t-figma-fix

t-figma-fix is a skill for Claude Code from timzaak/web-dev-skills. It costs 42 tokens per session (1,094 once invoked), scanned A, original, Apache-2.0.

A focused workflow for refining one Figma design region in an existing implementation. Figma is a collaborative interface-design tool; the workflow compares its design evidence with the matching code and updates only the selected area.

In plain words
What is it for?
Use it to fix a specific page region, including its responsive, hover, error, styling, or reuse issues. It captures local comparisons and checks the result against the selected Figma node.
Why use it?
It prevents a local visual correction from turning into an unintended redesign of the whole page, while recording the design and implementation evidence behind the change.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the t-tools plugin — 29 skills, 31 agents shipped together

Good fit Use it to fix a specific page region, including its responsive, hover, error, styling, or reuse issues. It captures local comparisons and checks the result against the selected Figma node.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add timzaak/web-dev-skills
Claude Code
/plugin install t-tools

Made for: Claude Code.

Or install t-tools, the plugin that ships this one along with the rest of its 29 skills, 31 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for t-figma-fix

README.md
[![agentmods](https://agentmods.dev/badge/skills/timzaak/web-dev-skills/t-figma-fix/github.svg)](https://agentmods.dev/skills/timzaak/web-dev-skills/t-figma-fix)
Your own site
<a href="https://agentmods.dev/skills/timzaak/web-dev-skills/t-figma-fix"><img src="https://agentmods.dev/badge/skills/timzaak/web-dev-skills/t-figma-fix/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for t-figma-fix

Your own site · 80×15
<a href="https://agentmods.dev/skills/timzaak/web-dev-skills/t-figma-fix"><img src="https://agentmods.dev/badge/skills/timzaak/web-dev-skills/t-figma-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,094 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.01094
Opus 5 $0.00021 $0.00547
Sonnet 5 $0.00008 $0.00219
Haiku 4.5 $0.00004 $0.00109

Measured 3d ago against content hash 540e1e566c19, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

t-figma-fix scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/t-figma-fix/SKILL.md · 47 lines

What it actually says

Figma 局部精修

共享契约:${CLAUDE_PLUGIN_ROOT}/protocols/figma-workflow-contract.md(生成或修订 spec、写 assets-manifest、判读 delta 分级或晋升长期规则前读) 二次重建:${CLAUDE_PLUGIN_ROOT}/guides/figma/reconstruction.md(判断偏差是否属于 spec 分组问题或修订二次规格前读) 规则记忆:${CLAUDE_PLUGIN_ROOT}/guides/figma/rules.md(写候选或晋升长期规则前读)

独立精修节点 URL 指向的已有实现;可以附着 t-figma-impl 等既有 session,也可以为手写或其他方式产生的代码自行建立局部基准。文字描述用于补充 hover、移动端、异常状态或代码问题。不得借机重做整页。

前置

校验 node URL、target-file 和非空描述,并确认 URL 对应区域已有可运行的代码实现;没有实现时停止,说明应先实现该区域或运行 t-figma-impl,不得把局部 fix 扩成整页实现。

调用 ${CLAUDE_PLUGIN_ROOT}/scripts/figma-session.py resolve,附着(同 fileKey,nodeId 可不同)、独立 create --stage fixing、不一致与 ambiguous 询问等决策按共享契约的 Session Resolve 表执行;附着时复用 session 中实际存在的 context、spec、manifest、candidates 和历史 delta,不要求这些产物必须来自 t-figma-impl

读取项目约束、长期规则、目标区域代码、邻近复用实现,以及 session 中实际存在的 candidates、spec revisions 和历史 delta。只对 fix 节点调用 metadata/design context/screenshot/variables,保存为新的 source 证据,不覆盖已有主稿快照。

缺少 context.md 时从项目和目标区域代码生成。独立 session 或无 spec 的附着 session,从 fix 节点证据与当前代码生成 revision 1 局部 spec.json;附着 session 已有 spec 但缺少当前 scope 时,增加 revision 后补入局部规格。两种情况都为可测语义元素添加稳定 probe,并在缺少 manifest 且本次不引入资产时写入空的 assets-manifest.json。当前代码就是修复前实现基线,不要求存在 impl 历史。若修复必须新增、替换或加工素材则停止,提示运行 t-figma-assets;不得用空 manifest 绕过本次变更涉及的资产。

精修闭环

  1. 将节点 screenshot 与当前 DOM 区域对照,判断偏差属于 spec 分组、素材、响应式、样式值或现有组件使用问题。
  2. 若 MCP 平面结构不准确,先更新 spec 对应 scope、增加 revision 并记录代码/截图/metadata 证据;首次生成的局部 spec 使用 revision 1。
  3. 当前 session 没有该 scope 的可用 delta 时,先用 scopeSelector 做一次只读局部测量,产生修复前 delta;把本次节点的 source/baseline-<node-name>.png 显式作为 --baseline。测量无法运行时停止,不得凭视觉描述代替 agent 所需的结构化 delta。
  4. 注入并委派 figma-fix,传入当前 scope 的 spec revision 和 delta,限制 change_scope 为目标区域及其直接共享样式;资产只能引用 manifest。发现新素材则停止,提示先运行 assets,不在 fix 内下载或转码。
  5. 用相同 scopeSelector 和 baseline 运行 figma-accept 的局部截图、数值 probes、资产/视频检查。最多 5 轮,只回改当前 scope 的阻塞项。
  6. 比较 Figma 表达、修复前代码和最终通过代码,写候选;收敛后按契约去重、改写、晋升长期规则。页面专属补丁和单次像素值不晋升。

输出修改范围、spec revision、局部 delta、验证证据、候选和已晋升规则。未收敛时不得更新长期规则。

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago Changed · -4 lines 540e1e566c19
  2. 5d ago Changed · +9 lines · +16 tokens per session bfefd2b6f7b3
  3. 9d ago First seen · 42 lines · 26 tokens per session scan A 69d9f5db6108

Subscribe to this mod's changes

t-figma-fix is a skill published in the GitHub repository timzaak/web-dev-skills (74 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 1,094 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

design-taste-frontend

A frontend-design skill for creating distinctive landing pages, portfolios, and redesigns. It first infers the desired visual character and then proposes a design direction and rules.

xiehuan123/coding-coach · 79 tokens

ui-ux-pro-max

UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design…

xiehuan123/coding-coach · 238 tokens

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for…

Bosh-Kuo/awesome-agent-toolkit · 90 tokens

impeccable

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states.…

Bosh-Kuo/awesome-agent-toolkit · 189 tokens

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…

Bosh-Kuo/awesome-agent-toolkit · 77 tokens

web-design-guidelines

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

Bosh-Kuo/awesome-agent-toolkit · 44 tokens