xyaz1313/xyskill / skills/xy-atomize
xy-atomize
Verified【原子入库】把本地内容资产抽成 XY 原子入库——指定一个目录(文稿/逐字稿/推文/课件),按原子标准抽成 jsonl 写进 incoming/:先审计、抽 3 篇样本过用户确认、再批量、去重、验收,最后提示 build_atoms 入库。用户说「把这些稿子做成原子」「把我的逐字稿入库」「批量提炼观点」时使用。|小爷出品
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 13.6 KB |
| agents/openai.yaml | config | 306 B |
| evals/evals.json | config | 1.6 KB |
| references/atoms.jsonl | other | 8.6 KB |
| scripts/validate_batch.pyexecutable | script | 6.2 KB |
references/atoms.jsonl
View on GitHub{"id": "RZP-020b", "type": "number", "confidence": "high", "topics": ["私域运营", "商业案例与实战复盘"], "knowledge": "实体店叠加私域的增效案例:月租5万的服装店原本线下月销稳定在20万,接入私域运营后可能提升到40-50万,增量部分几乎不增加固定成本,只多花一两个人工去私聊客户", "source_type": "course", "source_label": "认知篇", "chapter": "认知篇", "section": "万物皆可私域", "blocks": ["13-1", "08-7"], "skills": ["xy-atomize", "xy-biz-scan", "xy-close", "xy-private-ops"], "related": null, "q": 5}
{"id": "RZP-011", "type": "case", "confidence": "high", "topics": ["私域运营", "商业案例与实战复盘"], "knowledge": "百果园是实体店直营基因做私域的样板案例:客户进店消费加微信→通过客户完成社区团购拼单→分发销售送货,全国可查证的成功范例", "source_type": "course", "source_label": "认知篇", "chapter": "认知篇", "section": "什么是真正的私域", "blocks": ["13-1", "08-7"], "skills": ["xy-atomize", "xy-biz-scan", "xy-precedent", "xy-private-ops"], "related": null, "q": 4}
{"id": "XY-DY3-008", "type": "method", "confidence": "medium", "topics": ["IP人设", "AI与工具"], "knowledge": "AI 时代任何公开出镜的 IP 都可以被\"蒸馏\"成一个 skill:把他所有视频做语音转文字,喂给 AI 尽量深地拆解分析他的洞察和表达,再封装成 skill——连童锦程这样的主播都已经有人做成 skill 挂在开源平台上。这件事去年就有人在做,本质是把一个 AI agent 直接蒸馏成 skill。两面看:想学谁就能克隆谁的方法论,所有人在 AI 面前平权了;反过来,你自己发过的全部公开视频,也是随时可能被别人蒸馏走的资产。", "source_type": "account_video", "source_label": "小爷账号-口播补挖", "chapter": null, "section": "童锦程祖师爷SKILL你们见过吗", "blocks": ["07-3", "06-9"], "skills": ["xy-ai-workflow", "xy-atomize", "xy-ip"], "related": null, "q": 3}
{"id": "XY-DY-008", "type": "principle", "confidence": "high", "topics": ["合规与风控"], "knowledge": "账号/工具账号被封不是核心风险,只要把每次工作成果持续沉淀进知识库,账号本身是可替换的消耗品;真正该担心的是没有用账号产出真正的知识资产", "source_type": "account_video", "source_label": "账号内容", "chapter": null, "section": null, "blocks": ["08-8", "12-2"], "skills": ["xy-atomize", "xy-ops", "xy-publish-guard"], "related": null, "q": 2}
{"id": "XY-MA-141", "type": "method", "confidence": "high", "topics": ["认知与心态", "内容创作与平台", "AI与工具"], "knowledge": "持续输出原创内容有两个前提:一是日常养成积累知识和观点的习惯,素材来源可以是读书、刷视频,或和AI对话中被触动的点,把这些积累整理归档成结构化的本地笔记库;据经验,积累到约200条观点或语料时,基本就足以支撑围绕任意话题输出言之有物的内容,且这个积累过程会随着熟练度提升而越写越快;二是要对自己每条内容的可传播范围建立客观预期,主动跳出自己的专业视角,判断不同话题各自能触达的人群体量,避免把某条内容流量差的原因简单归咎为'做了原创'。", "source_type": "adapted_other", "source_label": "外部方法论·内化改写", "chapter": null, "section": null, "blocks": ["12-2", "06-9"], "skills": ["xy-ai-workflow", "xy-atomize", "xy-content-scan"], "related": null, "q": 3}
{"id": "XY-MC-0305", "type": "method", "confidence": "high", "topics": ["内容创作与平台", "AI与工具"], "knowledge": "在处理大量既有素材时,应采取“非破坏性”的提取策略:即在原始素材库之外新建文件夹或输出文件结构,将提取出的观点与案例存储在独立路径中,以防干扰原始文档。", "source_type": "adapted_course", "source_label": "外部方法论·内化改写", "chapter": null, "section": null, "blocks": ["12-2"], "skills": ["xy-ai-workflow", "xy-atomize", "xy-content-scan"], "related": null, "q": 2}
{"id": "XY-MC-0306", "type": "method", "confidence": "high", "topics": ["内容创作与平台", "AI与工具"], "knowledge": "在利用现有素材进行内容创作时,应建立独立的素材库结构,通过新建文档进行观点与案例的提取,以确保原始素材文件的完整性与原始文档不被干扰。", "source_type": "adapted_course", "source_label": "外部方法论·内化改写", "chapter": null, "section": null, "blocks": ["12-2", "06-9"], "skills": ["xy-ai-workflow", "xy-atomize", "xy-content-scan"], "related": null, "q": 2}
{"id": "XY-MD-029", "type": "insight", "confidence": "high", "topics": ["AI与工具"], "knowledge": "大模型的本质是一个搜索机器人:它擅长从海量素材里检索并重组,不擅长凭空创造。所以用 AI 的第一步永远是建自己的素材库;知识库不是存资料的地方而是回答问题的系统,每传一批内容就同步维护索引(有哪些观点、对应什么问题、引用时怎么定位)。", "source_type": "adapted_book", "source_label": "外部方法论·内化改写", "chapter": null, "section": null, "blocks": ["12-2", "12-3"], "skills": ["xy-ai-workflow", "xy-atomize", "xy-ip", "xy-vault"], "related": null, "q": 2}
{"id": "XY-MA-1485", "type": "principle", "confidence": "high", "topics": ["内容创作与平台", "AI与工具"], "knowledge": "看到值得学习的博主或值得拆解的内容时,不要只靠截图、收藏、手动复制,而要尽量把它变成可保存、可检索、可复盘的文本资料。只有变成文本,后续才能交给AI做拆解、归类、总结和二次创作;否则收藏再多视频也只是躺在收藏夹里,无法真正成为素材库。", "source_type": "adapted_other", "source_label": "外部方法论·内化改写", "chapter": null, "section": null, "blocks": ["12-2", "06-10"], "skills": ["xy-ai-workflow", "xy-atomize", "xy-content-scan", "xy-ip", "xy-peer-pick"], "related": null, "q": 1}
{"id": "XY-MA-1487", "type": "method", "confidence": "high", "topics": ["AI与工具"], "knowledge": "素材库中每条对标内容应按统一字段保存:标题、平台、博主、原始链接、发布时间、正文/口播文案或逐字稿。统一字段是后续检索、归类和交给AI批量分析的前提。", "source_type": "adapted_other", "source_label": "外部方法论·内化改写", "chapter": null, "section": null, "blocks": ["12-2", "06-10"], "skills": ["xy-ai-workflow", "xy-atomize", "xy-content-scan", "xy-ip", "xy-peer-pick", "xy-traffic"], "related": null, "q": 1}
{"id": "XY-MC-0068", "type": "method", "confidence": "high", "topics": ["IP人设", "内容创作与平台", "AI与工具"], "knowledge": "通过“负反馈规则积累”方法,将人类对AI输出的不满意点转化为结构化的写作规则。通过“AI文案 + 不满意原因 + 规则定义(名字、解释、例句)”的闭环,让AI规模化复制个人的内容风格,避免千人一面的模板化输出。", "source_type": "adapted_course", "source_label": "外部方法论·内化改写", "chapter": null, "section": null, "blocks": ["06-11", "12-3"], "skills": ["xy-ai-workflow", "xy-atomize", "xy-content-scan", "xy-ip"], "related": null, "q": 1}
{"id": "XY-MD-027", "type": "principle", "confidence": "high", "topics": ["内容创作与平台", "AI与工具"], "knowledge": "规模化产出靠系统不靠努力:输入端建素材库(选题库、金句库、案例库、对标库),处理端走固定流程,输出端一稿适配多平台。系统保证下限(每条及格),人负责上限(判断与创造);系统不是设计出来的,是被问题逼着长出来的。", "source_type": "adapted_book", "source_label": "外部方法论·内化改写", "chapter": null, "section": null, "blocks": ["06-10", "12-4"], "skills": ["xy-ai-workflow", "xy-atomize", "xy-content-scan", "xy-peer-pick", "xy-vault"], "related": null, "q": 1}
{"id": "XY-MD-030", "type": "principle", "confidence": "high", "topics": ["认知与心态", "AI与工具"], "knowledge": "AI 时代创作者的护城河不是内容是知识编码:把隐性经验变成显性规则、把方法论做成 AI 能执行的标准。内容会被 AI 吸收重组超越,但 AI 学不了你的经历、模仿不了你的判断、复刻不了你创造方法的过程。", "source_type": "adapted_book", "source_label": "外部方法论·内化改写", "chapter": null, "section": null, "blocks": ["12-2"], "skills": ["xy-ai-workflow", "xy-atomize", "xy-peer-pick"], "related": null, "q": 0}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |