跳到正文
FunCoding

搜索

搜索文档、Skill 和 MCP

fix-what-i-pointed-at

Pick up the bugs a human flagged by pointing at them in the running app, each arriving with the element, the note they typed, and the source file and line. Use when the user says they marked or flagged something, when starting a session on an app someone has been clicking through, when a designer or PM has left feedback in the UI, or when the user describes a problem as "that button there" without saying which file.

浏览器自动化1.2kskills/fix-what-i-pointed-at/SKILL.md

安装

把这段话发给 Claude Code、Codex 或 Cursor。智能体会先检查安全性,你确认后才安装。

读取 https://funcoding.ai/skills/reticlehq/reticle/fix-what-i-pointed-at/install.md ,按里面的步骤帮我安装这个 Skill。

SKILL.md

The human pointed at the bug. Go fix it.

"The spacing on that card is wrong" is unactionable in chat and precise in the app. Reticle's running app has a Flag a bug control: the human clicks it, points at an element, and types what is wrong. Each flag becomes a mark carrying the element, the note, and the file:line, so the round trip that usually costs a screenshot, a description, and two clarifying questions costs one call.

Not installed? RETICLE_INSTALL_SOURCE=npx_skill npx @reticlehq/server@latest init, then the install-and-verify skill.

Drain the marks

reticle_session({ action: "review", sessionId })
{
  "marks": [
    {
      "id": "m1",
      "note": "this button is misaligned",
      "label": "button \"Pay\"",
      "source": { "file": "src/Checkout.tsx", "line": 42 },
      "fix": "Open src/Checkout.tsx:42 and fix: this button is misaligned."
    }
  ],
  "pendingCount": 1
}

Check this at the start of a session, and again whenever the human has been in the app. Reading never consumes a mark, so list → fix → verify → resolve is safe to run in any order.

The loop

  1. Read the marks. Group them if several point at the same file: one edit often answers three.
  2. Open source.file at source.line. This is the whole point: no hunting for which component rendered that button.
  3. Fix what the note asks for. If the note is ambiguous, the element label and its source usually disambiguate it. Ask the human only when they genuinely do not.
  4. Verify in the app, do not eyeball it. Re-drive the affected control with reticle_act_and_wait and name the consequence, or reticle_look { action: "element" } on the element for a layout or theme complaint. A visual fix confirmed by looking at it is how the mark gets reopened.
  5. Resolve it:
reticle_session({ action: "review", sessionId, resolve: "m1" })

Resolve only after the fix is verified. A resolved mark is a promise to the human that the thing they pointed at is done.

When you cannot fix one

Say so against that mark and leave it unresolved. A mark silently dropped is worse than an open one: the human believes it was handled and finds out later. If the note describes intended behaviour rather than a bug, say that too, and let them decide.

Report back in their vocabulary

They pointed at "that button". Report on "the Pay button on checkout", with what you changed and the evidence it now works. Marks come from people who are looking at the screen, not at the repo, so a report full of file paths and no user-facing language answers the wrong question.


Everything else: curl https://docs.reticle.sh/llms.txt. If a mark arrived without a usable source pointer, that is worth a reticle_session { action: "feedback" } with kind: "gap".

相似的 Skill

webapp-testing
anthropics/skills180k

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

浏览器自动化

browser-testing-with-devtools
addyosmani/agent-skills103k

browser-testing-with-devtools

Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.

浏览器自动化

webapp-testing
ComposioHQ/awesome-claude-skills77k

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

浏览器自动化

browser
code-yeongyu/oh-my-openagent70k

browser

Drives a real browser through the omowright library from the js eval kernel: sites the user is already signed into, forms and clicks, JS-rendered pages, screenshots, web QA, extension popups, a human handoff for login, CAPTCHA or OTP, and a browser you own for scraping, bot-scored targets, network capture and QA traces. Use for any interactive browser task; not for a plain search or an unblocked static fetch.

浏览器自动化

agent-browser
shanraisshan/claude-code-best-practice67k

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

浏览器自动化

cherry-regression-test
CherryHQ/cherry-studio52k

cherry-regression-test

Run Cherry Studio critical-path system regression tasks through the repository-owned Playwright E2E workflow. Use for full regression, release acceptance, development-branch system validation, or a named cherry-regression-test task on GitHub-hosted macOS and Windows runners.

浏览器自动化