[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PDAFWB6672ZE72KVH57MZB":3,"skill-same:01M6PDAFWB6672ZE72KVH57MZB":80},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":33,"commitSha":61,"skillDirectory":62,"forksCount":13,"repositoryHtmlUrl":63,"repositoryHomepageUrl":6,"ownerHtmlUrl":64,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":65,"install":66,"resources":79},"01M6PDAFWB6672ZE72KVH57MZB","textme",null,"Text Claude from your phone — set up the njerschow\u002Ftextme daemon so inbound iMessages drive a Claude Code session on your laptop, with voice notes, image input, code execution, and a phone-number whitelist.","duc-duy-1612\u002FOnline-Delivery-Systems-Web","duc-duy-1612","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F192231384?v=4","01M6NSDKQQDKVTHZ8DZMZ1VYY6","01M6NSDKW8DDVTQHBT1HBDDJPT",0,"MIT","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fsendblue\u002Ftextme\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"critical","voice notes","number","daemon","remote-control","remote","code execution","sms","input","image","main","community","up","text","SET","code","notes","gemini","imessage","2026-11-10 10:12:30",false,"---\nname: textme\ndescription: \"Text Claude from your phone — set up the njerschow\u002Ftextme daemon so inbound iMessages drive a Claude Code session on your laptop, with voice notes, image input, code execution, and a phone-number whitelist.\"\ncategory: automation\nrisk: critical\nsource: community\nsource_repo: njerschow\u002Ftextme\nsource_type: community\ndate_added: \"2026-05-26\"\nauthor: AnthonyFirth\ntags: [textme, sendblue, imessage, sms, claude-code, daemon, remote-control, automation]\ntools: [claude, cursor, gemini]\nlicense: \"MIT\"\nlicense_source: \"https:\u002F\u002Fgithub.com\u002Fnjerschow\u002Ftextme\u002Fblob\u002Fmain\u002FLICENSE\"\nplugin:\n  targets:\n    codex: blocked\n    claude: blocked\n---\n\n# TextMe\n\n## Overview\n\n[`njerschow\u002Ftextme`](https:\u002F\u002Fgithub.com\u002Fnjerschow\u002Ftextme) is a local daemon that bridges inbound iMessages (via [Sendblue](https:\u002F\u002Fsendblue.com)) to a Claude Code session on the user's machine. Whitelisted phone numbers can text, send voice notes, send images, and drive Claude through filesystem operations, code execution, and `cd`-based directory navigation — turning the user's phone into a remote control for Claude on their laptop. This is the **inbound** counterpart to outbound notification patterns ([[sendblue-notify]]): textme is phone → Claude; sendblue-notify is Claude → phone.\n\n## When to Use This Skill\n\n- Use when the user says \"text Claude\", \"text my laptop\", \"drive Claude from my phone\", \"I want to send iMessages to Claude\", or \"let me code from my phone\".\n- Use when the user is heads-down away from their desk and wants to kick off, supervise, or interrupt a Claude session via SMS\u002FiMessage.\n- Use when setting up a long-running headless workstation that the user wants to remote-control while travelling or away from the keyboard.\n- Pair with [[sendblue-notify]] for bidirectional flow — outbound completion pings + inbound commands on the same Sendblue account.\n- Do **not** use for outbound-only \"text me when X finishes\" patterns. That is [[sendblue-notify]] and does not need a daemon.\n\n## Prerequisites\n\n- macOS or Linux host that stays online (the daemon polls Sendblue continuously).\n- Node.js 18+.\n- An active Sendblue account with API credentials and a provisioned iMessage number — set up via [[sendblue-cli]] (`sendblue setup`, then `sendblue show-keys` to surface API key\u002Fsecret).\n- Claude Code installed and authenticated on the host (`npm install -g @anthropic-ai\u002Fclaude-code`).\n- Optional: an OpenAI API key for Whisper voice-note transcription.\n\n## How It Works\n\n### Step 1: Install the daemon\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fnjerschow\u002Ftextme.git\ncd textme\u002Fdaemon\nnpm install\nnpm run build\nmkdir -p ~\u002F.config\u002Fclaude-imessage\n```\n\n### Step 2: Configure credentials and the whitelist\n\nCreate `~\u002F.config\u002Fclaude-imessage\u002Fconfig.json`:\n\n```json\n{\n  \"sendblue\": {\n    \"apiKey\": \"YOUR_SENDBLUE_API_KEY\",\n    \"apiSecret\": \"YOUR_SENDBLUE_API_SECRET\",\n    \"phoneNumber\": \"+1SENDBLUE_NUMBER\"\n  },\n  \"whitelist\": [\"+1YOUR_PHONE\"],\n  \"pollIntervalMs\": 5000,\n  \"conversationWindowSize\": 20\n}\n```\n\nThe `whitelist` is the **only** authorization gate between an inbound iMessage and code execution on the host. Treat it as a security boundary, not a UX preference. Add only phone numbers the user controls; never add a shared, work, or family number \"just in case\".\n\nFor voice transcription, optionally add to `.env` in the daemon directory:\n\n```bash\nOPENAI_API_KEY=sk-...\n```\n\n### Step 3: Run the daemon\n\nFor a quick test run:\n\n```bash\ncd textme\u002Fdaemon\nnpm start\n```\n\nFor persistent operation (recommended once the user has verified behavior):\n\n```bash\npm2 start dist\u002Findex.js --name textme\npm2 save\npm2 startup\n```\n\nOr, on macOS, install the launchd service:\n\n```bash\n.\u002Fscripts\u002Finstall-launchd.sh\n```\n\n### Step 4: Drive Claude from iMessage\n\nOnce the daemon is running, an iMessage from a whitelisted number to the Sendblue phone number reaches Claude. Built-in commands:\n\n| Command | Effect |\n|---|---|\n| `?` | List available commands |\n| `status` | Show current daemon status and working directory |\n| `queue` | Show messages queued for processing |\n| `history` | Recent message history |\n| `home` | `cd` back to home directory |\n| `reset` | Return home and clear conversation history |\n| `cd \u002Fpath` | Change working directory |\n| `stop` | Cancel the current Claude task |\n| `yes` \u002F `no` | Approve or reject the pending action |\n\nAnything else is treated as a Claude prompt and routed to the active session.\n\n### Step 5: Verify before relying on it\n\nBefore using textme in unattended workflows, the user must:\n\n1. Send `status` from the whitelisted phone — should get a directory + state reply.\n2. Send a benign command (`pwd`, `ls`) and confirm output arrives.\n3. Send something from a **non-whitelisted** number and confirm it is **ignored**, not echoed.\n4. Pull the plug: kill the daemon and confirm messages stop being processed (no zombie process).\n\nIf any of these fail, do not enable launchd \u002F pm2 auto-start.\n\n## Examples\n\n### Example 1: Initial setup walk-through\n\n```bash\n# 1. Make sure sendblue CLI is set up and creds work\nsendblue whoami\n\n# 2. Grab Sendblue API key & secret (these are NOT the CLI's bearer token)\nsendblue show-keys\n\n# 3. Clone + build the daemon\ngit clone https:\u002F\u002Fgithub.com\u002Fnjerschow\u002Ftextme.git\ncd textme\u002Fdaemon && npm install && npm run build\n\n# 4. Fill in ~\u002F.config\u002Fclaude-imessage\u002Fconfig.json with the values from step 2\n#    and YOUR personal phone number as the only whitelist entry\n\n# 5. Start, send \"?\" from your phone, confirm response\nnpm start\n```\n\n### Example 2: Composing with `sendblue-notify`\n\nWire outbound completion pings via [[sendblue-notify]] *and* inbound control via textme — they share the same Sendblue account but solve opposite problems:\n\n- Claude finishes a long task → texts user via [[sendblue-notify]] (`Stop` hook).\n- User replies \"look at the diff\" → textme routes that into Claude → Claude responds back via Sendblue.\n\n### Example 3: Tail the daemon log\n\n```bash\n# pm2\npm2 logs textme\n\n# Standalone\ntail -f ~\u002F.local\u002Flog\u002Fclaude-imessage.log\n```\n\n### Example 4: MCP-only alternative (no daemon)\n\nIf the user wants Sendblue messaging available to Claude Code as tools but does **not** want a polling daemon listening for inbound commands, they can register Sendblue as an MCP server instead:\n\n```bash\nclaude mcp add sendblue_api \\\n  --env SENDBLUE_API_API_KEY=your-api-key \\\n  --env SENDBLUE_API_API_SECRET=your-api-secret \\\n  -- npx -y sendblue-api-mcp --client=claude-code --tools=all\n```\n\nThis gives Claude outbound Sendblue tools inside a session but does **not** open the inbound phone-controls-Claude channel that textme provides. Pick textme when \"text Claude from anywhere\" is the goal; pick MCP when Claude only needs to send.\n\n## Best Practices\n\n- ✅ **Whitelist exactly one phone number to start.** The whitelist is the security boundary; expand it slowly and only to numbers the user controls.\n- ✅ **Run the daemon as a regular user**, never as root or via `sudo`.\n- ✅ **Start in a sandbox directory** for first tests (`cd ~\u002Ftextme-sandbox`), not in `~` or a real repo.\n- ✅ **Verify the non-whitelist ignore path** before enabling auto-start. A daemon that processes any sender is an open shell on the host.\n- ✅ **Keep `pollIntervalMs` ≥ 5000** unless the user understands the Sendblue rate limits and cost implications.\n- ❌ **Don't share the Sendblue number publicly.** Even with a whitelist, the host is doing per-message work; a flood from an unknown sender still costs polling cycles.\n- ❌ **Don't store `config.json` in a repo, dotfiles backup, or cloud sync** — it contains API credentials and the user's phone number.\n- ❌ **Don't run the daemon on a shared machine** without considering what every other user of that machine can now reach by sending an SMS.\n\n## Limitations\n\n- **Outbound-only flows do not need this skill.** For \"text me when X finishes\" use [[sendblue-notify]]; running a daemon is overkill.\n- **Voice transcription requires a separate OpenAI API key.** Without it, voice notes are dropped or surfaced as un-transcribed audio depending on daemon version.\n- **The daemon polls on an interval** — there is no push delivery. Expect single-digit-second latency between message receipt and Claude response.\n- **One conversation, one machine.** This is a per-host daemon, not a multi-tenant service. Two daemons sharing one Sendblue number will both try to handle every inbound message.\n- **Sendblue free-plan verification still applies.** The user's phone must have texted the Sendblue number once before outbound responses from Claude reach the user (see [[sendblue-cli]] limitations).\n\n## Security & Safety Notes\n\ntextme is a **remote code execution surface gated only by a phone-number whitelist**. Treat it accordingly.\n\n- **Whitelist is the security boundary.** Anyone who can spoof or hijack a whitelisted number can drive Claude on the host. Be deliberate about which numbers go on the list and remove them when they no longer need access. \u003C!-- security-allowlist: documented remote-control daemon; required disclosure per quality-bar.md -->\n- **Sendblue API credentials are sensitive.** `config.json` contains an API key, API secret, and the user's phone number. Mode it `600`, keep it out of dotfile repos, and never paste it into shared logs, gists, or screenshots.\n- **The daemon inherits the user's privileges.** It can read, write, and execute anything the running user can. Do not run as root, do not run from a directory with secrets the user does not want exposed to inbound SMS, and prefer a dedicated host or VM if available.\n- **Claude Code's permission model still applies inside the daemon-driven session** — destructive actions still surface confirmation prompts. textme exposes the `yes`\u002F`no` reply path for those prompts, which means the *phone number* is making the approval. Make sure the whitelist matches the trust level of approving destructive operations remotely.\n- **Inbound messages are untrusted input.** Treat textme prompts as user input from the open internet (with phone-number authentication). Do not pipe their contents into `eval`, shell substitution, or scripts that bypass Claude Code's review.\n- **Lock-screen previews of replies leak.** When Claude responds to a message, the reply lands on the user's lock screen unredacted. Don't ask Claude over textme to surface secrets, tokens, or customer data via SMS — link to a local log or PR instead.\n- **Daemon liveness is a footgun.** If pm2\u002Flaunchd is auto-restarting the daemon, the user must remember to stop it before changing whitelist entries, rotating credentials, or rebooting into an untrusted state.\n\n## Common Pitfalls\n\n- **Whitelist drift.** A number added \"for a demo\" never gets removed. Audit `whitelist` whenever the host changes hands or scope.\n- **`apiKey` \u002F `apiSecret` confusion.** Sendblue's API credentials (from `sendblue show-keys`) are distinct from the CLI's local bearer token in `~\u002F.sendblue\u002Fcredentials.json`. textme needs the *API* credentials, not the CLI auth file.\n- **Free-plan silent send failures.** If the user's phone never texted the Sendblue number first, outbound replies from Claude silently fail. Verify with `sendblue contacts` before relying on the loop.\n- **Auto-start before verification.** Installing the launchd plist or `pm2 save`-ing the daemon before testing the non-whitelist ignore path will baseline a potentially open daemon at boot. Verify first, persist second.\n- **Running the daemon in `~` or a repo with secrets.** The working directory at startup is exposed to anything textme is told to do (`ls`, `cat`, etc.). Start in a sandbox directory and `cd` deliberately.\n- **Confusing textme with the Sendblue MCP.** They look similar but the MCP variant only gives Claude *outbound* Sendblue tools — it does not open an inbound channel. If the user wants \"text Claude from my phone\", they need textme; if they want \"Claude can send a text mid-session\", the MCP is lighter.\n\n## Related Skills\n\n- `@sendblue-notify` — Outbound counterpart (Claude → phone). Composes with textme to make the loop bidirectional.\n- `@sendblue-cli` — Account setup, credential management, and the `show-keys` command that surfaces the API key\u002Fsecret textme needs.\n- `@sendblue-api` — HTTP API reference for users who want to build a custom inbound handler instead of using textme's daemon.\n- `@update-config` — If wiring textme alongside Claude Code hooks (e.g. a `Stop` hook that pings the user), use this for the settings.json edits.\n\n## Links\n\n- Repository: \u003Chttps:\u002F\u002Fgithub.com\u002Fnjerschow\u002Ftextme>\n- License: \u003Chttps:\u002F\u002Fgithub.com\u002Fnjerschow\u002Ftextme\u002Fblob\u002Fmain\u002FLICENSE> (MIT)\n- Sendblue: \u003Chttps:\u002F\u002Fsendblue.com>\n- Sendblue docs: \u003Chttps:\u002F\u002Fdocs.sendblue.com>\n","# TextMe\n\n## Overview\n\n[`njerschow\u002Ftextme`](https:\u002F\u002Fgithub.com\u002Fnjerschow\u002Ftextme) is a local daemon that bridges inbound iMessages (via [Sendblue](https:\u002F\u002Fsendblue.com)) to a Claude Code session on the user's machine. Whitelisted phone numbers can text, send voice notes, send images, and drive Claude through filesystem operations, code execution, and `cd`-based directory navigation — turning the user's phone into a remote control for Claude on their laptop. This is the **inbound** counterpart to outbound notification patterns ([[sendblue-notify]]): textme is phone → Claude; sendblue-notify is Claude → phone.\n\n## When to Use This Skill\n\n- Use when the user says \"text Claude\", \"text my laptop\", \"drive Claude from my phone\", \"I want to send iMessages to Claude\", or \"let me code from my phone\".\n- Use when the user is heads-down away from their desk and wants to kick off, supervise, or interrupt a Claude session via SMS\u002FiMessage.\n- Use when setting up a long-running headless workstation that the user wants to remote-control while travelling or away from the keyboard.\n- Pair with [[sendblue-notify]] for bidirectional flow — outbound completion pings + inbound commands on the same Sendblue account.\n- Do **not** use for outbound-only \"text me when X finishes\" patterns. That is [[sendblue-notify]] and does not need a daemon.\n\n## Prerequisites\n\n- macOS or Linux host that stays online (the daemon polls Sendblue continuously).\n- Node.js 18+.\n- An active Sendblue account with API credentials and a provisioned iMessage number — set up via [[sendblue-cli]] (`sendblue setup`, then `sendblue show-keys` to surface API key\u002Fsecret).\n- Claude Code installed and authenticated on the host (`npm install -g @anthropic-ai\u002Fclaude-code`).\n- Optional: an OpenAI API key for Whisper voice-note transcription.\n\n## How It Works\n\n### Step 1: Install the daemon\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fnjerschow\u002Ftextme.git\ncd textme\u002Fdaemon\nnpm install\nnpm run build\nmkdir -p ~\u002F.config\u002Fclaude-imessage\n```\n\n### Step 2: Configure credentials and the whitelist\n\nCreate `~\u002F.config\u002Fclaude-imessage\u002Fconfig.json`:\n\n```json\n{\n  \"sendblue\": {\n    \"apiKey\": \"YOUR_SENDBLUE_API_KEY\",\n    \"apiSecret\": \"YOUR_SENDBLUE_API_SECRET\",\n    \"phoneNumber\": \"+1SENDBLUE_NUMBER\"\n  },\n  \"whitelist\": [\"+1YOUR_PHONE\"],\n  \"pollIntervalMs\": 5000,\n  \"conversationWindowSize\": 20\n}\n```\n\nThe `whitelist` is the **only** authorization gate between an inbound iMessage and code execution on the host. Treat it as a security boundary, not a UX preference. Add only phone numbers the user controls; never add a shared, work, or family number \"just in case\".\n\nFor voice transcription, optionally add to `.env` in the daemon directory:\n\n```bash\nOPENAI_API_KEY=sk-...\n```\n\n### Step 3: Run the daemon\n\nFor a quick test run:\n\n```bash\ncd textme\u002Fdaemon\nnpm start\n```\n\nFor persistent operation (recommended once the user has verified behavior):\n\n```bash\npm2 start dist\u002Findex.js --name textme\npm2 save\npm2 startup\n```\n\nOr, on macOS, install the launchd service:\n\n```bash\n.\u002Fscripts\u002Finstall-launchd.sh\n```\n\n### Step 4: Drive Claude from iMessage\n\nOnce the daemon is running, an iMessage from a whitelisted number to the Sendblue phone number reaches Claude. Built-in commands:\n\n| Command | Effect |\n|---|---|\n| `?` | List available commands |\n| `status` | Show current daemon status and working directory |\n| `queue` | Show messages queued for processing |\n| `history` | Recent message history |\n| `home` | `cd` back to home directory |\n| `reset` | Return home and clear conversation history |\n| `cd \u002Fpath` | Change working directory |\n| `stop` | Cancel the current Claude task |\n| `yes` \u002F `no` | Approve or reject the pending action |\n\nAnything else is treated as a Claude prompt and routed to the active session.\n\n### Step 5: Verify before relying on it\n\nBefore using textme in unattended workflows, the user must:\n\n1. Send `status` from the whitelisted phone — should get a directory + state reply.\n2. Send a benign command (`pwd`, `ls`) and confirm output arrives.\n3. Send something from a **non-whitelisted** number and confirm it is **ignored**, not echoed.\n4. Pull the plug: kill the daemon and confirm messages stop being processed (no zombie process).\n\nIf any of these fail, do not enable launchd \u002F pm2 auto-start.\n\n## Examples\n\n### Example 1: Initial setup walk-through\n\n```bash\n# 1. Make sure sendblue CLI is set up and creds work\nsendblue whoami\n\n# 2. Grab Sendblue API key & secret (these are NOT the CLI's bearer token)\nsendblue show-keys\n\n# 3. Clone + build the daemon\ngit clone https:\u002F\u002Fgithub.com\u002Fnjerschow\u002Ftextme.git\ncd textme\u002Fdaemon && npm install && npm run build\n\n# 4. Fill in ~\u002F.config\u002Fclaude-imessage\u002Fconfig.json with the values from step 2\n#    and YOUR personal phone number as the only whitelist entry\n\n# 5. Start, send \"?\" from your phone, confirm response\nnpm start\n```\n\n### Example 2: Composing with `sendblue-notify`\n\nWire outbound completion pings via [[sendblue-notify]] *and* inbound control via textme — they share the same Sendblue account but solve opposite problems:\n\n- Claude finishes a long task → texts user via [[sendblue-notify]] (`Stop` hook).\n- User replies \"look at the diff\" → textme routes that into Claude → Claude responds back via Sendblue.\n\n### Example 3: Tail the daemon log\n\n```bash\n# pm2\npm2 logs textme\n\n# Standalone\ntail -f ~\u002F.local\u002Flog\u002Fclaude-imessage.log\n```\n\n### Example 4: MCP-only alternative (no daemon)\n\nIf the user wants Sendblue messaging available to Claude Code as tools but does **not** want a polling daemon listening for inbound commands, they can register Sendblue as an MCP server instead:\n\n```bash\nclaude mcp add sendblue_api \\\n  --env SENDBLUE_API_API_KEY=your-api-key \\\n  --env SENDBLUE_API_API_SECRET=your-api-secret \\\n  -- npx -y sendblue-api-mcp --client=claude-code --tools=all\n```\n\nThis gives Claude outbound Sendblue tools inside a session but does **not** open the inbound phone-controls-Claude channel that textme provides. Pick textme when \"text Claude from anywhere\" is the goal; pick MCP when Claude only needs to send.\n\n## Best Practices\n\n- ✅ **Whitelist exactly one phone number to start.** The whitelist is the security boundary; expand it slowly and only to numbers the user controls.\n- ✅ **Run the daemon as a regular user**, never as root or via `sudo`.\n- ✅ **Start in a sandbox directory** for first tests (`cd ~\u002Ftextme-sandbox`), not in `~` or a real repo.\n- ✅ **Verify the non-whitelist ignore path** before enabling auto-start. A daemon that processes any sender is an open shell on the host.\n- ✅ **Keep `pollIntervalMs` ≥ 5000** unless the user understands the Sendblue rate limits and cost implications.\n- ❌ **Don't share the Sendblue number publicly.** Even with a whitelist, the host is doing per-message work; a flood from an unknown sender still costs polling cycles.\n- ❌ **Don't store `config.json` in a repo, dotfiles backup, or cloud sync** — it contains API credentials and the user's phone number.\n- ❌ **Don't run the daemon on a shared machine** without considering what every other user of that machine can now reach by sending an SMS.\n\n## Limitations\n\n- **Outbound-only flows do not need this skill.** For \"text me when X finishes\" use [[sendblue-notify]]; running a daemon is overkill.\n- **Voice transcription requires a separate OpenAI API key.** Without it, voice notes are dropped or surfaced as un-transcribed audio depending on daemon version.\n- **The daemon polls on an interval** — there is no push delivery. Expect single-digit-second latency between message receipt and Claude response.\n- **One conversation, one machine.** This is a per-host daemon, not a multi-tenant service. Two daemons sharing one Sendblue number will both try to handle every inbound message.\n- **Sendblue free-plan verification still applies.** The user's phone must have texted the Sendblue number once before outbound responses from Claude reach the user (see [[sendblue-cli]] limitations).\n\n## Security & Safety Notes\n\ntextme is a **remote code execution surface gated only by a phone-number whitelist**. Treat it accordingly.\n\n- **Whitelist is the security boundary.** Anyone who can spoof or hijack a whitelisted number can drive Claude on the host. Be deliberate about which numbers go on the list and remove them when they no longer need access. \u003C!-- security-allowlist: documented remote-control daemon; required disclosure per quality-bar.md -->\n- **Sendblue API credentials are sensitive.** `config.json` contains an API key, API secret, and the user's phone number. Mode it `600`, keep it out of dotfile repos, and never paste it into shared logs, gists, or screenshots.\n- **The daemon inherits the user's privileges.** It can read, write, and execute anything the running user can. Do not run as root, do not run from a directory with secrets the user does not want exposed to inbound SMS, and prefer a dedicated host or VM if available.\n- **Claude Code's permission model still applies inside the daemon-driven session** — destructive actions still surface confirmation prompts. textme exposes the `yes`\u002F`no` reply path for those prompts, which means the *phone number* is making the approval. Make sure the whitelist matches the trust level of approving destructive operations remotely.\n- **Inbound messages are untrusted input.** Treat textme prompts as user input from the open internet (with phone-number authentication). Do not pipe their contents into `eval`, shell substitution, or scripts that bypass Claude Code's review.\n- **Lock-screen previews of replies leak.** When Claude responds to a message, the reply lands on the user's lock screen unredacted. Don't ask Claude over textme to surface secrets, tokens, or customer data via SMS — link to a local log or PR instead.\n- **Daemon liveness is a footgun.** If pm2\u002Flaunchd is auto-restarting the daemon, the user must remember to stop it before changing whitelist entries, rotating credentials, or rebooting into an untrusted state.\n\n## Common Pitfalls\n\n- **Whitelist drift.** A number added \"for a demo\" never gets removed. Audit `whitelist` whenever the host changes hands or scope.\n- **`apiKey` \u002F `apiSecret` confusion.** Sendblue's API credentials (from `sendblue show-keys`) are distinct from the CLI's local bearer token in `~\u002F.sendblue\u002Fcredentials.json`. textme needs the *API* credentials, not the CLI auth file.\n- **Free-plan silent send failures.** If the user's phone never texted the Sendblue number first, outbound replies from Claude silently fail. Verify with `sendblue contacts` before relying on the loop.\n- **Auto-start before verification.** Installing the launchd plist or `pm2 save`-ing the daemon before testing the non-whitelist ignore path will baseline a potentially open daemon at boot. Verify first, persist second.\n- **Running the daemon in `~` or a repo with secrets.** The working directory at startup is exposed to anything textme is told to do (`ls`, `cat`, etc.). Start in a sandbox directory and `cd` deliberately.\n- **Confusing textme with the Sendblue MCP.** They look similar but the MCP variant only gives Claude *outbound* Sendblue tools — it does not open an inbound channel. If the user wants \"text Claude from my phone\", they need textme; if they want \"Claude can send a text mid-session\", the MCP is lighter.\n\n## Related Skills\n\n- `@sendblue-notify` — Outbound counterpart (Claude → phone). Composes with textme to make the loop bidirectional.\n- `@sendblue-cli` — Account setup, credential management, and the `show-keys` command that surfaces the API key\u002Fsecret textme needs.\n- `@sendblue-api` — HTTP API reference for users who want to build a custom inbound handler instead of using textme's daemon.\n- `@update-config` — If wiring textme alongside Claude Code hooks (e.g. a `Stop` hook that pings the user), use this for the settings.json edits.\n\n## Links\n\n- Repository: \u003Chttps:\u002F\u002Fgithub.com\u002Fnjerschow\u002Ftextme>\n- License: \u003Chttps:\u002F\u002Fgithub.com\u002Fnjerschow\u002Ftextme\u002Fblob\u002Fmain\u002FLICENSE> (MIT)\n- Sendblue: \u003Chttps:\u002F\u002Fsendblue.com>\n- Sendblue docs: \u003Chttps:\u002F\u002Fdocs.sendblue.com>\n",{"name":5,"risk":23,"tags":47,"tools":51,"author":54,"plugin":55,"source":34,"license":14,"category":50,"date_added":58,"description":7,"source_repo":59,"source_type":34,"license_source":60},[5,48,41,30,49,26,27,50],"sendblue","claude-code","automation",[52,53,40],"claude","cursor","AnthonyFirth",{"targets":56},{"codex":57,"claude":57},"blocked","2026-05-26","njerschow\u002Ftextme","https:\u002F\u002Fgithub.com\u002Fnjerschow\u002Ftextme\u002Fblob\u002Fmain\u002FLICENSE","f3312ba749561b6159f477dbfc9313c875d40a56",".agents\u002Fskills_archive\u002Fsendblue\u002Ftextme","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612","2026-10-25 23:50:58",{"source":8,"skillName":5,"commands":67,"prompt":77,"zipAvailable":78},[68,71,74],{"tool":69,"command":70},"npx","npx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill textme",{"tool":72,"command":73},"bunx","bunx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill textme",{"tool":75,"command":76},"pnpm","pnpm dlx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill textme","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fsendblue\u002Ftextme\u002FSKILL.md",true,[],[81,107,131,155,182,204],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":90,"publishedAt":42},"01M6Q0FA5FZ410Z33Z3TFQ4DBA","zero-trust","Implement zero-trust network architecture. Configure identity-based access, micro-segmentation, and continuous verification. Use when implementing modern security architectures.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzero-trust\u002FSKILL.md",[87],{"categoryNo":88,"categoryName":89,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[91,92,93,94,95,96,83,97,98,99,100,101,34,33,102,23,103,104,105,106],"ZeRO","trust","zero trust","architecture","assessment","verification","segmentation","devops-security","access","configure","only","active","scope","scripts","relevant","implementing",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":42},"01M6Q0F1YZJW3KX5FBKEVZ8CV4","zcode-delegate","Delegate coding tasks to the Z.AI ZCode CLI only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzcode-delegate\u002FSKILL.md",[],[114,115,116,117,118,119,120,121,122,123,124,125,126,101,127,34,128,129,23,130],"delegate","zcode","zcode delegate","review","cli","orchestration","tasks","run","Bash","model","node","read","orchestrator","files","desktop app","app","agent-orchestration",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":42},"01M6Q0ETK41VGNMYEXW0T00AJN","youtube-transcript","Fetch YouTube transcripts through DeepAPI or local fallback tooling and save clean text output.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript\u002FSKILL.md",[],[138,139,140,141,142,143,144,145,146,36,147,148,149,34,33,150,151,152,153,154],"transcript","youtube transcript","youtube","safe","github","codex","research","license","https","fetch","tooling","clean","local","output","deepapi","youtube transcripts","blob",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":172,"publishedAt":42},"01M6Q0EPPH2PVMDW40017F8WX0","youtube-transcript-skills","Fetch YouTube video transcripts, search videos\u002Fchannels, browse channels, and extract playlists via the getyoutubetranscript.com API - free tier, no card required.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript-skills\u002FSKILL.md",[161,164,167],{"categoryNo":162,"categoryName":163,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":165,"categoryName":166,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":168,"categoryName":169,"taxonomyType":170,"taxonomyTypeDesc":171},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[138,139,140,173,141,40,142,143,145,174,175,176,177,147,178,34,33,179,180,181],"youtube transcript skills","search","api","Video","browse","api-integration","free","card","channels",{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":192,"publishedAt":42},"01M6Q0EAB96PX83W5PTE8A0R8D","youtube-notetaker","Turn YouTube talks into local study notes with slides, transcripts, editable annotations, and a markdown-backed viewer.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002FSKILL.md",[188,191],{"categoryNo":189,"categoryName":190,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":165,"categoryName":166,"taxonomyType":20,"taxonomyTypeDesc":21},[140,193,194,118,141,195,196,39,38,145,176,197,198,199,200,33,201,150,202,203],"youtube notetaker","notetaker","workflow","official","markdown","slides","annotations","README","study","dair-academy","viewer",{"skillNo":205,"name":206,"nameZh":6,"description":207,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":208,"categories":209,"keywords":211,"publishedAt":42},"01M6Q0E55F0GW5MX48V8HXS8B5","youtube-full","Fetch YouTube transcripts, search videos, browse channels, and extract playlists via TranscriptAPI — no yt-dlp, no Google API key, works from any cloud server.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-full\u002FSKILL.md",[210],{"categoryNo":162,"categoryName":163,"taxonomyType":20,"taxonomyTypeDesc":21},[212,140,213,214,141,40,174,215,216,175,176,177,147,217,178,34,33,179,218,153],"youtube full","full","google","server","dlp","credits","automatic"]