pencil-import-workflow
使用 Pencil MCP 读取当前打开的 .pen 文件与 Frame(无需上传),让用户确认导入范围与输出结构后,生成 Axhub Make 原型目录(spec.md + index.tsx)并验收。
Skill by tracyping-pm
Chalk Labs
Need help deploying pencil-import-workflow?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/tracyping-pm-pencil-import-workflow
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
pencil-import-workflow- Description
- 使用 Pencil MCP 读取当前打开的 .pen 文件与 Frame(无需上传),让用户确认导入范围与输出结构后,生成 Axhub Make 原型目录(spec.md + index.tsx)并验收。
- License
- Apache-2.0
- Instructions
- 76 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Pencil 导入工作流 本技能用于“从 Pencil 设计稿导入并生成 Axhub Make 原型代码”的交互编排。 重点是:**先通过 MCP 读取当前打开的 Pencil 文件与 Frame,再让用户确认导入范围与输出结构,最后才写文件**。 ## 前置条件 1. Pencil 桌面端已打开目标 `.pen` 文件 2. MCP 已可用(如不可用参考:`/skills/mcp-installer/SKILL.md`) ## 标准流程(必须按顺序) ### 1) 检测 Pencil MCP 可用性 - 优先调用:`mcp__pencil__get_editor_state` - 若不确定工具前缀/命名空间:先使用 MCP 的 `list_tools`(或等价能力)列出可用工具,找到 pencil 相关工具后再调用 - 若工具不可用/调用失败: - 停止后续步骤 - 提示用户打开 Pencil 并选中目标 Frame 后重试 ### 2) 获取当前 selection 与候选 Frame - 若 selection 中包含 Frame:候选 = selection Frames - 若 selection 为空或不是 Frame: - 使用 `mcp__pencil__batch_get` 在当前文件中搜索/列出 Frame 候选(“已有的 frame”) 输出给用户的候选信息至少包含: - 序号 - frameId - frameName - 尺寸(若可得) 候选较少时(可选):使用 `mcp__pencil__get_screenshot` 辅助用户辨认。 如果候选过多导致无法确认: - 要求用户回到 Pencil 先选中需要导入的 Frame(可多选) - 然后重新读取 selection ### 3) 让用户确认(阻塞点,确认前不写文件) 必须等待用户明确回答以下 2 类问题: 1. 导入范围:全部 / 子集(用序号或 frameId 指定)/ 回到 Pencil 重新选择 2. 输出结构(二选一,不要推荐): - A. 单原型多屏:生成 1 个 `src/prototypes/<name>/`,在 `index.tsx` 内提供导航切换各 Screen - B. 多原型批量:每个 Frame 生成 1 个 `src/prototypes/<proto-name>/` 同时确认命名规则: - `<name>` / `<proto-name>` 如何从 Frame 名称派生为 kebab-case - 重名冲突处理规则(后缀、序号或用户指定) ### 4) 生成原型产物 对每个生成的原型目录,至少输出: - `src/prototypes/<name>/spec.md` - `src/prototypes/<name>/index.tsx` - (可选)`src/prototypes/<name>/style.css` `spec.md` 必须记录 Pencil 来源信息(可得则写): - `.pen` 标识/路径(若能获取) - 导入的 frameId 列表、frameName 列表 - Screen 到实现模块的映射 > 如需更强的“先完成原型、再 1:1 回建 Pencil 并强制后续同步”约束,可参考:`/skills/pencil-sync-after-prototype-workflow/SKILL.md`(技能名:`pencil-sync-after-prototype-workflow`)。 ### 5) 验收 对每个生成的原型运行: ```bash node scripts/check-app-ready.mjs /prototypes/<name> ``` 直到状态为 `READY`。
From tracyping-pm/tms-pm, Apache-2.0.
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Apr 12, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/tracyping-pm/tms-pm
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.426score
pencil-import-workflow
liuqiao666
使用 Pencil MCP 读取当前打开的 .pen 文件与 Frame(无需上传),让用户确认导入范围与输出结构后,生成 Axhub Make 原型目录(spec.md + index.tsx)并验收。
SkillDFreshness: D★ 1Claude Code +9 - 0.281score
pencil-import-workflow
fern-ok
使用 Pencil MCP 读取当前打开的 .pen 文件与 Frame(无需上传),让用户确认导入范围与输出结构后,生成 Axhub Make 原型目录(spec.md + index.tsx)并验收。
SkillCFreshness: CClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get pencil-import-workflow running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
pencil-import-workflow skill. Agent Mart. https://agentmart.dev/skills/tracyping-pm-pencil-import-workflow (last updated 2026-10-24)