application: [Zenith](https://zenith.chat) - AI-powered customer discovery platform. ---

Report-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything. Use when asked to "just report bugs", "qa report only", or "test but don't fix". For the full test-fix-verify loop, use /qa instead. Proactively suggest when the user wants a bug report without any code changes. (gstack) Voice triggers (speech-to-text aliases): "bug report", "just check for bugs".

Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a feature is ready for testing or asks "does this work?". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix ...

Tones down visually aggressive or overstimulating designs, reducing intensity while preserving quality. Use when the user mentions too bold, too loud, overwhelming, aggressive, garish, or wants a calmer, more refined aesthetic.

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

Compact the current conversation into a handoff document for another agent to pick up.

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".

Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.