KKenny0

Shared safety notes available in catalog but not bound by default.

Builds a compact outline for a script generation stage.

Expands an outline into detailed scene-level writing guidance.

Builds character profile guidance for downstream generation.

Overrides default storyboard guidance for sports projects.

Builds default storyboard generation guidance.

Shared privacy guidance available in catalog but not bound by default.

Describes when a support reply should ask for escalation.

Generate a management-facing weekly report from Tracework raw entries, using git only as limited fallback coverage. Supports work, personal, and private all-project scopes. Three modes: quick conversation review ("这周做了啥", "周报简版", "quick weekly", "本周概要"), default Markdown brief ("写周报", "周报", "/tracework:weekly", "weekly brief", "本周总结", "weekly report"), and PPT-ready Markdown Deck only when weekly PPT is explicit ("weekly PPT", "周报 PPT", "weekly slides", "演示大纲"). Do not use for daily notes, generic slide decks, or single-commit analysis.

Adaptive-depth session recap and low-friction checkpoint capture for report-ready Tracework memory. Use this skill for "/tracework:capture" or when the user signals end of a work session, such as "收工", "今天到这", "done", "wrap up", "that's it for today", "好了", or "先这样". Also trigger on explicit checkpoint or logging requests like "记录变更", "log changes", "记一下今天做了什么", "记一下当前进展", or "checkpoint". The skill dynamically routes the session to lite, standard, or deep capture depth; explicit "/tracework:capture lite|standard|deep" wording overrides that route. Use day mode for "/tracework:capture day", "扫描今天的会话", "补录今天", or "capture today". Do NOT trigger when the user is simply saying goodbye or switching topics.

Configure Tracework's knowledge vault, project identity, and reporting group for first use. Use for "/tracework:cold-start-interview", "configure Tracework", "set up Tracework", "初始化 Tracework", or "配置 Tracework".

Generate or update workplace-facing daily reports from Tracework raw entries, using git only as limited fallback coverage. Supports work, personal, and private all-project scopes without mixing audiences. Use for "/tracework:daily", "更新日报", "写日报", "日报", "工作日志", "补日报", "daily note", or a dated daily work report. Do not use for agent handoff, meeting notes, generic prose reports, or git operations.

Generate a raw-first monthly management review, using Daily and Weekly reports as prior human judgments rather than semantic truth. Supports work, personal, and private all-project scopes. Use for "/tracework:monthly", "月报", "月度总结", "月度回顾", "monthly review", or monthly Daily Note archiving. Do not use for performance packaging or unsupported value claims.

Recall recent project memory at the start of an agentic coding session. Use this skill for "/tracework:recall", when the user says "开工", "session start", "start session", "recall context", "继续上次", "接着做", or asks what to remember before implementing in the current repo. Intra-project only; does not do cross-project retrieval.

Generate a narrative decision roadmap from accumulated raw entries in the Tracework knowledge vault. Use this skill for "/tracework:roadmap", when the user says "决策路线图", "decision roadmap", "项目决策历史", "decision history", "看看项目做了哪些关键决策", or when they want to understand how project decisions evolved over time. Also use this skill when the user wants to revisit abandoned alternatives, reassess past decisions, or find forgotten viable approaches.

Query Tracework's decision replay index for why a project chose a path, what alternatives were rejected, what should be revisited, what impact a decision had, or any natural-language question about project history. Use this skill for "/tracework:query", "why did we choose this?", "为什么当时这么选", "有没有被拒绝过的方案", "revisit this decision", "auth 迁移做到哪了", "我们讨论过 rate limiting 吗", or when a coding agent needs cited decision evidence before changing architecture, contracts, prompts, schemas, or product direction.

Adaptive-depth session recap and low-friction checkpoint capture for weekly reporting and decision replay. Use this skill for "/lode:capture" or when the user signals end of a work session — e.g. "收工", "今天到这", "done", "wrap up", "that's it for today", "好了", "先这样". Also trigger on explicit requests like "记录变更", "log changes", "记一下今天做了什么", "记一下当前进展", or "checkpoint". Do NOT trigger when the user is simply saying goodbye or switching topics.

Set up Lode for first use. Use this skill when the user runs "/lode:cold-start-interview", asks to configure Lode, or needs help creating a Lode config for persistent memory across sessions. Triggers on phrases like "configure Lode", "set up Lode", "初始化 Lode", "配置 Lode".

Generate or update structured Obsidian daily notes from weekly change entries and git commit history. Use this skill for "/lode:daily". Triggers on updating daily notes/work logs/diary from git commits, generating work reports from git history, filling in missing daily notes for past dates, or summarizing today's work across repos. Key phrases: "更新日报", "写日报", "日报", "工作日志", "生成工作日志", "根据git提交写日报", "补日报", "daily note", "work log", "git daily". Do NOT trigger for writing code, git operations (merge/rebase/conflict), meeting notes, or generic reports without git context.

Monthly work review from daily notes. Splits long Daily Note.md into monthly archives, extracts structured signals, and generates fact-based monthly summaries. Use this skill for "/lode:monthly" or when the user mentions: "月度总结", "月报", "月度回顾", "monthly review", "按月拆分日报", "生成本月工作总结", "工作日志整理", "月度分析". Also trigger when the user wants to review project progress, work distribution, or prepare materials for performance review from daily notes.

Query Lode's decision replay index for why a project chose a path, what alternatives were rejected, what should be revisited, what impact a decision had, or any natural-language question about project history. Use this skill for "/lode:query", "why did we choose this?", "为什么当时这么选", "有没有被拒绝过的方案", "revisit this decision", "auth 迁移做到哪了", "我们讨论过 rate limiting 吗", or when a coding agent needs cited decision evidence before changing architecture, contracts, prompts, schemas, or product direction.

Recall recent project memory at the start of an agentic coding session. Use this skill for "/lode:recall", when the user says "开工", "session start", "start session", "recall context", "继续上次", "接着做", or asks what to remember before implementing in the current repo. Intra-project only; does not do cross-project retrieval.

Generate a narrative decision roadmap from accumulated raw entries in the Lode knowledge vault. Use this skill for "/lode:roadmap", when the user says "决策路线图", "decision roadmap", "项目决策历史", "decision history", "看看项目做了哪些关键决策", or when they want to understand how project decisions evolved over time. Also use this skill when the user wants to revisit abandoned alternatives, reassess past decisions, or find forgotten viable approaches.

Convert weekly Lode raw change entries and fallback git commits into a structured Markdown PPT outline for presentation. Use this skill for "/lode:weekly". Triggers on requests like "周报", "写周报", "本周总结", "weekly PPT", "weekly report", "weekly outline", "总结这周工作", "这周做了什么", "multi-project status", "cross-project summary", "presentation outline from git". Also triggers when user wants to summarize work across repos, prepare a weekly slide deck, or consolidate development activity into a report. Supports single-project mode too. Key phrases: "周报大纲", "PPT 大纲", "本周汇报", "git 周报". Do NOT trigger for: daily notes, architecture docs, single-commit lookups, or non-git-based reporting.

Execution reliability expert. ALWAYS invoke this skill after any coding skill completes its work. Do not accept completed work without running this guard first. Use this skill to audit step execution and catch silent omissions.

Execute an approved implementation plan. Triggers after /taku-plan, or on "build this", "implement the plan", "start coding", "run the plan", "execute tasks", "写代码", "开始实现", "执行计划", "开发吧", "开始写". Also handles worktree setup on "create a worktree", "isolated environment", "new branch workspace", "创建工作树".

Use after implementation is complete. Triggers after /taku-build. Analyzes diffs for security issues, bugs, and code quality. Run when asked to "review this", "check my diff", "code review", "审查代码", "看看有什么问题", "检查一下", "准备合并", "代码质量", or before shipping. Proactively invoke when the user is about to merge or land code changes.

Clarify ambiguous development requests, new feature ideas, product/design choices, and idea-stage work before planning. Three adaptive modes: Quick (small clear changes -> fast alignment), Design (feature requests -> architecture + DESIGN.md), Explore (new ideas -> forcing questions before committing). Triggers on "add a feature", "I have an idea", "should we build", "let's design", "设计一下", "需求分析", "我有个想法", or when the user describes a desired end state but implementation choices or success criteria are not yet settled. Also handles design system creation. Bug fixes and refactors use `/taku-debug` or `/taku-review` directly unless they need fresh design decisions.

Create a recoverable active-work brief for context-heavy coding, design, debugging, review, research, or handoff sessions. Multi-mode context-control habit with resume, handoff, debug, review, design, and research policies.

When the user reports a bug, crash, error, or anything that is broken or behaving unexpectedly, invoke this skill FIRST — before writing any code or proposing any fix. This skill is the mandatory entry point for ALL bug-fix tasks. The user expects you to investigate root cause systematically before fixing. Without this skill, you will likely fix the symptom instead of the cause, which is the #1 debugging failure mode. Use this skill whenever the user says anything like: "fix this bug", "crashes", "returns null", "500 error", "not working", "wrong result", "throws exception", "timeout", "silent failure", "was working yesterday", "broke after deploy", "sometimes fails", "only in production", "works locally but not in CI/staging", "CLI crashes", "config missing", "test fails", or describes any error/stack trace. Also: "调试", "找bug", "报错", "排查问题", "不工作了", "挂了", "崩了", "数据不对". Do NOT use for: lint fixes, dependency updates, adding features, refactoring, or any task that is NOT about fixing broken behavior.

Turn an approved design into an executable implementation plan. Three-step pipeline: scope + architecture review → design review (UI only) → plan writing. Auto-detects which step to start from based on project state. Invoke when DESIGN.md exists and is approved. Triggers on "write the plan", "create implementation plan", "plan this", "review this plan", "scope check", "architecture review", "design review", "is this plan buildable", "what could go wrong", "写计划", "制定方案", "规划实施", "架构评审", "这个方案可行吗", "有什么风险", or after /taku-think completes.

User-invoked reflection. Three modes: Learn (script-backed recording, searching, pruning, exporting, and optional bootstrap for user-approved patterns, pitfalls, preferences, discoveries), Retro (weekly engineering retrospective with git commit analysis, metrics, team breakdowns, trends), and Write Skill (codify recurring learnings into reusable skills). Triggers on "what have we learned", "add learning", "show learnings", "weekly retro", "what did we ship", "engineering retrospective", "write a skill", "create a skill", "codify this pattern", "总结一下", "学到了什么", "记录一下", "回顾这周", "做个retro", "写个技能", "把这个模式固化". Also invoke when the user expresses satisfaction or frustration after completing work — these are natural reflection moments.

Render text content into a polished, shareable PNG visual. Use this skill whenever the user asks to turn words, notes, articles, quotes, arguments, stories, explicit WeChat Reading highlights/thoughts, or WeChat Reading personal statistics into an 信息图/infographic, 海报/poster, 卡片/card, 大字报, whiteboard, visual summary, comic, sketchnote, social card grid, 公众号头图, 博客封面, 正文配图, 正文解释图, 关系图, 流程图, 边界图, reading report, or non-summary editorial image for an essay. Trigger on phrases like 做成图, 渲染成图, 做张卡片, 卡片组, 做成漫画, 视觉笔记, 给文章配图, 微信读书划线做卡, 微信读书笔记, 微信读书阅读月报, article cover, blog hero, article diagram, concept map, process flow, and editorial image. Supports 9 modes: infographic, big-text poster, long-form reading card, whiteboard reasoning, multi-card poster, comic, sketchnote, editorial-image, and article-diagram. If the user mentions a restrained brand feel such as Apple, Stripe, Linear, Vercel, IBM, Notion, Claude, or similar, apply it as a visual style, not as a full brand redesign. Do not use for websites, UI components

Render text content into a polished, shareable PNG visual. Use this skill whenever the user asks to turn words, notes, articles, quotes, arguments, stories, explicit WeChat Reading highlights/thoughts, or WeChat Reading personal statistics into an 信息图/infographic, 海报/poster, 卡片/card, 大字报, whiteboard, visual summary, comic, sketchnote, social card grid, 公众号头图, 博客封面, 正文配图, 正文解释图, 关系图, 流程图, 边界图, reading report, or non-summary editorial image for an essay. Trigger on phrases like 做成图, 渲染成图, 做张卡片, 卡片组, 做成漫画, 视觉笔记, 给文章配图, 微信读书划线做卡, 微信读书笔记, 微信读书阅读月报, article cover, blog hero, article diagram, concept map, process flow, and editorial image. Supports 9 modes: infographic, big-text poster, long-form reading card, whiteboard reasoning, multi-card poster, comic, sketchnote, editorial-image, and article-diagram. If the user mentions a restrained brand feel such as Apple, Stripe, Linear, Vercel, IBM, Notion, Claude, or similar, apply it as a visual style, not as a full brand redesign. Do not use for websites, UI components

Generate or update structured Obsidian daily notes from git commit history with diff analysis. Triggers on: updating daily notes/work logs/diary from git commits, generating work reports from git history, filling in missing daily notes for past dates, summarizing today's work across repos. Key phrases: "更新日报", "写日报", "日报", "工作日志", "生成工作日志", "根据git提交写日报", "补日报", "daily note", "work log", "git daily". Do NOT trigger for: writing code, git operations (merge/rebase/conflict), meeting notes, generic reports without git context.

Multi-source research pipeline that produces a polished Chinese longform article from any of: source bundle (papers/articles/interviews/reports), technical project (GitHub repo + docs), or domain name. Auto-scouts sources when the user only has a topic. Use whenever the user asks in any language to 深入研究, 研究一下, 深度阅读, source dive, 测绘领域, 写一篇 X 的深度解析, 整理成研究文章, research, deep dive, study, or wants to understand anything from "this paper" to "this domain" deeply enough to write about it. Always triggers when the user provides URLs + analysis intent, GitHub URLs + "how does this work", or domain names + "what's the state of". Even if the user doesn't explicitly say "research" — if they share material and want to understand it deeply with a written output, use this skill.

Research an existing developer or open-source project from its repository, local files, documentation, official website, or release artifacts, identify why it matters to a specific reader, and turn it into a credible recommendation article, social post, cover, or persuasive 3:4 carousel. Use for 技术项目安利、开源项目宣传、GitHub/GitLab/Gitee 仓库介绍、Skill/CLI/框架/产品推荐、开源工具文章、社交媒体套图、小红书技术内容、项目发布配图, or when a user provides a project URL or local project folder and wants people to understand its use, value, evidence, fit, and next action. The visual output may use real project assets, typography, screenshots, diagrams, deterministic layout, or selective illustration; do not default to an all-AI-illustration series.

把任何 idea 变成一条给图像生成模型（GPT-IMAGE-2 / Nano Banana / Seedream 等）的 storyboard prompt，一次性画出整张多格故事板（3×2 / 3×3 / 4×4 / 漫画页）。用户说"分镜"/"故事板 prompt"/"storyboard"/"分镜提示词"/"出整张分镜图"/"把这个场景排成分镜"/"idea to storyboard prompt"/"分镜脚本画面"时必用。自动把 idea 拆成每格 beat，钉死美术方向保证跨格一致性，每格带镜头语言（景别+运镜+时长）。支持 6 种风格切换（铅笔电影分镜/漫画/写实电影/水墨/吉卜力/赛博朋克）。输出一条可直接粘贴的英文 text prompt，不生成图片本身，不写代码，不调 API。

全自动流水线：从技术主题的官方文档 + GitHub 源码出发，经过发现、并行分析、结构化撰写， 输出一篇完整的中文技术深度解析长文。零外部 skill 依赖，所有核心规则已内联。 当用户想要深入研究某个技术项目、框架、工具、库的内部实现时，都应该使用这个 skill， 即使用户没有明确说"写文章"。比如用户说"帮我看看 X 的架构"、"研究一下 X 的实现原理"、 "X 的源码是怎么工作的"、"深入分析 X 的设计"、"分析 X 的技术原理"、 "写一篇关于 X 的技术文章"、"深度研究 X"、"source dive X"， 或者给了一个 GitHub URL 并要求理解其内部机制，都应该触发。

智能反向面试问题推荐。根据求职者的岗位、面试轮次、面试官类型等场景，从 150+ 个问题中精选 5-8 个最适合的反向面试问题，附带提问策略和措辞建议。