KKenny0
UserContent in, PNG out. A Claude Code skill that renders text into designed images — 7 modes, 18+ brand design systems, print-quality aesthetic.
Categories
Indexed Skills (15)
card-skill
Convert text content into a designed PNG image. Renders articles, quotes, notes, or any text as an infographic, poster, visual card, mockup, or styled graphic — using 18 brand design systems (Apple, Stripe, Linear, Vercel, IBM, Notion, etc.) + 8 content tones (26 total), and 7 visual modes: infographic, big-text poster, long-form reading, whiteboard reasoning, multi-card grid, comic, sketchnote. Use this skill whenever the user wants to turn text into a shareable visual: making an 信息图/infographic/海报/卡片/设计稿 from content, applying a specific brand visual style to text (e.g. '用 Stripe 风格', 'Apple aesthetic'), creating social media graphics or Instagram card grids from articles, rendering a visual summary, making a comic or sketchnote from a story. Triggers on: 做成图, 渲染成图, 做成海报, 做张卡片, 卡片组, 信息图, 设计稿, 做成漫画, 视觉笔记, 大字报, whiteboard, visual summary, brand style, mockup. Do NOT use for: writing HTML/CSS/React code, building websites or UI components, creating Figma prototypes, designing logos or VI identity systems, plot
debate
辩证推理 — 通过扬弃达到更高层次理解，不是罗列正反方。输入主张、争议、Source Brief Disputes 或 Synthesis Pack Conflicts，输出结构化辩证记录（钢铁侠建构 → 反题 → 扬弃）。当用户想要辩证分析争议、钢��侠论证、压力测试主张、"把问题辩一辩"、或理解对立观点各抓住了什么时使用。
deep-read
深度阅读非技术素材，输出完整研究文章。四阶段流水线：捕获→精读→综合→撰写。素材类型：论文（arxiv、期刊）、书籍章节、新闻报道、长文、访谈记录、行业报告、政策文件。一个 skill 从头到尾完成，不依赖外部 skill。当用户想要：深度阅读论文、研究非技术主题、把多份素材综合成文章、对论文做深度解析、把报告整理成研究文章、综合分析多份素材、理解一篇论文的核心思想并写成文章、深度研究某个话题（社会现象、商业模式、理论框架等非代码主题）时，都应该触发。即使用户只说"分析这篇论文"或"帮我读一下这个"——只要素材不是代码或技术项目，就应该用 deep-read 而不是其他 skill。用户分享论文 PDF/URL、arxiv 链接、报告文件并要求分析时，一律触发。不触发：GitHub URL / 源码分析 / 技术框架深度解析 → source-dive；纯 URL 抓取不分析 → read skill；vault 维护 → loom-maintain。
excavate
假设考古 — 挖掘主张下的隐藏假设和未审视前提。输入 Source Brief、Topic Note、URL 或主张，输出结构化挖掘报告（表层主张 → 推理结构 → 隐藏假设 → 根基评级）。当用户想要挖掘假设、找隐藏前提、质疑"常识"、理解"这个论点默认了什么"、或分析观点站不站得住时使用。
forge
概念锻造 — 跨域发现新概念连接，不是总结。输入 2+ 个 Source Brief、Topic Note、URL 或文本，输出锻造图（原子分解 → 跨域映射 → 碰撞 → 锻造产物）。当用户想要连不同领域想法、找结构性相似、创造新隐喻或框架、跨域知识迁移、或"把这些东西碰撞一下"时使用。
loom-maintain
Validate, migrate, discover connections, generate evolution summaries, create Topic Notes, and rebuild indexes for a Loom vault. Use when the user asks to check vault health, migrate a legacy vault, find cross-topic connections, generate evolution reports, create or update Topic Notes, or rebuild indexes.
capture
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.
cold-start-interview
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".
daily
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
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
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
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.
roadmap
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.
weekly
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.
source-dive
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。
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.