Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 80 149 files from 1 774 authors, of which 62 489 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Read analyst.json and detective.json, make all editorial decisions — what the blog argues, which findings matter, narrative arc and section structure. Runs after the Analyst/Imagineer, before the Designer. No visual design. Outputs editor.md (prose) and editor.json (structure with edt_xx IDs).
Run sentence-level traceability verification on a Data2Story blog (verify.py -> verifier.json), then emit the in-page Inspector panel (the reader-facing runnable verifier) + the verify/ artifacts (verify_map.json, run_cells.json, the reproducible notebook, cell_registry.json). Mostly Python; the runnable layer recomputes each computation in-browser from its inlined data and grades it against the published output, while the bundled notebook re-executes from raw data. Use verify.py at Stage 6.4 (after validate.py, before the Critic) and generate_viewer.py at Stage 7 after the Programmer authors the verify/ files and pastes the panel shell. Triggers: a built index.html plus the role JSONs exist, or you need the traceability map / the in-page runnable verifier.
Fan out MANY candidate interactive concepts from the data + narrative — the ideation pool the Editor curates a hero + supporting set from. Deliberate over-generation: one concept per finding worth making hands-on, each declaring its archetype, purpose, what the reader produces, and an honest feasibility (node-checked against the Analyst's client_model). Builds NOTHING on-page — img_xx concepts are internal and never reach HTML. Outputs imagineer.json after the Analyst, before the Editor.
Build the curated interactive SET the Editor approved: the ONE narrative-bound hero centerpiece (an explorable/scrollytelling that makes the reader PRODUCE the lead finding) PLUS the ranked supporting playgrounds — each bound to a distinct finding — to the same three-layer-number standard, plus animation/transition craft. Consumes editor.json.interactives + imagineer.json + the Analyst's client_model. Outputs interaction.json (centerpiece + supporting[] + playtest_handoff) for the Programmer; may reach back into the Editor's spine when the lead finding should be hands-on.
Read editor.md, editor.json, analyst.json, and designer.json. Resolve chart data from analyst data_tables. Build the final index.html with data-* traceability attributes. Pure implementation — no editorial or visual decisions, no raw data access.
Data Journalist Agent (Data2Story) — orchestrator: turn a dataset into a blog. Runs detective → analyst → editor → designer → programmer → auditor → inspector in sequence. Creates a versioned project folder for each run.
Exhaustively profile a dataset and list ALL possible analyses — distributions, correlations, rankings, trends, group comparisons, anomalies. Reads detective.json for context. Outputs analyst.json with ana_xx IDs and chart-ready data_tables.
Source and VERIFY rich external media (music, high-value real photos/video) and the latest live status that the Detective's background pass didn't cover. Every asset carries a checked license + identity block; nothing unlicensed or misidentified passes downstream. Outputs scout.json (sct_xx) after the Detective, before analysis.
Detect and fix layout issues in generated HTML using visual rendering tests. Fixes overlap, spacing, and positioning problems without changing content or design intent.
Read editor.md, editor.json, and analyst.json. Make data-driven creative visual decisions for every section — teaser, charts, images, videos, audio, maps, and interactive demos when they fit the data. Generate selected assets. No HTML. Outputs designer.json with des_xx IDs.
Read analyst.json and detective.json, make all editorial decisions — what the blog argues, which findings matter, narrative arc and section structure. No visual design. Outputs editor.md (prose) and editor.json (structure with edt_xx IDs).
Research external context for a dataset — domain background, history, related studies, and why this data matters. Outputs detective.json (structured findings with det_xx IDs) before any analysis begins.
Generate music (NOT speech) via OpenRouter using Google Lyria 3 Pro.
Read editor.md, editor.json, analyst.json, and designer.json. Resolve chart data from analyst data_tables. Build the final index.html with data-* traceability attributes. Pure implementation — no editorial or visual decisions, no raw data access.
Run sentence-level traceability verification on a blog, then generate viewer.html with interactive evidence panel. No LLM needed — pure Python.
A shared reference library for editorial-grade data-visualization craft — Vega-Lite-first with a D3 fallback for charts Vega-Lite can't express. Read by the Designer at chart selection (intent → ranked chart type), the Programmer at implementation (editorial Vega-Lite recipes, annotation layers, axis/label de-clutter, encoding craft), and the Auditor/Critic for chart-quality review. It encodes the FT Visual Vocabulary intent taxonomy, the Cleveland–McGill channel-accuracy ordering, the BBC bbplot de-clutter ruleset, and colorblind-safe encoding rules. Not a pipeline stage — a craft source, like frontend-design.
Find a dataset for a Data2Story blog. Accepts a topic, a URL, or a DIP-style category. Downloads + validates against 4 completeness gates before handing off to /data2story-pro. Local-first: searches Economist/Pudding/TidyTuesday clones before going online. Supports --validate-only to audit a folder you already have.
This skill should be used whenever the user wants to develop, refine, or stress-test an idea, plan, design, research direction, product/business concept, argument, or any decision with more than one reasonable path — i.e. whenever they want a thinking partner rather than a quick answer. Trigger it when the user says things like "let's brainstorm", "help me think through this", "poke holes in my idea", "be my devil's advocate", "roast this idea", "challenge my assumptions", "sanity-check my plan", "what am I missing?", "I have a rough idea for…", or shares a half-baked concept and wants to make it better — even if they never use the word "brainstorm". It makes Claude a rigorous, anti-sycophantic sparring partner that researches just-in-time, drives the idea through Frame → Diverge → Converge → Pressure-test → Decide, asks sharp questions, and refuses to rubber-stamp. Do NOT use it for simple factual lookups, well-defined tasks with one correct answer, or when the user just wants direct execution of a clear instruction.
Reusable UI/visual-design system for building polished, distinctive, multimedia-rich self-contained HTML stories. A shared reference library that the Data2Story Designer and Programmer borrow from so every blog looks intentional and editorial rather than generic. Not a pipeline stage — a design source.
Shared UI/visual-design rule library for building polished, distinctive, multimedia-rich self-contained HTML stories. The Data2Story Designer and Programmer read it to choose a visual language (theme, type pairing, layout, components, motion) and implement it so every blog looks intentional and editorial, never templated. Use when designing or reshaping a story's look, picking fonts/colors/themes, building a hero/chart/card/map/audio component, adding motion or an interactive, or fixing a visual defect (invisible chart, overflow, broken media, AI-slop look). Not a pipeline stage — a design source consulted by other roles.
Use when you need to interactively test a nori-skillsets CLI subcommand end-to-end via tmux, with full filesystem isolation
Use when automating or testing TUI/CLI applications - provides isolated tmux sessions with scripts for input, output capture, and state verification
Use when the user asks about anything related to nori.
Refactor code to reduce cyclomatic complexity so it stays readable, maintainable, and aligned with the long-term vision of the codebase, not just optimized for AI comprehension. Use whenever the user asks to refactor, simplify, clean up, or review code quality; mentions complexity, maintainability, readability, spaghetti code, deeply nested logic, or god functions; or asks to check AI-generated code before merging. Also use proactively after writing any nontrivial function with heavy branching.
Use this skill when a user asks to diagnose, repair, clean up, recover, migrate, configure, secure, or maintain a Windows, macOS, or Linux computer. It covers system drives, app or data migration to another drive, slow or unstable machines, storage, apps, updates, networking, printers, backups, credentials, drivers, hardware, startup/WinRE, BitLocker, partitions, data recovery, developer tools, and OpenClaw setup. Do not use for general programming, software design, buying advice, or questions that do not require inspecting or changing a computer.
制作代码驱动的软件版本更新宣传片（release notes video、changelog promo）。从真实更新提炼卖点，复用产品组件和设计语言，完成分镜、代码原创配乐、动作音效、渲染与验收。
Apply small, meaning-preserving rhetorical edits to a finished academic manuscript, to counter wording-driven LLM review penalties while keeping the scientific assessment a human could make materially unchanged. Uses model-agnostic strategies from LLM reviewer preference research without querying a target reviewer. Use after ordinary writing and polishing; not for drafting or generating reviews.
用于【AI科幻】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AI科幻入口名，并明确要求优先强制加载并使用 `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【AI科幻】题材下的多平台适配策略。作为题材包装层与兼容入口，负责保留AI科幻入口名、补充异常数据、系统摩擦、数字压迫感与长期谜团在各平台的保真边界，并明确要求优先强制加载并使用 `通用-多平台小说适配`。关键词：AI科幻多平台适配、平台差异、改写前推演、平台保真。
用于【AI科幻】题材下的多平台输出 SOP 编排。作为题材包装层、兼容入口与路由层，负责保留AI科幻入口名，并明确要求优先强制加载并使用 `通用-多平台输出编排`，同时在多平台分发前先锁定母稿底盘与题材差异。支持今日头条分发。
用于【AI科幻】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AI科幻标准入口名，补充技术视角、技术针脚、数据链/系统逻辑链、长线系统谜团等题材维度，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：AI科幻竞对分析、AI科幻竞品分析、起点AI科幻榜单、标杆作品拆解、技术悬疑标杆报告。
Use when creating a full or partial set of genre wrapper skills under a genre directory. Builds `.github/skills/` subfolders and `SKILL.md` skeletons for a specified genre, keeps the `题材名-能力名` naming rule, and writes hard requirements that each genre skill must load and use its corresponding common skill when that common skill already exists.
用于审阅AI科幻人物传记。作为题材包装层与兼容入口，负责补充可证据化秘密、事件性关系网与镜头抓手等题材裁判口径，并明确要求优先强制加载并使用 `通用-审阅人物传记`。关键词：AI科幻人物审阅、可证据化秘密、关系网、心理弧线。
用于【AI科幻】题材下的去 AI 味重写。作为题材包装层、兼容入口与路由层，负责保留AI科幻标准入口名、补充程序 / 数据痕迹径、数值双轨与冷压迫来源保护边界，并明确要求优先强制加载并使用 `通用-去AI味重写`。关键词：AI科幻去AI味、模板腔、数据痕迹径、冷压迫。
用于【AI科幻】题材下的章节正文创作。作为题材包装层、兼容入口与路由层，负责保留AI科幻入口名，补充起点追读、数据追溯程序、真实编号、数字压迫感与文件写回要求，并要求生成的 `
审阅AI科幻章节正文。用于检查章内追读驱动、中段回报、章末钩子、人物传记一致性、公平推理、数据链、时间表达与作者管理编号出戏风险，并输出可落库、可回写的章节审阅报告。
审阅AI科幻小说分部大纲、分卷大纲、章清单与单元案执行版。核心要求是：分部/分卷大纲必须把上一级分配给本层的内容切实、全量、保质落地。分部审阅要核查总纲层文件组分配给本部的全部内容是否已落地；分卷审阅要按是否存在分部，分别核查其是否完整落地总纲层或分部层分配内容。关键词：分部审阅、分卷审阅、单元案审阅、节奏布点、钩子策略、章清单审阅。
审阅AI科幻小说总大纲、全书总纲、故事多面体、主线谜团与单元案矩阵。这里的“总大纲”默认指总纲层文件组，而非单一文件；至少包括 `小说总大纲.md`、`故事面/`、`伏笔与回收总纲.md`、`故事多面体大纲.md`，以及其它相关总表级大纲文件。用于审阅总纲层 Canon 文件及其联动关系。关键词：总纲审阅、总大纲、全书审阅、机制递进、单元案矩阵、总纲报告。
用于【AI科幻】题材下的章末钩子强化。作为题材包装层与兼容入口，负责保留AI科幻入口名、补充未完成动作、新变量入场、更糟后果与订阅级驱动口感，并明确要求优先强制加载并使用 `通用-强化章末钩子`。关键词：AI科幻章末钩子、转折、揭露、危机、下一章驱动。
用于审阅AI科幻故事设定、手法、系统逻辑链与数据痕载体文档。作为题材包装层与兼容入口，负责补充异常数据、系统摩擦与技术代价等题材裁判口径，并明确要求优先强制加载并使用 `通用-审阅故事设定`。关键词：AI科幻设定审阅、系统逻辑链、数据痕载体、规则代价。
用于【AI科幻】题材下的项目级战略初始化——在选定平台后、设计大纲之前，补充AI科幻特有的技术切口、异常数据体系、数字空间压迫感、技术代价锚点与平台适配偏好。作为题材包装层与路由层，强制加载并使用 `通用-小说项目初始化`。
用于【AI科幻】题材下以默认极严、保守、负面证据优先的口径评估作品在{目标平台}的签约、过稿与连载潜力。作为题材包装层与路由层，负责保留AI科幻标准入口名，并明确要求优先强制加载并使用 `通用-平台签约评估框架`。关键词：AI科幻签约评估、极严评估、签约概率评估、过稿潜力、总纲闸门预评估、分卷闸门预评估、正文准入评估、竞品威胁评估。
用于【AI科幻】题材下的章节开头强化。作为题材包装层与兼容入口，负责保留AI科幻入口名、补充冷开场、异常触发、技术针脚与即时动作压力口感，并明确要求优先强制加载并使用 `通用-强化章节开头`。关键词：AI科幻开头强化、冷开场、异常触发、首屏留存。
用于【AI科幻】题材下的多平台母稿提纯。作为题材包装层与兼容入口，负责保留AI科幻入口名、补充异常数据、系统摩擦、数字压迫感与长期谜团的底盘保真，并明确要求优先强制加载并使用 `通用-提纯多平台母稿`。关键词：AI科幻母稿提纯、多平台底稿、数据链、平台可分化。
用于【AI科幻】题材下的微空间或受限空间场景施工。作为题材包装层、兼容入口与路由层，负责保留AI科幻标准入口名、补充受限数字空间、技术针脚、规则代价与数据痕迹回收口径，并明确要求优先强制加载并使用 `通用-执行微空间受限场景`。关键词：AI科幻微空间、系统机房、电梯井、系统监控室、数据存储区、贴脸技术惊悚。
用于【AI科幻】题材下的场景单元施工、章节微型剧本与抓眼开场。作为题材包装层、兼容入口与路由层，负责保留AI科幻标准入口名、补充数字空间压迫、系统阻力与数据痕迹入场口感，并明确要求优先强制加载并使用 `通用-执行场景单元`。关键词：AI科幻场景单元、系统界面、数据面板、服务器机房、数字日常异化。
用于【AI科幻】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AI科幻入口名、补充技术现实压迫、异常数据与人性代价的推荐话术，并明确要求优先强制加载并使用 `通用-撰写书评`。支持今日头条平台。
用于【AI科幻】题材下的审讯、试探、争执、谈判与规则对峙场景。作为题材包装层、兼容入口与路由层，负责保留AI科幻入口名、补充职业语体与程序压迫，并明确要求优先强制加载并使用 `通用-执行对话冲突`。
用于【AI科幻】题材下的作者有话说润色。作为题材包装层与兼容入口，负责保留AI科幻入口名，补充“一粒城市微细节 + 一点后怕或冷笑 + 一个轻追问”的章后口感，并明确要求优先强制加载并使用 `通用-润色作者有话说`。关键词：AI科幻作者有话说、读者向小剧场、余波、轻悬念。
用于【AI科幻】题材下的正文润色。作为题材包装层、兼容入口与路由层，负责保留AI科幻标准入口名、补充有限视角、数据链、系统阻力与数字压迫感裁判边界，并明确要求优先强制加载并使用 `通用-正文润色`。关键词：AI科幻正文润色、有限视角、数据链、系统阻力、代入感。
用于【AI科幻】题材下的内容简介撰写、压缩与适配。作为题材包装层、兼容入口与路由层，负责保留AI科幻入口名、补充题材卖点与持续承诺，并明确要求优先强制加载并使用 `通用-撰写内容简介`。支持今日头条平台。
用于【AI科幻】题材下的投稿材料组包、起点内投整包与补件审计。作为题材包装层、兼容入口与路由层，负责保留AI科幻入口名，补充技术抓手、数据痕迹常、系统摩擦、长期谜团与起点男频裁判口径，并明确要求优先强制加载并使用 `通用-组包投稿材料`。
用于【AI科幻】题材下的单元案、事件母板与技术事件供血设计。作为题材包装层与路由层，负责保留AI科幻标准入口名，并明确要求优先强制加载并使用 `通用-设计事件案件引擎`。
用于【AI科幻】题材下的章节控制卡生成。作为题材包装层、兼容入口与路由层，负责保留AI科幻入口名、补充主线推进、数据痕迹场、系统阻力与危险升级口径，并明确要求优先强制加载并使用 `通用-生成章节控制卡`。关键词：AI科幻控制卡、主线推进、数据痕迹场、中段回报、危险升级。
用于【AI科幻】题材下的连续性、旧线回收与冷热线管理。作为题材包装层、兼容入口与路由层，负责保留AI科幻入口名、补充旧案回声、关系余波、数据链不断点与回归压力判断，并明确要求优先强制加载并使用 `通用-管理连续性冷热线`。关键词：AI科幻连续性、旧线回收、冷热线、回归窗口、数据链不断点。
用于【AI科幻】题材下的章节创作 SOP 编排。作为题材包装层、兼容入口与路由层，负责保留AI科幻入口名，并明确要求优先强制加载并使用 `通用-章节创作闭环`，同时锁定题材写作链、程序数据痕迹续性、数字压迫感与批量回炉护栏。
设计AI科幻小说分部大纲、分卷大纲、卷纲、章清单与章节微型剧本。核心要求是：分部/分卷大纲必须把上一级大纲分配给本层的内容切实、全量、保质落地。分部大纲要承接总纲层文件组分配给本部的全部内容；分卷大纲在无分部小说中按分部口径承接总纲层分配内容，在有分部小说中承接本部分配给本卷的全部内容。覆盖：分部、分卷、卷纲、章纲、章清单、故事线、情节块、故事点、卷级启动表、爽点布点表、章节钩子链、反AI味、技术锚点、移动端可读性。
用于【AI科幻】题材下的人物传记设计与重写。作为题材包装层、兼容入口与路由层，负责保留AI科幻入口名、补充可证据化秘密、镜头抓手、风险边界与程序口径，并明确要求优先强制加载并使用 `通用-设计人物传记`。关键词：AI科幻人物传记、可证据化秘密、镜头抓手、人物裁判源。
用于【AI科幻】题材下的封面生图提示词设计。作为题材包装层、兼容入口与路由层，负责保留AI科幻入口名、补充数字压迫感、异常数据、人物危险感与平台展示边界，并明确要求优先强制加载并使用 `通用-设计封面生图提示词`。关键词：AI科幻封面提示词、城市压迫、异常数据、平台展示。
设计AI科幻小说总大纲、全书总纲、故事多面体、主线谜团面与单元案矩阵。这里的“总大纲”默认指总纲层文件组，而非单一文件；至少包括 `小说总大纲.md`、`故事面/`、`伏笔与回收总纲.md`、`故事多面体大纲.md`，以及其它相关总表级大纲文件。用于创建、重写、修改总纲层 Canon 文件及其联动关系。覆盖：总大纲、总纲、全书、故事面、M0、X01、单元案矩阵、钩子链、反AI味、技术锚点、缺陷型主角、总纲模板、总纲审计。
Claude Skills — questions
Answers built from the skills we actually parsed.