sergekostenchuk/ui-ux-agent-skill-system

figma-workflow-auditor

Audit Figma MCP, design-to-code, code-to-canvas, canvas-editing, and design-system workflows for correctness, freshness, privacy, evidence, and routing quality.

查看源码

使用方法

  1. 复制安装命令,在自己的智能体环境安装前先检查源码包。
  2. 从原始文档核对所需工具、凭据和支持的宿主。
  3. 说明输入材料与期望交付物,并对照来源检查输出。
npx skills add https://github.com/sergekostenchuk/ui-ux-agent-skill-system --skill figma-workflow-auditor

开始前需了解

  • 安装不包含模型订阅、API 额度或访问文件的权限。
  • 仓库星数和安装量反映活跃情况,不等于独立质量或安全测试。
仓库原始内容

按源仓库内容呈现,保留标题、案例、代码、表格、链接以及原文引用的演示图片。

Figma Workflow Auditor

Use this skill as the quality gate for Figma-related workflows. It does not mutate Figma files.

Modes

  • capability-audit: verify claims against current Figma MCP/tool availability.
  • privacy-audit: check whether data transfer and permissions are acceptable.
  • evidence-audit: check whether claimed reads/writes/exports actually ran.
  • routing-audit: check whether the right Figma specialist was selected.
  • skill-audit: review a Figma skill draft or existing skill.

Workflow

  1. Identify the workflow under review: prompt, plan, skill, transcript, report, or file change.
  2. Check official/current sources when capability details may have changed.
  3. Verify tool evidence: tool response, metadata readback, screenshot/export, local diff, or report artifact.
  4. Flag overclaims separately from implementation bugs.
  5. Return findings ordered by severity, with concrete fixes.

Findings Format

Use assets/audit-report-template.md.

Audit Rules

  • A Figma MCP claim is weak if it lacks session tool availability and evidence.
  • A mutation claim is invalid without a target, scope, executed tool, and readback.
  • A privacy plan is weak if it omits what data is sent to Figma or another service.
  • A design-to-code plan is weak if it skips local component inspection and visual verification.
  • An effects plan is weak if it treats NOISE, TEXTURE, GLASS, or progressive blur as universally available without runtime checks.

按任务相关推荐

来自同一仓库

更多 Skills

全部 Skills
sergekostenchuk
社区

admin-ui-builder

Use when admin/CMS/back-office screens need to be built or specified after admin-ui-orchestrator defines roles, permissions, workflows, and safety gates. Covers tables, forms, editors, moderation queues, dashboards, CRUD surfaces, and state coverage without production destructive actions.

1小时安装量
1
GitHub Stars
35
最近更新
9月13日
sergekostenchuk
社区

admin-ui-orchestrator

Use when a project needs admin/CMS/back-office UI architecture: roles, permissions, content workflows, AI assistant boundaries, audit logs, destructive-action confirmations, and builder handoff. Planning only; do not perform production admin actions or expose secrets.

1小时安装量
1
GitHub Stars
35
最近更新
9月13日
sergekostenchuk
社区

analytics-setup-architect

Use when a website or web app needs privacy-aware analytics architecture: GA4, Yandex Metrica, self-hosted analytics, consent, UTM, event taxonomy, funnels, dashboards, and launch verification. Do not mutate real analytics accounts or store credentials without explicit approval.

1小时安装量
1
GitHub Stars
35
最近更新
9月13日
sergekostenchuk
社区

editorial-quality-gate

Review public site content for editorial quality, source support, prompt residue, duplicate blocks, translation drift, hidden filler, and human usefulness before SEO or LLM-friendly publication. Use this skill when the user asks to quality-gate news briefs, longform explainers, blog posts, topic pages, project pages, translated content, or generated article drafts without changing the live publishing pipeline.

1小时安装量
1
GitHub Stars
35
最近更新
9月13日