Web Artifacts Builder
anthropics/skills
Builds multi-component claude.ai HTML artifacts as a small React, TypeScript and Tailwind project, then bundles it into one shareable HTML file.
OpenPrd 前端设计框架 skill:为界面、页面、视觉、样式和前端体验任务提供设计资产框架、审美立意、反 AI 味门禁和实现前方向评审规则。
$ npx skills add DavidLam-oss/obsidian-wechat-converter --skill openprd-frontend-design -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install DavidLam-oss/obsidian-wechat-converter openprd-frontend-design --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/DavidLam-oss/obsidian-wechat-converter.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/openprd-frontend-design .claude/skills/openprd-frontend-design && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "openprd-frontend-design" agent skill from https://github.com/DavidLam-oss/obsidian-wechat-converter/tree/main/.codex/skills/openprd-frontend-design into .claude/skills/openprd-frontend-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openprd-frontend-design", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/DavidLam-oss/obsidian-wechat-converter/tree/main/.codex/skills/openprd-frontend-designType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add DavidLam-oss/obsidian-wechat-converter --skill openprd-frontend-design -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install DavidLam-oss/obsidian-wechat-converter openprd-frontend-design --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DavidLam-oss/obsidian-wechat-converter.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.codex/skills/openprd-frontend-design .agents/skills/openprd-frontend-design && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "openprd-frontend-design" agent skill from https://github.com/DavidLam-oss/obsidian-wechat-converter/tree/main/.codex/skills/openprd-frontend-design into .agents/skills/openprd-frontend-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openprd-frontend-design", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add DavidLam-oss/obsidian-wechat-converter --skill openprd-frontend-design -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install DavidLam-oss/obsidian-wechat-converter openprd-frontend-design --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DavidLam-oss/obsidian-wechat-converter.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.codex/skills/openprd-frontend-design .cursor/skills/openprd-frontend-design && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "openprd-frontend-design" agent skill from https://github.com/DavidLam-oss/obsidian-wechat-converter/tree/main/.codex/skills/openprd-frontend-design into .cursor/skills/openprd-frontend-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openprd-frontend-design", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/DavidLam-oss/obsidian-wechat-converter.git --path .codex/skills/openprd-frontend-design--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add DavidLam-oss/obsidian-wechat-converter --skill openprd-frontend-design -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install DavidLam-oss/obsidian-wechat-converter openprd-frontend-design --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DavidLam-oss/obsidian-wechat-converter.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.codex/skills/openprd-frontend-design .gemini/skills/openprd-frontend-design && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "openprd-frontend-design" agent skill from https://github.com/DavidLam-oss/obsidian-wechat-converter/tree/main/.codex/skills/openprd-frontend-design into .gemini/skills/openprd-frontend-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openprd-frontend-design", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install DavidLam-oss/obsidian-wechat-converter openprd-frontend-designInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add DavidLam-oss/obsidian-wechat-converter --skill openprd-frontend-design -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/DavidLam-oss/obsidian-wechat-converter.git skills-src && mkdir -p .github/skills && cp -r skills-src/.codex/skills/openprd-frontend-design .github/skills/openprd-frontend-design && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "openprd-frontend-design" agent skill from https://github.com/DavidLam-oss/obsidian-wechat-converter/tree/main/.codex/skills/openprd-frontend-design into .github/skills/openprd-frontend-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openprd-frontend-design", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add DavidLam-oss/obsidian-wechat-converter --skill openprd-frontend-design -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install DavidLam-oss/obsidian-wechat-converter openprd-frontend-design --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DavidLam-oss/obsidian-wechat-converter.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.codex/skills/openprd-frontend-design .opencode/skills/openprd-frontend-design && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "openprd-frontend-design" agent skill from https://github.com/DavidLam-oss/obsidian-wechat-converter/tree/main/.codex/skills/openprd-frontend-design into .opencode/skills/openprd-frontend-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openprd-frontend-design", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
openprd-frontend-designOpenPrd 前端设计框架 skill:为界面、页面、视觉、样式和前端体验任务提供设计资产框架、审美立意、反 AI 味门禁和实现前方向评审规则。
Openprd Frontend Design is an agent skill from DavidLam-oss/obsidian-wechat-converter. OpenPrd 前端设计框架 skill:为界面、页面、视觉、样式和前端体验任务提供设计资产框架、审美立意、反 AI 味门禁和实现前方向评审规则。
Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/design-asset-contract.md` and `references/direction-engine.md`).
It sits in Frontend & Design. The repository describes itself as: Obsidian 公众号排版(支持自定义 CSS和公众号贴图)、飞书云同步与多平台(小红书、知乎等)发布插件。Markdown 转微信文章 / Feishu docs / 知乎、小红书、今日头条等草稿,支持数学公式、本地图片、GIF 和 Mermaid。 The licence is MIT.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 3fef612. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Openprd Frontend Design loads about 2.7k tokens when it runs, and up to ~4.3k if it reads all its reference files. Until then it costs about 24 tokens; SKILL.md has 595 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from DavidLam-oss/obsidian-wechat-converter at commit 3fef612, republished under its MIT licence (© DavidLam-oss). 595 words, ~2,727 tokens.
.claude/skills/openprd-frontend-design/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.<!-- OPENPRD:GENERATED
adapter=codex
source=openprd-frontend-design
version=0.1.19
checksum=c1dce7f1b79de34b
-->
当任务涉及界面、页面、视觉、样式、组件层级、信息架构、内容型页面或前端体验时,使用这份 skill。
如果任务会新建界面、结构性改变信息架构/核心布局/视觉系统,或后续要交给 Impeccable,实现前同时读取 skills/openprd-ui-context/SKILL.md。由 UI Context 负责 greenfield/brownfield 项目理解、三个专业方向、用户确认以及 PRODUCT.md/DESIGN.md 编译;本 skill 继续提供审美资产框架与反模板化门禁。低风险局部修正使用 UI Context 的 local-fix 路径,不重复冻结完整合同。
.openprd/design/README.md.openprd/design/templates/README.mdskills/openprd-frontend-design/references/design-asset-contract.mdskills/openprd-frontend-design/references/direction-engine.md如果当前工作区本来就有现成前端结构,或你明确需要偏离模板默认组合,再读:
.openprd/design/lenses/frontend-lenses.md.openprd/design/themes/theme-catalog.json.openprd/design/layouts/layout-catalog.json.openprd/design/components/component-catalog.md.openprd/design/checklists/ui-quality-gate.md.openprd/design/anti-slop.md如果本轮已经进入实现准备,再读:
.openprd/design/active/facts-sheet.md.openprd/design/active/asset-spec.md.openprd/design/active/image-preflight.md.openprd/design/active/direction-plan.md.openprd/design/active/selected-direction.mdlens,明确这次界面的视觉判断角度。theme、一个 layout skeleton 和一个 recipe,并说明它们如何服务上面的审美立意。facts-sheet.md。asset-spec.md,并记录字体、色彩、动效、背景/表面这些审美资产。image-preflight.md。direction-plan.md,明确 3 个异源方向;每个方向都要有不同审美主张和记忆点。selected-direction.md,把选中的 lens、theme、layout、组件、审美主张、记忆点和风险锁定。starter / lens / theme / layout 只作为实现加速器,不作为高于参考图的裁决源。openprd run . --context --message <用户原话>,不要先跑不带 message 的 run --context。design-starter 后,立即进入 Patch Mode:把生成的入口文件当成稳定基座,在同一路径里细化结构、内容、样式和交互。.openprd/design/checklists/ui-quality-gate.md 和 .openprd/design/anti-slop.md 做自检。如果当前工作区几乎没有前端入口文件,或只有 .openprd/ 与说明文档:
openprd run . --context 看建议路径;如果当前轮用户已经把页面主题、模块范围或“直接实现”的意图说清,优先带 --message <用户原话>,让建议基于当前请求,而不是只看空白工作区状态。clarify-user 但用户原话已足够明确,不要继续长时间翻 docs/basic/ 占位文档。.openprd/design/active/facts-sheet.md、asset-spec.md、image-preflight.md、direction-plan.md、selected-direction.md 写成具体内容;如果当前任务是个人博客、通用静态首页、单页介绍或其他不依赖外部产品事实/品牌素材/真实图片的页面,也要明确写成“无外部事实依赖”“当前无品牌素材依赖”“真实图片不是页面成立前提”,不要长期保留 pending。.openprd/design/templates/ 里最接近的一份模板;如果用户已经给了效果图、设计稿或参考图,先挑最接近它的 starter / lens / theme / layout;只有确实接近时才复用,不接近就允许偏离默认组合,以用户参考图为准。如果当前任务已经有一句明确页面主题和模块范围,优先直接运行 openprd design-starter . --starter <starter-id> --out index.html --brief "<页面主题>" --sections "<模块1|模块2|模块3>"。只有像个人博客、工具台、纯结构化产品页这类确认不靠真实图片成立的静态首页,才补 --no-external-facts --no-brand-assets --no-real-images,让 starter 同步写实 active design artifacts,并把 docs/basic/、入口文件说明书和根目录文件夹 README 一起补到可过 standards 的状态;如果题目更像旅游、导览、展览、博物馆、城市、自然观察、案例展示或品牌内容页,默认不要带 --no-real-images,先让 starter 尝试补首批真实图片。design-starter 已经带 --brief 生成了第一版真实内容,就直接在生成的入口文件上细化结构、内容和样式,并立即进入 Patch Mode。Patch Mode 的意思是:入口路径已经固定,后续所有大改都在当前文件里完成;如果你觉得整页都要重写,也是在同一路径内覆盖,不做 delete-first。禁止删除 index.html 后另起新稿;即使结构要大改,也是在当前文件里重排,不要回头整份通读模板源码。如果你真的需要整页重写,先把完整新稿写到同目录 sibling draft,例如 index.next.html,确认内容成形后再覆盖回 index.html,不要让入口文件出现空窗。starter 一落地后,只允许做一轮就地对焦:快速读一次生成的入口文件和必要的 active design artifacts;这轮对焦结束后,下一步就必须是真实写入口,不要再回头搜网页、翻 docs/basic/ 或继续模板漫游。把最后一批必要的查事实、查图、读模板动作放在口头宣布之前做完;一旦你已经口头宣布“开始覆盖入口文件”或“进入整页重写”,下一步必须是对 index.html 或 sibling draft 的实际写操作,不要继续长时间读模板、翻文档、压图片或停在口头承诺。只有规划、下载图片、补合同或口头说明还不算完成;必须把最终页面真的改到入口文件里。默认要求:
lenses / themes / layouts / components。openprd design-starter . --starter <starter-id> --out index.html,把“挑模板”和“创建入口文件”变成确定动作,不要让 Agent 自己发明复制步骤。design-starter 的 --brief 与 --sections,让 starter 直接落真实首版,并顺手把基础文档和说明书从模板态拉成当前事实,而不是先生成整页占位再手工回填。openprd run . --context --message <用户原话> 参与当前请求解析,而不是只看空白工作区自身状态。无外部产品事实依赖、当前无品牌素材依赖、真实图片不是页面成立前提;这类页面不该因为“没有更多证据可查”而一直停在 待填写 / pending。--no-real-images。design-starter 后,立即替换生成入口文件里的 title、首屏文案、CTA 和所有 [占位] 文案;除非真的需要额外结构,不要再回头整页阅读模板文件。design-starter 后,不要再重新判断“要不要删文件重写”;下一步默认就是进入 Patch Mode,至少同时修改 index.html 和必要的 active design artifacts;直接在生成的入口文件上改。禁止删除 index.html 后重起,也不要继续翻 theme / layout / template 源码来给自己找“再等等”的理由。design-starter 后,如果确实还需要确认当前骨架,只允许做一轮就地对焦:快速读一次生成的入口文件和必要的 active design artifacts;对焦结束后,下一步就必须是真实写入 index.html 或 sibling draft,不要再回头搜网页、翻 docs/basic/ 或继续模板漫游。index.next.html 或 index.rewrite.html,确认新稿已经成形后再覆盖回 index.html;不要先把当前入口删掉再慢慢补。index.html,或先写 index.next.html / index.rewrite.html,不要继续只读浏览或长时间停住。design-starter 后的第一目标不是“回到样式库重新想一版”,而是把参考图里的版式、信息层级、主视觉和关键路径真正映射到当前入口文件里。design-starter 一旦生成入口文件,这个路径就视为稳定基座;后续默认围绕它继续实现。Patch Mode 的主裁决源;现有样式库、starter 和 design tokens 只负责加速,不负责把页面带到另一种风格。Patch Mode 至少同时收口入口文件和必要的 active design artifacts;如果事实、素材或图片还没准备好,先补这些,再继续改页面,不要把入口文件删空当成思考中间态。index.html 在重写过程中处于缺失状态。design-starter 刚落地时,如果需要短暂对焦,只允许围绕生成的入口文件和 active design artifacts 做一轮快速确认;对焦之后就进入真实写入,不再回头搜网页、翻 docs/basic/ 或继续模板漫游。Patch Mode 的覆盖阶段,下一步必须是实际写入 index.html 或 sibling draft;不能继续只做素材处理、重复阅读或停在“准备开始改”的状态。把“开始覆盖”这句话视为最后一跳承诺,不要太早说。Patch Mode 完成。.openprd/design/active/facts-sheet.md。待确认,而不是自己补一个像真的答案。.openprd/design/active/asset-spec.md,再决定版式。.openprd/design/active/image-preflight.md 记录:是否需要真实图、计划来源、风险和降级方案。contrast:刻意拉开气质、密度、明暗或叙事角度reference-transfer:从真实世界成熟范式迁移结构方法design-lens:基于某种明确设计哲学从头重构lens + theme + layout + component set + aesthetic direction + memory point,再进入编码。这套框架不是“参考图收藏夹”,而是 Agent 可执行的设计骨架:
lenses/:这次站在哪种设计判断角度看页面themes/:色彩、字体、密度、圆角、阴影、边框、留白、动效和表面规则layouts/:页面骨架components/:高频结构块recipes/:按任务类型打包的默认方案checklists/:实现前后自检assets/:允许反复复用的背景、表面、图案和位图资产说明templates/:可直接开工的页面模板,减少空白工作区从 0 到 1 的犹豫anti-slop.md:反模板化检查,拦住紫白渐变、通用字体、卡片堆叠和没有语境的装饰facts-sheet.mdasset-spec.mdimage-preflight.mddirection-plan.mdselected-direction.mdanti-slop.md 改写审美主张,再进入实现asset-spec.md 的“功能图标”行——先复用项目已有图标体系;项目没有时按最佳实践路由选型(UI 图标 Phosphor,落码 Lucide/Tabler/React Icons,AI 品牌 LobeHub Icons,技术栈 Tech Icons,功能图标/插画 iconfont),登记图标名、来源和用途后再接入实现。这是默认动作,不等用户提出;只有语义确实不需要图标或用户明确说不要时才跳过,并在收口说明原因imagegen 仍然负责出候选效果图。#00ff00 绿幕、无文字、无 UI 容器、主体居中且留足裁切边距;用户选定前不写项目文件。选定后先用源图顺序或 contact sheet 确认选中图,再保留绿幕源图、抠透明 PNG/WebP、裁切居中、导出 384px 或多尺寸资产,并按真实入口位置分别调显示比例。接入后同步写回 .openprd/design/active/asset-spec.md 和 selected-direction.md,记录选中方向、资产路径、接入位置和验证结果。openprd visual-prepare 负责把整板、多对象或网格参考图整理成可实现的 reference-set。openprd visual-compare 负责实现后的视觉证据,而不是替代这份设计前置判断。visual-compare 每次都会返回 chatEmbed markdown;生成证据板后必须把  直接嵌入最终回复,让证据在对话流里可见,不要只报告文件路径。openprd dev-check 触达界面文件且最近 24 小时没有证据板时会输出视觉证据提醒,收口前按提醒补齐。visual-compare 的修改前后图、局部焦点证据板、截图实测证据板或对齐辅助线证据板。构建通过、打包成功、dev-check 通过和单张截图都不能替代视觉证据。openprd visual-compare . --board <alignment-board.json> 生成对齐证据。只量外框、列宽或行顶不算完整对齐验收。openprd visual-compare . --board <centering-board.json> 生成内部居中证据板;Agent 要先裁出目标元素,再用类似 Canvas 的像素 mask 量画布中心、主体外接框中心和视觉重心偏移。证据板必须显示红色画布中心线、绿色主体外接框、黄色视觉重心点和 offset 数值;单张截图或主观“看起来居中”不算完整验收。© DavidLam-oss, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 2 other files (references) in .codex/skills/openprd-frontend-design of DavidLam-oss/obsidian-wechat-converter.
Open the folder on GitHubat commit 3fef612
Openprd Frontend Design next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Openprd Frontend Design this skillDavidLam-oss/obsidian-wechat-converter | 335 | — | ~2.7k | Automated safety check: Pass | MIT | |
| Web Artifacts Builderanthropics/skills | 180k | 40 repos | ~769 | Automated safety check: Pass | Apache-2.0 | |
| React Doctormakeplane/plane | 61k | 12 repos | ~657 | Automated safety check: Pass | AGPL-3.0 | |
| Impeccablebestofjs/bestofjs | 3.1k | 26 repos | ~2.6k | Automated safety check: Pass | MIT | |
| Figma Design System Builderwarpdotdev/warp | 65k | 2 repos | ~4.4k | Automated safety check: Pass | AGPL-3.0 | |
| Web Interface Guidelines Reviewervercel-labs/openreview | 1.7k | 97 repos | ~308 | Automated safety check: Pass | None |
anthropics/skills
Builds multi-component claude.ai HTML artifacts as a small React, TypeScript and Tailwind project, then bundles it into one shareable HTML file.
makeplane/plane
Scans React code for lint, accessibility, bundle size and architecture issues, reports a health score and checks that changes do not lower it.
bestofjs/bestofjs
A skill your agent uses when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a…
warpdotdev/warp
Builds or updates a design system in Figma from a codebase in ordered phases: discovery, variables and tokens, components, theming and documentation, with checkpoints.
vercel-labs/openreview
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my…
anonaddy/anonaddy
Always invoke when the user's message includes 'tailwind' in any form.
DavidLam-oss/obsidian-wechat-converter
OpenPrd UI Context skill:区分 greenfield、brownfield 与局部修正,基于已确认 PRD、可选 CodeGraph 和本地证据提出专业 UI/UX 方向,并在用户确认后编译 PRODUCT.md、DESIGN.md 和 Impeccable handoff。
DavidLam-oss/obsidian-wechat-converter
为 Obsidian 微信公众号转换器生成受约束的 AI 编排结果。只在需要把文章内容映射为公众号安全 block JSON、诊断编排结果、优化 layout schema、分析 fallback 介入原因时使用。遇到教程、案例、产品介绍、截图型内容时应优先考虑这个 skill。
DavidLam-oss/obsidian-wechat-converter
OpenPrd 测试策略分流 skill:按风险把任务分到单元、集成、端到端、人工、视觉、小程序、性能和安全验证,并要求 evidence-plan。
DavidLam-oss/obsidian-wechat-converter
Release workflow for obsidian-wechat-converter (version bump, release notes, tag and publish).
DavidLam-oss/obsidian-wechat-converter
生成并迭代 OpenPrd 图示产物,供用户确认或理解。适用于解释型 SVG、架构图、产品流程图、用户旅程、流程图、系统边界图、依赖图,以及 freeze 前的可视化评审场景。
DavidLam-oss/obsidian-wechat-converter
OpenPrd 需求入口与 PRD 分流 skill:判断用户可见需求类型和内部 L0/L1/L2 路由码,决定直接澄清、mini-plan 或正式 PRD,并选择通用 / 面向个人消费者场景 / 面向企业服务场景 / 以 Agent 为主要使用场景的 PRD 视角。对用户复述时不要直接把 consumer / b2b / agent 当展示词;这些枚举值只用于内部记录和命令。
Categories
OpenPrd 前端设计框架 skill:为界面、页面、视觉、样式和前端体验任务提供设计资产框架、审美立意、反 AI 味门禁和实现前方向评审规则。. Openprd Frontend Design is an agent skill from DavidLam-oss/obsidian-wechat-converter.
Openprd Frontend Design fits situations like: frontend & Design work in your project.
Run `npx skills add DavidLam-oss/obsidian-wechat-converter --skill openprd-frontend-design -a claude-code`. Or copy the skill folder (.codex/skills/openprd-frontend-design in DavidLam-oss/obsidian-wechat-converter) into .claude/skills/openprd-frontend-design in your project. Claude Code loads it when a task matches its description.
Run `npx skills add DavidLam-oss/obsidian-wechat-converter --skill openprd-frontend-design -a codex`. Or copy the skill folder (.codex/skills/openprd-frontend-design in DavidLam-oss/obsidian-wechat-converter) into .agents/skills/openprd-frontend-design in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add DavidLam-oss/obsidian-wechat-converter --skill openprd-frontend-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/openprd-frontend-design, .gemini/skills/openprd-frontend-design, .github/skills/openprd-frontend-design and .opencode/skills/openprd-frontend-design in your project.
SKILL.md names no scripts, command-line tools or credentials: Openprd Frontend Design is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Openprd Frontend Design is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.6k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Openprd Frontend Design: Web Artifacts Builder (anthropics/skills, 180k stars), React Doctor (makeplane/plane, 61k stars), Impeccable (bestofjs/bestofjs, 3.1k stars) and Figma Design System Builder (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
DavidLam-oss (a GitHub user) maintains it in DavidLam-oss/obsidian-wechat-converter, which has 335 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 10, 2026.
Source: DavidLam-oss/obsidian-wechat-converter on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.