walletchan
Interact with web3 dapps using the WalletChan browser extension via Chrome CDP. Use when the user asks to connect a wallet, swap tokens, supply/deposit to DeFi protocols, sign messages, view balances on-chain, or perform any blockchain transaction through a dapp in the browser. Requires Chrome with remote debugging and the WalletChan extension installed.
Best use case
walletchan is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Interact with web3 dapps using the WalletChan browser extension via Chrome CDP. Use when the user asks to connect a wallet, swap tokens, supply/deposit to DeFi protocols, sign messages, view balances on-chain, or perform any blockchain transaction through a dapp in the browser. Requires Chrome with remote debugging and the WalletChan extension installed.
Teams using walletchan should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/walletchan/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How walletchan Compares
| Feature / Agent | walletchan | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Interact with web3 dapps using the WalletChan browser extension via Chrome CDP. Use when the user asks to connect a wallet, swap tokens, supply/deposit to DeFi protocols, sign messages, view balances on-chain, or perform any blockchain transaction through a dapp in the browser. Requires Chrome with remote debugging and the WalletChan extension installed.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
SKILL.md Source
# WalletChan — Browser Wallet Agent Skill Control the [WalletChan](https://walletchan.com/) browser extension to interact with any web3 dapp via Chrome DevTools Protocol (CDP). ## Prerequisites 1. **Chrome** installed with remote debugging enabled (e.g. `--remote-debugging-port=9222`) 2. **WalletChan extension** installed from the [Chrome Web Store](https://chromewebstore.google.com/detail/walletchan/kofbkhbkfhiollbhjkbebajngppmpbgc) 3. **Agent password configured** — the user must set an Agent Password in WalletChan settings before the agent can operate > **⚠️ IMPORTANT — Tell the user:** > - Set an **Agent Password** in WalletChan settings and share it with the agent. > - **NEVER share the Master Password** with ANY agent. The Master Password controls private key access. Agents must ONLY ever receive the Agent Password. > - The Agent Password grants limited scope: unlock the wallet, review & confirm transactions. It cannot reveal or export private keys. ## Setup ### Launch Chrome with CDP The user needs Chrome running with remote debugging. Example launch script: ```bash "/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" \ --remote-debugging-port=9222 \ --user-data-dir="$HOME/.walletchan-agent/chrome-profile" \ --no-first-run \ --no-default-browser-check ``` Adjust the path for the user's OS. The `user-data-dir` should be a dedicated profile with the WalletChan extension installed. ### Get the Extension ID - **Chrome Web Store build:** `kofbkhbkfhiollbhjkbebajngppmpbgc` (stable) - **Local/dev builds:** ID varies — navigate to `chrome://extensions/` via CDP and read it The extension's full-tab URL is: `chrome-extension://<EXTENSION_ID>/index.html` ### Connect via CDP Connect to Chrome using CDP on the configured port (default `9222`). All interaction happens through browser automation — navigate tabs, click elements, read page content. **Always use CDP** for tab control. Chrome sidepanels are NOT accessible via CDP, so WalletChan must be used in **full-tab mode** (open `chrome-extension://<ID>/index.html` in a tab). ## Core Workflow ### 1. Navigate to the dapp Open the target dapp URL in a Chrome tab (e.g. `app.aave.com`, `app.uniswap.org`). ### 2. Connect wallet Click the dapp's "Connect Wallet" button and select **"WalletChan"** from the wallet list. Connection is instant — no popup or approval needed. ### 3. Interact with the dapp Perform the intended action: enter amounts, select tokens, click "Supply", "Swap", etc. This triggers a transaction or signature request in WalletChan. ### 4. Switch to the extension tab Navigate to the WalletChan tab (`chrome-extension://<ID>/index.html`) so the request is visible. **Always switch the visible/active tab** — the user can only see the active tab, so switch to whichever tab you're working on. ### 5. Check lock state & unlock WalletChan has an **auto-lock** feature — the wallet locks after inactivity. Before confirming any request: 1. Check if the wallet is locked (password prompt visible) 2. If locked, enter the **Agent Password** and click Unlock 3. The pending request will appear after unlocking ### 6. Review the request WalletChan provides two views for each request: - **Decoded tab** — human-readable breakdown of the transaction: - Function name and parameters - Recursively decoded nested calldata (e.g. bytes params containing inner calldata) - Auto-resolved ENS, Basename (`.base.eth`), and `.wei` domains for addresses - Labels for known contract addresses - Unit conversion dropdowns for uint params (wei→ETH, unix timestamps, 10^6, bps, etc.) - Some params (like `bytes`) may be collapsed — expand for full detail - **Raw tab** — raw calldata/signature data for manual verification **Verify before confirming:** - Correct function being called - Correct token/asset addresses - Correct amounts (watch decimals — e.g. USDC uses 6 decimals, so 1 USDC = 1,000,000) - Correct recipient/`onBehalfOf` address - Correct network - Gas estimation succeeded (if it shows the tx would revert, investigate before confirming) ### 7. Confirm or reject - **Confirm** if everything matches the intended action - **Reject** if anything looks wrong, and inform the user - **Ask the user** if uncertain about any detail ### 8. Switch back & verify After confirming, switch back to the dapp tab and verify the result: - Success toast/notification - Updated balances or positions - Transaction hash (link to block explorer if available) **Never assume success** — always check actual state changes on the dapp. ## Gotchas - **Auto-lock is real.** The wallet locks after inactivity. Always check lock state before attempting to confirm a transaction. If you get an "Invalid Password" error, the wallet may have locked between actions — just unlock again. - **Full-tab mode only.** Chrome sidepanels are not accessible via CDP. Always open the extension URL in a regular tab. - **Always switch the active tab.** The user monitors progress by watching the browser. If you're working in a background tab, the user sees nothing. Switch to the tab you're interacting with. - **Decimals vary by token.** ETH/WETH = 18 decimals, USDC/USDT = 6 decimals, DAI = 18. Always verify amounts accounting for the token's decimals. - **Gas estimation failure = likely revert.** If WalletChan shows the transaction would revert, do NOT confirm. Investigate the cause first. - **Tenderly simulation** — WalletChan has a "Simulate on Tenderly" button on the request page. Only use it when: the user asks for a simulation, the tx shows it would revert (to debug why), or something looks off and needs verification before broadcasting.
Related Skills
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.
notebooklm
Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。
小红书长图文发布 Skill
## 概述