How to use it
- Hit Copy the whole skill.
- Claude: ⋯ → Download .md, then Customize → Skills → Add → Upload skill.
ChatGPT: make a Project and paste it into Instructions.
Neither? Paste it at the top of a new chat — it works for that chat. - Describe your job in plain words. The AI follows the skill from there.
Claude Code — installs the whole folder, not just SKILL.md
npx degit gooseworks-ai/goose-skills/skills/outreach/capabilities/send-sms-textbelt#main ~/.claude/skills/send-sms-textbeltFor one project only, change the path to .claude/skills/send-sms-textbelt.
Not working?
- Check which app you pasted it into — the steps above name the right one.
- Some skills need the paid tier of Claude or ChatGPT.
Paste into Claude, ChatGPT or Cursor.
Show the full text89 lines
Send Text Message
Setup
Read your credentials from ~/.gooseworks/credentials.json:
export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")
If ~/.gooseworks/credentials.json does not exist, tell the user to run: npx gooseworks login
All endpoints use Bearer auth: -H "Authorization: Bearer $GOOSEWORKS_API_KEY"
Send SMS messages via the Textbelt API on Orthogonal.
Workflow
Step 1: Gather Info
Ask the user for:
- Phone number (required) - US/Canada: 10-digit with area code. International: E.164 format (e.g., +44...)
- Message (required) - Max 800 characters. No URLs allowed.
Step 2: Send the Message
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
-H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"api":"textbelt","path":"/text"}'
"phone": "<phone_number>",
"message": "<message_text>"
}'
Step 3: Confirm Delivery
The response includes a textId. Use it to check delivery status:
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
-H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"api":"textbelt","path":"/status/{textId}"}'
This endpoint is free.
Response
Send Response (/text)
- success (boolean) -
trueif message was queued - textId (string) - Message ID for delivery tracking (only on success)
- quotaRemaining (integer) - Remaining SMS credits
- error (string) - Error message (only on failure)
Status Response (/status/{textId})
- status (string) -
DELIVERED,SENDING,FAILED, orUNKNOWN
Constraints
- Max 800 characters per message
- No URLs in message text
- Sender name is optional and not visible to the recipient in most countries
Optional Parameters
When sending, you can also include:
sender(string) - Business/org name for regulatory purposesreplyWebhookUrl(string) - US only: URL to receive reply webhookswebhookData(string) - Extra data passed to webhook (max 100 chars)
Error Handling
- success: false with
errorfield describes the issue (e.g., invalid phone number, insufficient credits) - US/Canada numbers only work from US/Canada IP region
- International numbers require E.164 format (e.g.,
+44...) - Messages containing URLs are rejected — use descriptions instead
- Max 800 characters — longer messages are rejected, not truncated
| 1 | |
| 2 | name send-sms-textbelt |
| 3 | description Send SMS text messages to phone numbers. Use when the user asks to send a text, send an SMS, text someone, message a phone number, or send a notification via text message. |
| 4 | source orthogonal |
| 5 | |
| 6 | |
| 7 | |
| 8 | # Send Text Message |
| 9 | |
| 10 | ## Setup |
| 11 | |
| 12 | Read your credentials from ~/.gooseworks/credentials.json: |
| 13 | |
| 14 | export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])") |
| 15 | export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))") |
| 16 | |
| 17 | |
| 18 | If ~/.gooseworks/credentials.json does not exist, tell the user to run: `npx gooseworks login` |
| 19 | |
| 20 | All endpoints use Bearer auth: `-H "Authorization: Bearer $GOOSEWORKS_API_KEY"` |
| 21 | |
| 22 | |
| 23 | Send SMS messages via the Textbelt API on Orthogonal. |
| 24 | |
| 25 | ## Workflow |
| 26 | |
| 27 | ### Step 1: Gather Info |
| 28 | |
| 29 | Ask the user for: |
| 30 | **Phone number** (required) - US/Canada: 10-digit with area code. International: E.164 format (e.g., +44...) |
| 31 | **Message** (required) - Max 800 characters. No URLs allowed. |
| 32 | |
| 33 | ### Step 2: Send the Message |
| 34 | |
| 35 | |
| 36 | curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \ |
| 37 | -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \ |
| 38 | -H "Content-Type: application/json" \ |
| 39 | -d '{"api":"textbelt","path":"/text"}' |
| 40 | "phone": "<phone_number>", |
| 41 | "message": "<message_text>" |
| 42 | }' |
| 43 | |
| 44 | |
| 45 | ### Step 3: Confirm Delivery |
| 46 | |
| 47 | The response includes a `textId`. Use it to check delivery status: |
| 48 | |
| 49 | |
| 50 | curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \ |
| 51 | -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \ |
| 52 | -H "Content-Type: application/json" \ |
| 53 | -d '{"api":"textbelt","path":"/status/{textId}"}' |
| 54 | |
| 55 | |
| 56 | This endpoint is free. |
| 57 | |
| 58 | ## Response |
| 59 | |
| 60 | ### Send Response (`/text`) |
| 61 | **success** (boolean) - `true` if message was queued |
| 62 | **textId** (string) - Message ID for delivery tracking (only on success) |
| 63 | **quotaRemaining** (integer) - Remaining SMS credits |
| 64 | **error** (string) - Error message (only on failure) |
| 65 | |
| 66 | ### Status Response (`/status/{textId}`) |
| 67 | **status** (string) - `DELIVERED`, `SENDING`, `FAILED`, or `UNKNOWN` |
| 68 | |
| 69 | ## Constraints |
| 70 | |
| 71 | Max 800 characters per message |
| 72 | No URLs in message text |
| 73 | Sender name is optional and not visible to the recipient in most countries |
| 74 | |
| 75 | ## Optional Parameters |
| 76 | |
| 77 | When sending, you can also include: |
| 78 | `sender` (string) - Business/org name for regulatory purposes |
| 79 | `replyWebhookUrl` (string) - US only: URL to receive reply webhooks |
| 80 | `webhookData` (string) - Extra data passed to webhook (max 100 chars) |
| 81 | |
| 82 | ## Error Handling |
| 83 | |
| 84 | **success: false** with `error` field describes the issue (e.g., invalid phone number, insufficient credits) |
| 85 | US/Canada numbers only work from US/Canada IP region |
| 86 | International numbers require E.164 format (e.g., `+44...`) |
| 87 | Messages containing URLs are rejected — use descriptions instead |
| 88 | Max 800 characters — longer messages are rejected, not truncated |
| 89 |
Discussion
Alternatives
Also in Services & APIsContext7Pulls up-to-date, version-specific library docs and code examples into the prompt so the AI stops inventing old APIs.Adaptyv Bio Foundry APIHow to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval. Use this skill whenever the user mentions Adaptyv, Foundry API, protein binding assays, protein screening experiments, BLI/SPR assays, thermostability assays, or wants to submit protein sequences for experimental characterization. Also trigger when code imports `adaptyv`, `adaptyv_sdk`, or `FoundryClient`, or references `foundry-api-public.adaptyvbio.com`..NET Backend Development PatternsMaster C#/.NET backend development patterns for building robust APIs, MCP servers, and enterprise applications. Covers async/await, dependency injection, Entity Framework Core, Dapper, configuration, caching, and testing with xUnit. Use when developing .NET backends, reviewing C# code, or designing API architectures.Add AI protectionProtect AI chat and completion endpoints from abuse — detect prompt injection and jailbreak attempts, block PII and sensitive info from leaking in responses, and enforce token budget rate limits to control costs. Use this skill when the user is building or securing any endpoint that processes user prompts with an LLM, even if they describe it as "preventing jailbreaks," "stopping prompt attacks," "blocking sensitive data," or "controlling AI API costs" rather than naming specific protections.