kachilu-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, logging in to sites, posting to social apps, handling CAPTCHA workflows, or automating browser actions. Load the core guide to choose between host-provided sessions, MCP tools, and CLI commands.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-13
- Stars
- ★ 1.6k
- Forks
- 483
01 前言 Front Matter
- name
- kachilu-browser
- hidden
- true
- description
- 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, logging in to sites, posting to social apps, handling CAPTCHA workflows, or automating browser actions. Load the core guide to choose between host-provided sessions, MCP tools, and CLI commands.
- allowed-tools
- Bash(npx kachilu-browser:*), Bash(kachilu-browser:*)
03 SKILL.md 正文
kachilu-browser
Browser automation CLI for AI agents. Chrome/Chromium via CDP with
accessibility-tree snapshots and compact @eN element refs.
Install: npm i -g kachilu-browser && kachilu-browser install
Start Here
This file is a discovery stub, not the usage guide. Before running any
kachilu-browser command, load the actual workflow content from the CLI:
kachilu-browser skills get core # start here: workflows, control-plane routing, CAPTCHA, troubleshooting
kachilu-browser skills get core --full # include references and templates when needed
The CLI serves skill content that matches the installed version, so instructions do not drift when the package is upgraded. The core guide contains the Kachilu human-like interaction defaults, control-plane routing rules, rich composer safeguards, CAPTCHA workflow, and the command reference.
If the host already provides a pre-attached browser session, CDP endpoint,
session ref file, or explicit kachilu-browser --session ... --cdp ... command,
use that host-provided session through the CLI. Do not switch to MCP
prepare_workspace or auto-connect unless the core guide says that no
host-provided session is available.
For MCP hosts such as OpenClaw, keep using the same prepared workspace session
across related browser work in one user request, even when moving between sites
such as LinkedIn and X. The site hint is for routing only. Do not close the
workspace between those steps unless the user explicitly wants cleanup. If the
daemon still exists but the browser connection is gone, treat that workspace as
stale and reconnect instead of reusing it.
Critical Fallback
If an element-targeted click fails but the visible cursor is already on the intended button or control, take a screenshot/capture and confirm the cursor is on target. Then click at the current cursor position:
kachilu-browser mouse down left
kachilu-browser mouse up left
kachilu-browser snapshot -i
Use this after visual confirmation instead of repeating the same failing ref or locator click.
04 同仓库更多 Skills
migrate-to-e2e
Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for /migrate-to-e2e, "migrate our tests to e2e", "port these Maestro flows", "move our TesterArmy tests", or when a project has an e2e config and an older suite still running.
e2e
Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.
create-verification-skill
Generate a project-local verify-<app> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for /create-verification-skill, "make a verification skill for this repo", or when a project has no scripted way to prove UI behavior.
deja-search
deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.
deja-reflect
End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.
revid
Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.