Add Feishu (飞书/Lark) as a channel. Uses WebSocket long connection mode — no public URL needed. Bot responds to all messages (no trigger required).
npx skills add https://github.com/sugarforever/01coder-agent-skills --skill add-feishu
This skill adds Feishu (飞书) support to NanoClaw using the skills engine for deterministic code changes, then walks through interactive setup.
Read .nanoclaw/state.yaml. If feishu is in applied_skills, skip to Phase 3 (Setup). The code changes are already in place.
Use AskUserQuestion to collect configuration:
AskUserQuestion: Do you have a Feishu app already, or do you need to create one?
If they have one, collect FEISHU_APP_ID and FEISHU_APP_SECRET now. If not, we'll create one in Phase 3.
Run the skills engine to apply this skill's code package. The package files are in this directory alongside this SKILL.md.
If .nanoclaw/ directory doesn't exist yet:
npx tsx scripts/apply-skill.ts --init
npx tsx scripts/apply-skill.ts .claude/skills/add-feishu
This deterministically:
src/channels/feishu.ts (FeishuChannel class implementing Channel interface)src/index.ts (reads credentials via readEnvFile, creates FeishuChannel if configured)@larksuiteoapi/node-sdk npm dependency.env with FEISHU_APP_ID and FEISHU_APP_SECRET.nanoclaw/state.yamlIf the apply reports merge conflicts, read the intent file:
modify/src/index.ts.intent.md — what changed and invariants for index.tsnpm run build
Build must be clean before proceeding.
If the user doesn't have a Feishu app, tell them:
> I need you to create a Feishu bot:
>
> 1. Go to Feishu Open Platform and create a new app
> 2. Under Credentials, copy the App ID and App Secret
> 3. Under Event Subscriptions, enable Long Connection (WebSocket) mode
> 4. Add the event: im.message.receive_v1 (Receive messages)
> 5. Under Permissions, add:
> - im:message:send_as_bot (Send messages as bot)
> - im:message (Read messages)
> 6. Publish the app (or create a version and approve it)
Wait for the user to provide the App ID and App Secret.
Add to .env:
FEISHU_APP_ID=<their-app-id>
FEISHU_APP_SECRET=<their-app-secret>
npm run build
launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS
# Linux: systemctl --user restart nanoclaw
Tell the user:
> 1. Start the bot: npm run dev
> 2. Send any message to the bot in Feishu (DM or group)
> 3. Check the logs — the chat_id will appear in the metadata
> 4. The JID format is {chat_id}@feishu
Or check the database directly:
sqlite3 store/messages.db "SELECT jid FROM chats WHERE jid LIKE '%@feishu'"
Register directly in SQLite:
INSERT INTO registered_groups (jid, name, folder, trigger_pattern, added_at, requires_trigger)
VALUES ('{chat_id}@feishu', 'feishu', 'feishu', '@{ASSISTANT_NAME}', datetime('now'), 0);
Note: requires_trigger is set to 0 (false) so the bot responds to all messages without needing @mention.
Then restart the service to pick up the new registration.
Tell the user:
> Send a message to the bot in Feishu. It should respond within a few seconds.
tail -f logs/nanoclaw.log
# Or run interactively:
npm run dev
Look for:
Feishu bot info fetched — bot connected and identified itselfConnected to Feishu via WebSocket — WebSocket establishedFeishu message sent — outbound message deliveredCheck:
FEISHU_APP_ID and FEISHU_APP_SECRET are set in .envsqlite3 store/messages.db "SELECT * FROM registered_groups WHERE jid LIKE '%@feishu'"im.message.receive_v1 is enabledlaunchctl list | grep nanoclaw (macOS) or systemctl --user status nanoclaw (Linux)im:message permissionim.message.receive_v1 is subscribedim:message:send_as_bot permissionNon-critical warning. Bot message detection (filtering own messages) won't work, but message sending/receiving still functions. Usually means the bot API endpoint isn't accessible — check network connectivity.
To remove Feishu integration:
src/channels/feishu.tsFeishuChannel import and creation block from src/index.tsreadEnvFile import if no other channel uses itFEISHU_APP_ID and FEISHU_APP_SECRET from .envsqlite3 store/messages.db "DELETE FROM registered_groups WHERE jid LIKE '%@feishu'"npm uninstall @larksuiteoapi/node-sdknpm run build && launchctl kickstart -k gui/$(id -u)/com.nanoclaw (macOS) or npm run build && systemctl --user restart nanoclaw (Linux)Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take sugarforever/add-feishu from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference npx.
Without those the skill loads but fails at the first command.