feishu-e2e-test — Claude Code skill: local Feishu bot testing
feishu-e2e-test is a Claude Code skill for debugging and end-to-end testing a Feishu bot on a developer's machine, including responses and document interactions through the web interface.
MIT 122 installs ★ 4,217 updated 2026-03-29
npx skills add m1heng/clawdbot-feishu --skill feishu-e2e-test -a claude-codeWhat feishu-e2e-test does
This skill provides local testing tools for OpenClaw-Feishu integration: launch a browser session with agent-browser, log into Feishu web, send messages to your bot letter by letter, and monitor gateway logs to verify behavior. Requires OpenClaw, agent-browser CLI, and access to https://feishu.cn/next/messenger.
The framework includes strategies for reliable Feishu web UI interaction: search chats with Cmd+K instead of clicking, focus input with "/", and type text character by character since type command often fails on special characters. Chinese characters don't work with press — use English only. Full document URLs are more reliable than document IDs.
Restart the OpenClaw gateway with openclaw gateway restart after every code change for modifications to take effect. Monitor ~/.openclaw/logs/gateway.log to trace message flow, confirm agent execution, and verify which tools were called.
What it helps with
- debug message flow between bot and Feishu
- verify bot responses to commands
- confirm bot can read Feishu documents
- test tool execution through web UI
Example prompts for the agent
- Start testing:
agent-browser --headed --session feishu-test open "https://feishu.cn/next/messenger", search for bot by name (Cmd+K), send a test message - Verify document tool works: send bot a full URL like
https://feishu.cn/docx/YOUR_DOC_IDand check logs withtail -f ~/.openclaw/logs/gateway.log - After code changes, run
openclaw gateway restartand send a test message to confirm the new version is live
How to install feishu-e2e-test
1Skills CLI (Vercel)
npx skills add m1heng/clawdbot-feishu --skill feishu-e2e-test -a claude-code2Manually: put the files in place
~/.claude/skills/feishu-e2e-test/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/feishu-e2e-test/
1Skills CLI (Vercel)
npx skills add m1heng/clawdbot-feishu --skill feishu-e2e-test -a codex2Manually: put the files in place
.agents/skills/feishu-e2e-test/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add m1heng/clawdbot-feishu --skill feishu-e2e-test -a cursor2Manually: put the files in place
.cursor/skills/feishu-e2e-test/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install m1heng/clawdbot-feishu .claude/skills/feishu-e2e-test2Manually: put the files in place
.github/skills/feishu-e2e-test/SKILL.md1Skills CLI (Vercel)
npx skills add m1heng/clawdbot-feishu --skill feishu-e2e-test -a gemini-cli2Platform CLI
gemini skills install https://github.com/m1heng/clawdbot-feishu --path .claude/skills/feishu-e2e-testManually: put the files in place
.devin/skills/feishu-e2e-test/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add m1heng/clawdbot-feishu --skill feishu-e2e-test -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about feishu-e2e-test
How do I install feishu-e2e-test in Claude Code?
Run in order: npx skills add m1heng/clawdbot-feishu --skill feishu-e2e-test -a claude-code, then open ~/.claude/skills/feishu-e2e-test/SKILL.md.
What does feishu-e2e-test do?
Enables local testing of your Feishu bot: open a browser via agent-browser, send messages to the bot, and inspect responses and logs. Catch bugs before deploying to production.
Why can't I type Chinese characters in tests?
The press command doesn't support Chinese characters — use English or Cyrillic only. Type in ASCII if you need to test text processing.
Source text
SKILL.md · MIT
--- name: feishu-e2e-test description: Local E2E debug and test framework for clawd-feishu plugin development. Use when debugging message flow, testing bot responses, verifying Feishu web UI interactions, or performing end-to-end validation of the OpenClaw-Feishu integration during development. allowed-tools: Bash(agent-browser:*) --- # Feishu E2E Test Framework Local development testing using `agent-browser` CLI to interact with Feishu web app. ## Prerequisites - Feishu web logged in at `https://feishu.cn/next/messenger` - `agent-browser` CLI available - OpenClaw locally installed - Feishu bot appid/secret given in chat or in .env - User given bot name which will display in Feishu web UI ## Important Notes **Every time you modify extension code, you MUST restart OpenClaw Gateway for changes to take effect.** ```bash # Restart gateway (required after code changes) openclaw gateway restart # Check if gateway is running ps aux | grep openclaw # View gateway logs tail -f ~/.openclaw/logs/gateway.log ``` ## agent-browser Usage Always use `--headed` mode so user can see the browser and help with login: ```bash agent-browser --headed --session feishu-test open "https://feishu.cn/next/messenger" ``` ## Feishu Web UI Tips Feishu web has complex UI that makes direct clicking unreliable. Use these strategies: ### 1. Use Search (Cmd+K) Instead of Clicking Clicking on chat list items often misses or selects wrong item. Use global search: ```bash # Open search agent-browser --session feishu-test press "Meta+k" # Type bot name letter by letter agent-browser --session feishu-test press "o" agent-browser --session feishu-test press "p" agent-browser --session feishu-test press "e" agent-browser --session feishu-test press "n" # Select first result agent-browser --session feishu-test press "Enter" ``` ### 2. Focus Input with "/" Key After entering a chat, press "/" to focus the message input: ```bash agent-browser --session feishu-test press "/" agent-browser --session feishu-test press "Backspace" # Remove the "/" # Then type your message ``` ### 3. Type Characters One by One The `type` command often fails with special characters. Use `press` for each character: ```bash # Instead of: agent-browser type "ping" agent-browser --session feishu-test press "p" agent-browser --session feishu-test press "i" agent-browser --session feishu-test press "n" agent-browser --session feishu-test press "g" ``` ### 4. Chinese Characters Do NOT Work **Chinese characters cannot be typed with `press` command.** Use English only: ```bash # BAD - Chinese won't render for char in $(echo "读取文档" | grep -o .); do agent-browser --session feishu-test press "$char" # Will fail silently done # GOOD - Use English for char in r e a d " " d o c; do agent-browser --session feishu-test press "$char" done ``` ### 5. Typing Spaces Spaces must be quoted as `" "`: ```bash # Type "read doc" for char in r e a d " " d o c; do agent-browser --session feishu-test press "$char" done ``` ### 6. Typing Long Strings Efficiently Use a for loop to type URLs or long text: ```bash # Type a full URL url="https://feishu.cn/docx/YOUR_DOC_TOKEN" for char in $(echo "$url" | grep -o .); do agent-browser --session feishu-test press "$char" 2>/dev/null || true done ``` ### 7. Avoid JS eval on Feishu Do NOT use `eval` to set input values - it can break the page: ```bash # BAD - will corrupt page agent-browser eval "document.activeElement.innerText = 'text'" # GOOD - use keyboard input agent-browser press "t" && agent-browser press "e" ... ``` ### 8. Full URLs Work Better Than IDs When testing document tools, send full URLs rather than just document IDs: ```bash # Better - bot recognizes as document link "https://feishu.cn/docx/YOUR_DOC_TOKEN" # Less reliable - may not trigger tool "read YOUR_DOC_TOKEN" ``` ## Verifying Tool Calls ### Log Patterns Monitor gateway logs to verify tool execution: ```bash tail -f ~/.openclaw/logs/gateway.log ``` Key log entries: - `[feishu] received message from ...` - incoming message - `[feishu] dispatching to agent` - sent to agent - `[feishu] added typing indicator reaction` - bot is processing - `[feishu] deliver called: text=...` - agent response - `[feishu] dispatch complete` - response sent ### Verify Tool Usage Ask bot explicitly to confirm tool usage: ``` use feishu_doc tool to read YOUR_DOC_TOKEN ``` Look for confirmation in response like: > "我已经用 **Feishu Doc Tool** 读过了这个文档" ## Common Errors ### Permission Error (99991672) ``` Access denied. One of the following scopes is required: [contact:contact.base:readonly...] ``` This means bot lacks contact permission. Doesn't affect core messaging but prevents resolving sender names. ### Other Log Locations ```bash # Error logs tail -f ~/.openclaw/logs/gateway.err.log # All log files ls -la ~/.openclaw/logs/ # Raw agent session records (tool calls, responses, etc.) ls ~/.openclaw/agents/main/sessions/ # View specific session cat ~/.openclaw/agents/main/sessions/<session-id>.json ``` ## Test Workflow 1. Start browser: `agent-browser --headed --session feishu-test open "https://feishu.cn/next/messenger"` 2. User scans QR to login 3. Search for bot: `Cmd+K` → type bot name → `Enter` 4. Focus input: press `/` then `Backspace` 5. Type message (English only, letter by letter) 6. Press `Enter` to send 7. Wait 10-20 seconds for response 8. Take screenshot and check logs to verify ## Testing feishu_doc Tool ```bash # 1. Focus input agent-browser --session feishu-test press "/" && \ agent-browser --session feishu-test press "Backspace" # 2. Type full doc URL url="https://feishu.cn/docx/YOUR_DOC_ID" for char in $(echo "$url" | grep -o .); do agent-browser --session feishu-test press "$char" 2>/dev/null || true done # 3. Send agent-browser --session feishu-test press "Enter" # 4. Wait and check logs sleep 15 && tail -30 ~/.openclaw/logs/gateway.log ```
© m1heng · MIT · m1heng/clawdbot-feishu