Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
op7418 avatar

Claude To Im

op7418/claude-to-im-skill

  • 6.9k installs
  • 2.8k repo stars
  • Updated March 23, 2026
  • op7418/claude-to-im-skill

A daemon-based bridge that forwards Claude Code or Codex agent sessions to messaging platforms, enabling mobile chat and remote tool permission approval through platform-specific interfaces.

About

claude-to-im bridges active Claude Code or Codex sessions to messaging platforms, letting developers chat with Claude from mobile devices. It forwards Claude replies to Telegram, Discord, Feishu/Lark, QQ, or WeChat and handles permission approval through inline buttons or text commands. The skill manages a background daemon that maintains WebSocket or long-polling connections to both the messaging platform and the local Claude SDK. Developers use subcommands (setup, start, stop, status, logs, reconfigure, doctor) to configure credentials, start/stop the bridge, and diagnose issues. Setup requires platform-specific bot tokens or QR login and validates credentials before writing config. The daemon persists across terminal sessions and stores data at ~/.claude-to-im/. Each platform has different capabilities: Telegram and Feishu support streaming previews and inline permission buttons, while QQ and WeChat use text commands only.

  • Bridges Claude Code/Codex to Telegram, Discord, Feishu, QQ, WeChat for mobile chat and remote permission approval
  • Manages background daemon with start/stop/status/logs/doctor subcommands and credential validation during setup
  • Supports streaming previews and inline permission buttons on Telegram/Feishu; text-based permissions on QQ/WeChat
  • Interactive setup wizard (Claude Code) collects tokens one at a time, masks secrets in output, validates credentials bef
  • Feishu requires two-phase setup: publish permissions/bot first, then configure events/callbacks after bridge starts

Claude To Im by the numbers

  • 6,929 all-time installs (skills.sh)
  • +26 installs in the week ending Jul 28, 2026 (Skillselion tracking)
  • Ranked #114 of 16,659 AI & Agent Building skills by installs in the Skillselion catalog
  • Security screen: HIGH risk (skills.sh audit)
  • Data as of Jul 28, 2026 (Skillselion catalog sync)
At a glance

claude-to-im capabilities & compatibility

Free (requires bot tokens or QR login from messaging platforms; Claude/Codex runtime costs separate)

Capabilities
bridge claude sessions to telegram/discord/feish · interactive credential setup with one field at a · token validation before writing config · daemon process management (start/stop/status/log · platform specific permission approval (inline bu · streaming preview support on telegram and feishu · diagnostic tooling with doctor subcommand · credential reconfiguration with masked secret di
Works with
openai
Use cases
orchestration · memory · planning
Platforms
macOS · Linux · Windows
Runs
Runs locally
Pricing
Free
From the docs

What claude-to-im says it does

Bridge THIS Claude Code or Codex session to Telegram, Discord, Feishu/Lark, QQ, or WeChat so the user can chat with Claude from their phone.
SKILL.md
Always mask secrets in output (show only last 4 characters) — users often share terminal output in bug reports, so exposed tokens would be a security incident.
SKILL.md
npx skills add https://github.com/op7418/claude-to-im-skill --skill claude-to-im

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs6.9k
repo stars★ 2.8k
Security audit2 / 3 scanners passed
Last updatedMarch 23, 2026
Repositoryop7418/claude-to-im-skill ↗

What it does

Bridge Claude Code/Codex sessions to messaging platforms (Telegram, Discord, Feishu, QQ, WeChat) so developers can chat with Claude from their phone and approve tool permissions remotely.

Who is it for?

Developers who need mobile access to Claude agent sessions, remote approval of tool permissions during long-running tasks, or team-based Claude interactions through messaging platforms.

Skip if: Building standalone chatbots unrelated to Claude sessions, webhook integrations, or coding with messaging platform SDKs (those are regular programming tasks).

When should I use this skill?

Setting up a bridge between Claude and a messaging platform, starting or stopping the bridge daemon, diagnosing connection issues, or reconfiguring credentials after platform changes.

What you get

Developers can chat with Claude and approve tool permissions from their phone via Telegram/Discord/Feishu/QQ/WeChat while the agent session runs on their desktop.

  • Background daemon process forwarding messages between Claude and messaging platform
  • Config file at ~/.claude-to-im/config.env with validated credentials
  • Platform-specific bot or linked account receiving Claude replies

By the numbers

  • Supports 5 messaging platforms: Telegram, Discord, Feishu/Lark, QQ, WeChat
  • 7 subcommands: setup, start, stop, status, logs, reconfigure, doctor
  • Feishu requires 6 additional permissions for full functionality (cardkit:card:write, cardkit:card:read, im:message:updat

Files

SKILL.mdMarkdownGitHub ↗

Claude-to-IM Bridge Skill

You are managing the Claude-to-IM bridge. User data is stored at ~/.claude-to-im/.

The skill directory (SKILL_DIR) is at ~/.claude/skills/claude-to-im. In Codex installs it may instead be ~/.codex/skills/Claude-to-IM-skill. If neither path exists, fall back to Glob with pattern **/skills/**/claude-to-im/SKILL.md or **/skills/**/Claude-to-IM-skill/SKILL.md and derive the root from the result.

Command parsing

Parse the user's intent from $ARGUMENTS into one of these subcommands:

User says (examples)Subcommand
setup, configure, 配置, 我想在飞书上用 Claude, 帮我连接 Telegram, 帮我接微信setup
start, start bridge, 启动, 启动桥接start
stop, stop bridge, 停止, 停止桥接stop
status, bridge status, 状态, 运行状态, 怎么看桥接的运行状态status
logs, logs 200, 查看日志, 查看日志 200logs
reconfigure, 修改配置, 帮我改一下 token, 换个 botreconfigure
doctor, diagnose, 诊断, 挂了, 没反应了, bot 没反应, 出问题了doctor

Disambiguation: `status` vs `doctor` — Use status when the user just wants to check if the bridge is running (informational). Use doctor when the user reports a problem or suspects something is broken (diagnostic). When in doubt and the user describes a symptom (e.g., "没反应了", "挂了"), prefer doctor.

Extract optional numeric argument for logs (default 50).

Before asking users for any platform credentials, read SKILL_DIR/references/setup-guides.md internally so you know where to find each credential. Do NOT dump the full guide to the user upfront — only mention the specific next step they need to do (e.g., "Go to https://open.feishu.cn → your app → Credentials to find the App ID"). If the user says they don't know how, then show the relevant section of the guide.

Runtime detection

Before executing any subcommand, detect which environment you are running in:

1. Claude Code — AskUserQuestion tool is available. Use it for interactive setup wizards. 2. Codex / other — AskUserQuestion is NOT available. Fall back to non-interactive guidance: explain the steps, show SKILL_DIR/config.env.example, and ask the user to create ~/.claude-to-im/config.env manually.

You can test this by checking if AskUserQuestion is in your available tools list.

Config check (applies to start, stop, status, logs, reconfigure, doctor)

Before running any subcommand other than setup, check if ~/.claude-to-im/config.env exists:

  • If it does NOT exist:
  • In Claude Code: tell the user "No configuration found" and automatically start the setup wizard using AskUserQuestion.
  • In Codex: tell the user "No configuration found. Please create ~/.claude-to-im/config.env based on the example:" then show the contents of SKILL_DIR/config.env.example and stop. Don't attempt to start the daemon — without config.env the process will crash on startup and leave behind a stale PID file that blocks future starts.
  • If it exists: proceed with the requested subcommand.

Subcommands

setup

Run an interactive setup wizard. This subcommand requires AskUserQuestion. If it is not available (Codex environment), instead show the contents of SKILL_DIR/config.env.example with field-by-field explanations and instruct the user to create the config file manually.

When AskUserQuestion IS available, collect input one field at a time. After each answer, confirm the value back to the user (masking secrets to last 4 chars only) before moving to the next question.

Step 1 — Choose channels

Ask which channels to enable (telegram, discord, feishu, qq, weixin). Accept comma-separated input. Briefly describe each:

  • telegram — Best for personal use. Streaming preview, inline permission buttons.
  • discord — Good for team use. Server/channel/user-level access control.
  • feishu (Lark) — For Feishu/Lark teams. Streaming cards, tool progress, inline permission buttons.
  • qq — QQ C2C private chat only. No inline permission buttons, no streaming preview. Permissions use text /perm ... commands.
  • weixin — WeChat QR login. Single linked account only; a new login replaces the previous one. No inline permission buttons, no streaming preview. Permissions use text /perm ... commands or quick 1/2/3 replies. Voice messages only use WeChat's own speech-to-text text; raw voice audio is not transcribed by the bridge.

Step 2 — Collect tokens per channel

For each enabled channel, collect one credential at a time. Tell the user where to find each value in one sentence. Only show the full guide section (from SKILL_DIR/references/setup-guides.md) if the user asks for help or says they don't know how:

  • Telegram: Bot Token → confirm (masked) → Chat ID (see guide for how to get it) → confirm → Allowed User IDs (optional). Important: At least one of Chat ID or Allowed User IDs must be set, otherwise the bot will reject all messages.
  • Discord: Bot Token → confirm (masked) → Allowed User IDs → Allowed Channel IDs (optional) → Allowed Guild IDs (optional). Important: At least one of Allowed User IDs or Allowed Channel IDs must be set, otherwise the bot will reject all messages (default-deny).
  • Feishu: App ID → confirm → App Secret → confirm (masked) → Domain (optional) → Allowed User IDs (optional). After collecting credentials, explain the two-phase setup the user must complete:
  • Phase 1 (before starting bridge): (A) batch-add permissions, (B) enable bot capability, (C) publish first version + admin approve. This makes permissions and bot effective.
  • Phase 2 (requires running bridge): (D) run /claude-to-im start, (E) configure events (im.message.receive_v1) and callback (card.action.trigger) with long connection mode, (F) publish second version + admin approve.
  • Why two phases: Feishu validates WebSocket connection when saving event subscription — if the bridge isn't running, saving will fail. The bridge needs published permissions to connect.
  • Keep this to a short checklist — show the full guide only if asked.
  • QQ: Collect two required fields, then optional ones:

1. QQ App ID (required) → confirm 2. QQ App Secret (required) → confirm (masked)

  • Tell the user: these two values can be found at https://q.qq.com/qqbot/openclaw

3. Allowed User OpenIDs (optional, press Enter to skip) — note: this is user_openid, NOT QQ number. If the user doesn't have openid yet, they can leave it empty. 4. Image Enabled (optional, default true, press Enter to skip) — if the underlying provider doesn't support image input, set to false 5. Max Image Size MB (optional, default 20, press Enter to skip)

  • Remind user: QQ first version only supports C2C private chat sandbox access. No group/channel support, no inline buttons, no streaming preview.
  • Weixin: Do not ask for a static token. Instead:

1. Tell the user this channel uses QR login, not manual credential entry. 2. Run cd SKILL_DIR && npm run weixin:login 3. The helper writes ~/.claude-to-im/runtime/weixin-login.html and tries to open it automatically in the local browser. 4. If auto-open fails, tell the user to open that HTML file manually and scan the QR code with WeChat. 5. Wait for the helper to report success, then confirm that the linked account was saved locally.

  • Explain briefly: the linked Weixin account is stored in ~/.claude-to-im/data/weixin-accounts.json. Running the helper again replaces the previously linked account.
  • Explain briefly: CTI_WEIXIN_MEDIA_ENABLED only controls inbound image/file/video downloads. For voice messages, the bridge only accepts the text returned by WeChat's built-in speech-to-text. If WeChat does not provide a transcript, the bridge replies with an error instead of downloading/transcribing raw audio.

Step 3 — General settings

Ask for runtime, default working directory, model, and mode:

  • Runtime: claude (default), codex, auto
  • claude — uses Claude Code CLI + Claude Agent SDK (requires claude CLI installed)
  • codex — uses OpenAI Codex SDK (requires codex CLI; auth via codex auth login or OPENAI_API_KEY)
  • auto — tries Claude first, falls back to Codex if Claude CLI not found
  • Working Directory: default $CWD
  • Model (optional): Leave blank to inherit the runtime's own default model. If the user wants to override, ask them to enter a model name. Do NOT hardcode or suggest specific model names — the available models change over time.
  • Mode: code (default), plan, ask

Step 4 — Write config and validate

1. Show a final summary table with all settings (secrets masked to last 4 chars) 2. Ask user to confirm before writing 3. Use Bash to create directory structure: mkdir -p ~/.claude-to-im/{data,logs,runtime,data/messages} 4. Use Write to create ~/.claude-to-im/config.env with all settings in KEY=VALUE format 5. Use Bash to set permissions: chmod 600 ~/.claude-to-im/config.env 6. Validate tokens — read SKILL_DIR/references/token-validation.md for the exact commands and expected responses for each platform. This catches typos and wrong credentials before the user tries to start the daemon. For Weixin, a successful QR login already counts as validation. 7. Report results with a summary table. If any validation fails, explain what might be wrong and how to fix it. 8. On success, tell the user: "Setup complete! Run /claude-to-im start to start the bridge."

start

Pre-check: Verify ~/.claude-to-im/config.env exists (see "Config check" above). Without it, the daemon will crash immediately and leave a stale PID file.

Run: bash "SKILL_DIR/scripts/daemon.sh" start

Show the output to the user. If it fails, tell the user:

  • Run doctor to diagnose: /claude-to-im doctor
  • Check recent logs: /claude-to-im logs

stop

Run: bash "SKILL_DIR/scripts/daemon.sh" stop

status

Run: bash "SKILL_DIR/scripts/daemon.sh" status

logs

Extract optional line count N from arguments (default 50). Run: bash "SKILL_DIR/scripts/daemon.sh" logs N

reconfigure

1. Read current config from ~/.claude-to-im/config.env 2. Show current settings in a clear table format, with all secrets masked (only last 4 chars visible) 3. Use AskUserQuestion to ask what the user wants to change 4. When collecting new values, tell the user where to find the value; only show the full guide from SKILL_DIR/references/setup-guides.md if they ask for help 5. Update the config file atomically (write to tmp, rename) 6. Re-validate any changed tokens 7. Remind user: "Run /claude-to-im stop then /claude-to-im start to apply the changes."

If the user wants to switch Weixin accounts during reconfigure, run cd SKILL_DIR && npm run weixin:login again. Each successful scan replaces the previously linked local account.

doctor

Run: bash "SKILL_DIR/scripts/doctor.sh"

Show results and suggest fixes for any failures. Common fixes:

  • SDK cli.js missing → cd SKILL_DIR && npm install
  • dist/daemon.mjs stale → cd SKILL_DIR && npm run build
  • Config missing → run setup
  • Weixin account missing / expired → cd SKILL_DIR && npm run weixin:login
  • Weixin voice message reports missing speech-to-text → enable WeChat's own voice transcription and resend; the bridge does not transcribe raw voice audio itself

For more complex issues (messages not received, permission timeouts, high memory, stale PID files), read SKILL_DIR/references/troubleshooting.md for detailed diagnosis steps.

Feishu upgrade note: If the user upgraded from an older version of this skill and Feishu is returning permission errors (e.g. streaming cards not working, typing indicators failing, permission buttons unresponsive), the root cause is almost certainly missing permissions or callbacks in the Feishu backend. Refer the user to the "Upgrading from a previous version" section in SKILL_DIR/references/setup-guides.md — they need to add new scopes (cardkit:card:write, cardkit:card:read, im:message:update, im:message.reactions:read, im:message.reactions:write_only), add the card.action.trigger callback, and re-publish the app. The upgrade requires two publish cycles because adding the callback needs an active WebSocket connection (bridge must be running).

Notes

  • Always mask secrets in output (show only last 4 characters) — users often share terminal output in bug reports, so exposed tokens would be a security incident.
  • Always check for config.env before starting the daemon — without it the process crashes on startup and leaves a stale PID file that blocks future starts (requiring manual cleanup).
  • The daemon runs as a background Node.js process managed by platform supervisor (launchd on macOS, setsid on Linux, WinSW/NSSM on Windows).
  • Config persists at ~/.claude-to-im/config.env — survives across sessions.

Related skills

mattpocockSetup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la462k185klarksuiteLark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.379k15.8kjuliusbrusseeCavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.378k92.5kopen.feishu.cnLark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.375kxixu-meRunning Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72runcomfy-comCodex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k8

How it compares

Session bridge for existing Claude Code/Codex installs; not a framework for building custom chatbots.

FAQ

Why does Feishu setup require two publish cycles?

Feishu validates the WebSocket connection when saving event subscription. The bridge needs published permissions to connect, but the event config needs a running bridge. Phase 1 publishes permissions/bot so the bridge can start, Phase 2 adds events/callbacks after the bridge is r

What's the difference between status and doctor subcommands?

status shows if the bridge daemon is currently running (informational). doctor runs diagnostics when something is broken - checks for missing SDK files, stale config, expired Weixin accounts, permission errors, and refers to troubleshooting guides.

How does permission approval work on different platforms?

Telegram and Feishu show inline buttons for immediate approval/rejection. QQ and WeChat use text commands (/perm ...) or quick reply numbers (1/2/3) since they don't support inline interactive elements in the current API version.

Is Claude To Im safe to install?

skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

AI & Agent Buildingagentsautomation
Browse by category
AI & AgentsFrontend & DesignBackend & DataDev ToolsAutomationTesting & ReviewSecurityMonitoring & CloudDocs & Planning
Design & frontend
Design systemsAnimation & motionAccessibility (a11y)CSS & TailwindUI designUXDesign to codeshadcn/uiLanding pagesBest design skills
Most searched skills
find-skillscavemanfrontend-designbrainstormingsystematic-debuggingstop-slopemil-design-engui-ux-pro-maxkarpathy-guidelinesweb-design-guidelinesreact-best-practicesgrill-meimprovemicrosoft-foundryagent-browser
Browse all listings
All agent skillsAll MCP serversAll marketplacesAll plugins

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.