跳到正文
cccskills
免费在 GitHub 公开

fix-design-notes

Read design review notes attached to a pull request’s screenshots, locate the affected components, and fix the product code using the team’s design rules. Repeat the review and inspect screenshots to verify the result.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Design notes on a PR, "Design review (advisory)" in the evidence check, "worth fixing", layout.split-row, OW-LIST, a reviewer says the UI looks off. Use to read what the design review found on a PR's screenshots, fix it in code, and prove the note is gone.

集成工具GitHub
查看安装方法

适用场景

  • Resolving design notes on a pull request
  • Reproducing reported layout problems locally
  • Fixing shared components behind repeated UI issues
  • Documenting why a design suggestion should be kept unchanged

包含的文件(1)

  • SKILL.md3.2 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Skill: Fix design notes

Every PR that records evidence screenshots gets an advisory design review. Its notes ride in the Evidence preview check, next to the evidence they are about: one summary line, and the notes as the check's text. They never change the evidence verdict, but a note marked Worth fixing is a defect a careful designer would send back. Fix it, or say in the PR why the screen is right.

Read the notes

sha=$(gh pr view <pr> --json headRefOid --jq .headRefOid)
check() { gh api "repos/{owner}/{repo}/commits/$sha/check-runs?check_name=Evidence%20preview" --jq ".check_runs[0].output.$1"; }
check summary   # ends with "Design review (advisory): 3 notes, 1 worth fixing." or "no notes."
check text      # the notes, then the same notes as JSON

Each note gives:

FieldUse it to
rulelayout.* was measured from the DOM (exact). S2, V2… are DESIGN.md; OW-* are the OpenWork Design rules in evals/design-review/rubric.md (judged from pixels; may vary run to run)
Screenshotthe spec step that took it, and the spec file
Where in the codegrep for the hook ([data-library-row="…"] → data-library-row) or the class list to find the component
Reproducethe command that re-records the screenshots and reviews them locally

The JSON block at the end of the check text has the same notes for scripts. The screenshots themselves are in the review report the check links to.

Reproduce, fix, verify

  1. Run the note's reproduce command. Read --json output, not prose: pnpm evals:e2e <slug> --local && pnpm --dir evals design:review -- --test-run latest --json (judged notes need OPENAI_API_KEY or ANTHROPIC_API_KEY; measured ones do not).
  2. Find the component from the hook or class list. Read DESIGN.md and the rule in evals/design-review/rubric.md before changing anything: the fix follows the team's pattern, not the note's wording.
  3. Fix it in the product code, never in the spec or the rubric.
  4. Re-run the same command. The note must be gone and no new Worth fixing note may appear. Look at the screenshot yourself: a passing rule is not a good screen.
  5. Push. CI re-runs the review; the evidence check's summary says Design review (advisory): no notes. or lists only what you decided to keep.

When the screen is right

A judged note can be wrong, and a team decision can outrank a generic rule. Leave the code, and put one line in the PR body under Evidence: Design review: kept OW-LIST-HEADER on the Library; the columns are compared (see DESIGN.md S2). Do not edit the rubric to silence a note in the same PR that triggers it.

Rules

  • Measured notes are facts about the layout; do not argue with the numbers.
  • Never chase a judged note across runs: if it flips between runs, it is low confidence. Fix what you can see in the screenshot.
  • Fix the shared component when the hook points at one (a row used by every list), not each screen.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Manage OpenWork feature releases with feature flags, switches that control access to new behavior. Register features before coding, release them by organization and deployment, prepare a global shutdown option, and remove temporary flags after rollout.

中文简介正在准备中。当前显示英语简介。

  • Registering a feature before implementation
  • Releasing a feature to selected organizations
  • Separating cloud and self-hosted availability
different-ai/openwork2.4万2026年10月19日 更新

Connect OpenCode browser tools to a locally running OpenWork Electron app to inspect its UI, enter a task, and check the response. This skill supports exploration and debugging through CDP, Chrome's remote control protocol.

中文简介正在准备中。当前显示英语简介。

  • Connecting browser tools to a local Electron development app
  • Inspecting screen state during debugging
  • Entering a task in the composer and running it
different-ai/openwork2.4万2026年10月19日 更新

Check added lines in a change for information identifying customers, prospects, partners, or outside individuals. Report locations and generic remediation without reproducing identities, and escalate cases where the information is already public.

中文简介正在准备中。当前显示英语简介。

  • Checking changes for customer and partner identities
  • Reviewing documents and test data for identifying details
  • Reporting disclosure locations without repeating identities
different-ai/openwork2.4万2026年10月19日 更新

Connects supported AI clients, including Claude Code and Codex, to OpenWork through MCP, a protocol for accessing external tools. It guides account sign-in and verifies that tools for finding and running organization capabilities are available.

中文简介正在准备中。当前显示英语简介。

  • Connecting an AI client to OpenWork organization resources
  • Signing in and verifying available MCP tools
  • Switching organizations or troubleshooting authentication
different-ai/openwork2.4万2026年10月19日 更新

Review an outside contributor’s pull request before running its code. Identify concealed behavior, obfuscated code, risky dependencies, and build hooks, with file locations and specific checks for maintainers to follow up.

中文简介正在准备中。当前显示英语简介。

  • Screening an outside contributor’s pull request before execution
  • Checking encoded code and unexplained network calls
  • Reviewing dependency changes and installation scripts
different-ai/openwork2.4万2026年10月19日 更新

Create an OpenCode plugin for OpenWork with custom tools and hooks, which run code at specific events. The skill builds the plugin file and adds its entry to the project configuration.

中文简介正在准备中。当前显示英语简介。

  • Adding custom tools to OpenWork
  • Creating a plugin to save and list notes
  • Running custom code before or after tool execution
different-ai/openwork2.4万2026年10月19日 更新

查看 different-ai 的全部技能

报告此技能的问题