← all publishers

nangongwentian-fe

@nangongwentian-fe source repo

Report this profile Claim this profile

• 13 skills
• 0 followers
• 17 hours ago last updated

1. ▌
   Buddy Reroll · nangongwentian-fe bundle

   Reroll your Claude Code buddy (companion) to get a specific species, rarity, or shiny variant. Use when the user says "reroll buddy", "change my buddy", "I want a shiny buddy", "give me a legendary dragon", "/buddy-reroll", or any request to customize their Claude Code companion pet.
   0
   installs
2. ▌
   Codex Imagegen · nangongwentian-fe bundle

   Generate AI images (photos, illustrations, concept art, product shots, game assets, UI mockups, posters, textures, sprites, stickers) by delegating to Codex CLI's built-in image_gen tool. Use this skill whenever the user asks to generate, create, or make any AI-generated bitmap image in Claude Code — including requests like 'generate an image', 'create a photo of', 'make an illustration', 'design a poster', 'draw a picture', 'generate a product shot', 'create concept art', 'make a logo', 'create a thumbnail', 'generate a hero image', or any visual asset request that needs AI image generation rather than code-based SVG/HTML. Also trigger when the user says '生成图片', '画一张图', '做个海报', '生成一张照片', '帮我画', '生成插画'. Do NOT trigger for editing existing SVG/vector files, creating HTML/CSS layouts, or generating diagrams/flowcharts (those are better handled by code or other tools).
   0
   installs
3. ▌
   Show Dont Tell · nangongwentian-fe bundle

   信息可视化呈现行为准则。当模型回复中包含对比、步骤、配置、架构等结构化信息时自动激活，确保优先使用表格、代码块、列表、树形结构等可视化格式，而不是纯文字堆砌。触发词：「用表格」「画个图」「列个表」「结构化一下」「别光用文字」「可视化」「对比一下」。即使没有触发词，只要回复中包含适合可视化的结构化信息，本 skill 的规则就应生效。也适用于：「太多字了看不下去」「能不能更直观一点」「整理成表格」等场景。
   0
   installs
4. ▌
   Sync Skill To Jay · nangongwentian-fe bundle

   Publish a newly created or updated Agent Skill through the jay-skills repository, then reinstall the published version into the canonical global skills directory. Use after a Skill change when the user wants to validate, document, commit, push, and install it. Do not publish private or local-only Skills without explicit approval.
   0
   installs
5. ▌
   Daily Work Summary · nangongwentian-fe bundle

   根据指定 Git 仓库和日期，仅从提交作者为用户本人的 commit、提交正文、文件变更及必要的 diff 中提炼每日工作内容。用于用户要求按项目和日期生成日报、每日工作总结、根据 Git commit 总结工作，或要求用 1、2、3 编号列出某天或某段日期完成事项的场景。
   0
   installs
6. ▌
   Split UI Components · nangongwentian-fe bundle

   Analyze, plan, implement, and review frontend UI component boundaries across component-based frameworks, with React-specific guidance. Use when Codex is asked to split or refactor components, review oversized or over-abstracted UI, decide state ownership, extract Hooks or Composables, design component APIs, preserve behavior during UI refactors, or handle requests about 组件拆分、组件边界、前端重构、过大组件或过度抽象.
   0
   installs
7. ▌
   Web Content Fetcher · nangongwentian-fe

   获取公开网页的正文或 Markdown 内容。当用户要求抓取链接、读取文章、提取网页正文、将页面转为 Markdown，或获取 X/Twitter、微信、知乎、Medium 等公开页面的文字内容时使用。支持在直接抓取失败或内容不完整时，通过内容提取代理和网页搜索逐级回退；不适用于需要登录的页面、付费墙绕过、媒体下载或结构化数据抓取。
   0
   installs
8. ▌
   Git Topic Commit Push · nangongwentian-fe bundle

   Create one or more Git commits grouped by coherent change topic, then push the current branch. Use when the user asks to commit and push, submit by topic, split current changes into topical commits, or do "按照主题提交 commit 并 push"; especially when a worktree has mixed staged, unstaged, or untracked changes that need honest commit boundaries before `git push`. Commit messages must be written in Chinese unless the user explicitly requests another language.
   0
   installs
9. ▌
   Clean Wechat Wps Storage · nangongwentian-fe bundle

   Clean local disk usage from WeChat/微信 and WPS Office on macOS. Use when the user says WeChat, Weixin, 微信, WPS, or WPS Office takes too much space, asks what can be cleaned, wants to clear chat records, chat images, videos, emojis, caches, cloud-document caches, plugins, fonts, logs, or wants an interview-confirm-plan-clean workflow before moving app data to Trash.
   0
   installs
10. ▌
    Post Task Learning Review · nangongwentian-fe bundle

    Review a completed or nearly completed non-trivial task and directly maintain durable lessons across project docs, memory, existing skills, or new skills without asking for separate confirmation. Use after complex debugging, deployment, live verification, repo documentation work, repeated workflow discovery, creating or updating a skill, or when the user asks whether anything is worth remembering, updating, or deleting.
    0
    installs
11. ▌
    Progressive Disclosure Docs · nangongwentian-fe bundle

    Design, create, split, or revise Markdown/project documentation using progressive disclosure so agents and humans can find the right level of detail without context bloat. Use when writing docs, README files, runbooks, architecture notes, deployment guides, troubleshooting docs, rules, skills, or when deciding whether content belongs in an existing document or should become a new document.
    0
    installs
12. ▌
    Maintainable Frontend Styles · nangongwentian-fe bundle

    Implement, review, and refactor maintainable styles for React, Next.js, and Vite applications. Use when choosing between Tailwind CSS, CSS Modules, SCSS Modules, global CSS, and inline styles; creating component variants or reusable style compositions; splitting oversized .module.scss files; removing raw global component CSS; or reviewing frontend style architecture, specificity, responsiveness, theming, and accessibility.
    0
    installs
13. ▌
    Post Implementation Review Gate · nangongwentian-fe bundle

    Use after completing a non-trivial implementation and before final handoff, especially for public API/schema compatibility, database or migration work, authentication/security, deployment/configuration, concurrency or data integrity, algorithmic or control-flow complexity, cross-module refactors, runtime lifecycle, and rendered UI behavior. Make sure to invoke this skill even when the user asks only to implement or fix something and does not explicitly request review. Risk-classify the completed change, use a new isolated read-only subagent for review-triggering changes when delegation is allowed, otherwise perform and disclose a local fallback, verify findings, fix authorized in-scope defects, rerun relevant checks, and report residual risks. Do not use for planning, answer-only or diagnosis-only tasks, trivial text edits, mechanical formatting, or tasks with no implementation-artifact change.
    0
    installs