Skip to content

mxyhi/ok-skills / kimi-webbridge

kimi-webbridge

Unverified

Kimi Browser Extension(Kimi 浏览器扩展,原 Kimi WebBridge)lets AI control the user's real browser — navigate, click, type, read, screenshot, and interact with any website using the user's actual login sessions. Use this skill whenever the user wants to interact with websites, automate browser tasks, scrape web content, or perform any action requiring a real browser. Also use when the user mentions "browser", "webpage", "open URL", "screenshot", asks to read/interact with any website, or wants a reusable CLI tool or script that automates a specific website. Use even for simple-sounding browser requests — the daemon handles all complexity.

references/cli-creator/companion-skill-template.md

View on GitHub
# Companion Skill Template

Once the CLI works, write `skill/{platform}-cli/SKILL.md` in the CLI project from this template. It tells a future agent how to *use* the CLI — not how it was built.

Copy the block below into the new file, then fill in the blanks.

````markdown
---
name: {platform}-cli
description: Use when the user wants to [read/post/search/interact with] [Site Name]. Invoke when the user mentions "[site name]", asks to automate [site] tasks, or needs to [key action verbs].
---

# {Platform} CLI

Automates [Site Name] in the user's real, logged-in browser through the Kimi Browser Extension daemon (`kimi-webbridge`).

## Requirements

- The `kimi-webbridge` skill. If a command fails because the daemon is unreachable or the browser extension is not connected, recover the way that skill describes, then retry. If the daemon is not on its default address, pass `--daemon-url http://<host>:<port>`.
- The CLI at `<absolute path to the CLI>` — run it by that path unless it is on `PATH`
- For commands that need login: `{platform}-cli login-status`. If not logged in, ask the user to log in to [Site URL] in their browser, then retry.

## Commands

| Command | Args / Flags | Returns |
|---------|-------------|---------|
| `login-status` | — | `{logged_in, user}` |
| `search` | `<query> [--limit N]` | `[{id, text, author}]` |
| _(one row per command)_ | | |

Run `{platform}-cli <command> --help` for full flag documentation.

## Output format

Every command prints JSON on stdout:

```json
{"ok": true, "data": ...}
```

On error (non-zero exit):

```json
{"ok": false, "error": {"code": "error_code", "message": "human-readable message"}}
```

## Common workflows

```bash
# Search, then act on a result
{platform}-cli search "keyword" --limit 10
{platform}-cli like <id>
```

## Known limitations

- Login is done by the user in their browser; the CLI never automates it
- [Site-specific quirks found during development]
````

## Fill-in checklist

- [ ] Replace `{platform}` with the CLI's name
- [ ] Replace `[Site Name]` and `[Site URL]` with actual values
- [ ] Write the `description` from phrases the user would really say
- [ ] Fill in the CLI's absolute path, so an agent in a fresh conversation can run it
- [ ] Fill the Commands table from `{platform}-cli --help`
- [ ] Add 2–3 real workflows
- [ ] Record the limitations found during development
- [ ] If the site doesn't need login, drop the `login-status` row, the login requirement, and "logged-in" from the intro
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall