Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Feishu Bridge — measured AI agent skill | DecimalAI

sundial-org/feishu-bridge

NewSkillScoreMaintained

Connect a Feishu (Lark) bot to Clawdbot via WebSocket long-connection. No public server, domain, or ngrok required. Use when setting up Feishu/Lark as a messaging channel, troubleshooting the Feishu bridge, or managing the bridge service (start/stop/logs). Covers bot creation on Feishu Open Platform, credential setup, bridge startup, macOS launchd auto-restart, and group chat behavior tuning.

agent-toolingby sundial-org

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Coding pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/sundial-org-feishu-bridge/SKILL.md

decimalai skills pull sundial-org-feishu-bridge --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/sundial-org-feishu-bridge/SKILL.md https://app.decimal.ai/s/sundial-org-feishu-bridge/SKILL.md

Raw file: /s/sundial-org-feishu-bridge/SKILL.md ↗ · machine-readable summary at /s/sundial-org-feishu-bridge.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 3h ago

Yes — +55% lift-23% tokens0% turns95% of whole cases pass with skill (21/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-03	✗→✓	▲ Improved	-11%	0%
case-01	✗→✓	▲ Improved	-31%	0%
case-02	✗→✓	▲ Improved	-32%	0%
case-06	✗→✓	▲ Improved	69%	0%
case-13	✗→✓	▲ Improved	-55%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

sundial-org / awesome-openclaw-skills

skills/feishu-bridge/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Skill contents

SKILL.md

Feishu Bridge

Bridge Feishu bot messages to Clawdbot Gateway over local WebSocket.

Architecture

Feishu user → Feishu cloud ←WS→ bridge.mjs (local) ←WS→ Clawdbot Gateway → AI agent

Feishu SDK connects outbound (no inbound port / public IP needed)
Bridge authenticates to Gateway using the existing gateway token
Each Feishu chat maps to a Clawdbot session (feishu:<chatId>)

Setup

1. Create Feishu bot

Go to open.feishu.cn/app → Create self-built app → Add Bot capability
Enable permissions: im:message, im:message.group_at_msg, im:message.p2p_msg
Events: add im.message.receive_v1, set delivery to WebSocket long-connection
Publish the app (create version → request approval)
Note the App ID and App Secret

2. Store secret

bash
mkdir -p ~/.clawdbot/secrets
echo "YOUR_APP_SECRET" > ~/.clawdbot/secrets/feishu_app_secret
chmod 600 ~/.clawdbot/secrets/feishu_app_secret

3. Install & run

bash
cd <skill-dir>/feishu-bridge
npm install
FEISHU_APP_ID=cli_xxx node bridge.mjs

4. Auto-start (macOS)

bash
FEISHU_APP_ID=cli_xxx node setup-service.mjs
launchctl load ~/Library/LaunchAgents/com.clawdbot.feishu-bridge.plist

Diagnostics

bash
# Check service
launchctl list | grep feishu

# Logs
tail -f ~/.clawdbot/logs/feishu-bridge.err.log

# Stop
launchctl unload ~/Library/LaunchAgents/com.clawdbot.feishu-bridge.plist

Group chat behavior

Bridge replies only when: user @-mentions the bot, message ends with ?/？, contains request verbs (帮/请/分析/总结…), or calls the bot by name. Customize the name list in bridge.mjs → shouldRespondInGroup().

Environment variables

| Variable | Required | Default | |---|---|---| | FEISHU_APP_ID | ✅ | — | | FEISHU_APP_SECRET_PATH | — | ~/.clawdbot/secrets/feishu_app_secret | | CLAWDBOT_CONFIG_PATH | — | ~/.clawdbot/clawdbot.json | | CLAWDBOT_AGENT_ID | — | main | | FEISHU_THINKING_THRESHOLD_MS | — | 2500 |

Want to see if sundial-org/feishu-bridge would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.