Skip to content
Agentmart
Submit a tool

t-figma-impl

Implement a Figma UI in an existing frontend file, block by block; leave pending assets empty, bind prepared assets, and hand over for manual acceptance.

Skill by timzaak

IndexedApache-2.0★ 97
Write a review

Chalk Labs

Need help deploying t-figma-impl?

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.

Book a call

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/timzaak-t-figma-impl

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.

We use your email only for this newsletter. Privacy

About

Implement a Figma UI in an existing frontend file, block by block; leave pending assets empty, bind prepared assets, and hand over for manual acceptance. Does not prepare media assets.

Use cases: design, frontend

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/t-figma-impl

What's inside

Skill name
t-figma-impl
Description
Implement a Figma UI in an existing frontend file, block by block; leave pending assets empty, bind prepared assets, and hand over for manual acceptance. Does not prepare media assets.
License
Apache-2.0
Instructions
22 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • allowed-tools: must be a space-separated string

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Figma 整页实现

按人确认的本轮范围重建 Figma UI 并实现到既有前端文件;遵循工作流契约的「协作范围」,不补全未确认设计,不下载、转换素材。还原方法见 `${CLAUDE_PLUGIN_ROOT}/guides/figma/reconstruction.md`(分块前读),manifest 与交付规则见 `${CLAUDE_PLUGIN_ROOT}/protocols/figma-workflow-contract.md`,agent 派发遵循 `${CLAUDE_PLUGIN_ROOT}/protocols/subagent-dispatch.md`。

## 前置

校验 URL 与 target-file;`<preview-url>` 可选,仅用于交付报告回显。工作目录为 `.ai/figma/<fileKey>-<nodeId>/`。先读已有 `context.md`,再读取目标文件、邻近模块与项目 token/组件/动效模式;按工作流契约的「布局决策与恢复」补齐块清单和决策信息,记录主稿 viewport、适用断点和目标栈验证命令。manifest 用路径引用,不复述内容。栈无法确定时询问。

按工作流契约的「工作目录」检查素材就绪情况:已就绪的引用 manifest 条目;manifest 缺失、部分条目缺失或产物未就绪时,对应位置跳过留空,缺项写 `context.md`,继续实现其它内容。位图、SVG、视频均交给 `t-figma-assets` 准备,impl 不补做素材。绑定遵循契约的「素材类型保真」。

## 还原与实现

1. 在 MCP 窗口内为主节点和各视觉块保存 baseline 截图到 `source/`(一次写入,不覆盖);metadata、design context 和 variables 只在窗口内消费,不整页落盘。
2. 按 reconstruction 指南分块:截图定结构、节点树补精确数值与显式布局属性;按契约记录原始观测、采用规则与待裁决项。有裁决需求时按影响范围询问,不将候选写成已采用规则。
3. 逐块委派 `figma-impl` agent:每次一个块或少量相邻小块,给出该块的 baseline、观测与采用规则、已就绪资产条目 id、待补素材清单和组件映射。按契约消费 agent 输出并更新 context;汇总 `layout_questions` 询问用户,记录答复后仅恢复受影响部分,其它独立部分可继续。执行失败先处理原因再重试该块,布局待裁决不走失败重试;中断后按契约恢复未完成块、待裁决项与待补素材。

## 交付

4. 按契约检查本轮块进度与待裁决项,存在未完成部分时报告进度和恢复条件,不宣称完成。仅剩待补素材时报告留空清单,提示以同一主稿 URL 运行 `t-figma-assets`,本轮以待绑定状态结束。素材补齐后重读 manifest,按「素材类型保真」绑定并核对目标代码实际引用,重跑栈验证;无需重做已完成布局。
5. 按契约核对本轮进度与缺项,再在目标项目根运行 `python ${CLAUDE_PLUGIN_ROOT}/scripts/figma-assets.py verify <工作目录>/assets-plan.json`;plan/manifest 缺失、旧产物缺少验证证据或复验失败时交回 assets 修复,保留布局。栈验证和素材门禁均通过才按契约「验收」交付范围、布局调整依据、preview URL(如有)和 baseline 位置,并列出本轮人工检查项;未做页面比对不报告视觉验收通过。

From timzaak/web-dev-skills, Apache-2.0.

More from timzaak/web-dev-skills

Signals

Stars
97
Forks
9
Open issues
0
Last commit (this folder)
Oct 23, 2026 (8 days ago)
Last release
Oct 20, 2026 (11 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from timzaak

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 t-figma-impl 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.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying t-figma-impl?

CallGet help
Cite this page

t-figma-impl skill. Agent Mart. https://agentmart.dev/skills/timzaak-t-figma-impl (last updated 2026-10-24)