tdiminotdimino/claude-code-minoan/skills/integration-automation/sms/SKILL.md

sms

Skill41 starsChanged 7 months agoMITView on GitHub

Send, read, listen, respond, and manage SMS conversations via Telnyx and Twilio. Supports 8 phone numbers across both providers with auto-detection, conversation threading, MMS, real-time inbound listening, background watcher, batch reply processor, and soul-aware auto-reply. 10 Python scripts for SMS operations.

Reads credentials
Installs packages

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

0
Common
Most of the 22 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Read messages collected by sms_listen.py.
line 337
Very specific:
When you use --from, the skill detects the provider by matching against known numbers:
line 370
Very specific:
All sent messages are automatically logged to ~/.claude/skills/sms/data/messages.jsonl (JSONL format).
line 386
Distinctive:
Offline message browsing: Read/conversation scripts automatically fall back to the local log when Telnyx API returns 404.
line 388

“Common” is measured: kept by at least 6 in 10 of the 22 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

SMS Skill

Send SMS/MMS, read inboxes, auto-reply as Claudius, and view conversation threads via Telnyx (2 numbers) and Twilio (6 numbers).

When to Use This Skill

Sending a text message to any phone number
Reading recent SMS messages (inbox)
Listening for real-time inbound messages (two-way SMS)
Auto-replying to inbound SMS as Claudius (soul-aware responses)
Viewing a conversation thread with a specific number
Listing available phone numbers across providers
Sending MMS with image attachments

Prerequisites

Requires requests (uv pip install --system requests).

Credentials are loaded automatically:

Telnyx: TELNYX_API_KEY env var, or falls back to ~/.claude.json (already configured)
Twilio: TWILIO_ACCOUNT_SID + TWILIO_AUTH_TOKEN env vars, or falls back to hardcoded defaults

Quick Start

# Send a text
python3 ~/.claude/skills/sms/scripts/sms_send.py "+19175551234" "Hello from Claude"

# Read recent messages
python3 ~/.claude/skills/sms/scripts/sms_read.py -n 10

# View conversation with someone
python3 ~/.claude/skills/sms/scripts/sms_conversation.py "+19175551234"

# List all available numbers
python3 ~/.claude/skills/sms/scripts/sms_numbers.py

# Start real-time listener (background)
python3 ~/.claude/skills/sms/scripts/sms_listen.py --bg

# Check inbound messages
python3 ~/.claude/skills/sms/scripts/sms_inbox.py

Available Scripts

1. sms_send.py — Send SMS/MMS

python3 ~/.claude/skills/sms/scripts/sms_send.py TO "MESSAGE" [OPTIONS]

Flag	Description
`--from NUMBER`	Send from a specific number (auto-detects provider)
`--provider telnyx\|twilio`	Force a specific provider
`--media URL`	Attach media for MMS

Examples:

# Send via Telnyx (default)
python3 ~/.claude/skills/sms/scripts/sms_send.py "+19175551234" "Meeting at 3pm"

# Send from a Twilio number
python3 ~/.claude/skills/sms/scripts/sms_send.py "+19175551234" "Hello" --from "+18508058037"

# Send MMS with image
python3 ~/.claude/skills/sms/scripts/sms_send.py "+19175551234" "Check this" --media "https://example.com/photo.jpg"

2. sms_read.py — Read Inbox

python3 ~/.claude/skills/sms/scripts/sms_read.py [OPTIONS]

Flag	Description
`--to NUMBER`	Messages to a specific number
`--from-number NUMBER`	Messages from a specific sender
`--direction inbound\|outbound`	Filter by direction
`-n/--limit NUM`	Number of messages (default: 10)
`--provider telnyx\|twilio`	Query specific provider
`--all-providers`	Query both providers

Examples:

# Read last 10 messages (Twilio recommended for reads)
python3 ~/.claude/skills/sms/scripts/sms_read.py -n 10 --provider twilio

# Messages to a specific number
python3 ~/.claude/skills/sms/scripts/sms_read.py --to "+18508058037" --provider twilio

# Only inbound messages
python3 ~/.claude/skills/sms/scripts/sms_read.py --direction inbound --provider twilio

# Query both providers
python3 ~/.claude/skills/sms/scripts/sms_read.py --all-providers -n 20

3. sms_conversation.py — View Conversation Thread

python3 ~/.claude/skills/sms/scripts/sms_conversation.py NUMBER [OPTIONS]

Flag	Description
`-n/--limit NUM`	Max messages per direction (default: 20)
`--our-number NUMBER`	Filter to a specific one of our numbers
`--provider telnyx\|twilio`	Query specific provider
`--all-providers`	Query both providers

Examples:

# View conversation with a number
python3 ~/.claude/skills/sms/scripts/sms_conversation.py "+19175551234" --provider twilio

# Limit to last 10 messages per direction
python3 ~/.claude/skills/sms/scripts/sms_conversation.py "+19175551234" -n 10 --provider twilio

# Filter to a specific one of our numbers
python3 ~/.claude/skills/sms/scripts/sms_conversation.py "+19175551234" --our-number "+18508058037"

4. sms_numbers.py — List Available Numbers

python3 ~/.claude/skills/sms/scripts/sms_numbers.py [OPTIONS]

Flag	Description
`--provider telnyx\|twilio`	Filter by provider
`--live`	Query APIs for live status (slower)

Examples:

# List all 8 numbers
python3 ~/.claude/skills/sms/scripts/sms_numbers.py

# Twilio numbers only
python3 ~/.claude/skills/sms/scripts/sms_numbers.py --provider twilio

# Live API status check
python3 ~/.claude/skills/sms/scripts/sms_numbers.py --live

5. sms_listen.py — Real-Time Inbound Listener

Background daemon that polls Twilio for new inbound messages and runs a webhook server for Telnyx inbound. Messages are written to data/inbox.jsonl.

python3 ~/.claude/skills/sms/scripts/sms_listen.py [OPTIONS]

Flag	Description
`--bg`	Run in background (daemonize)
`--stop`	Stop running listener
`--status`	Check if listener is running
`--interval N`	Twilio poll interval in seconds (default: 10)
`--numbers +1... +1...`	Twilio numbers to monitor (default: all 6)
`--webhook-port N`	Telnyx webhook port (default: 9147)
`--no-telnyx`	Disable Telnyx webhook server
`--no-twilio`	Disable Twilio polling

Examples:

# Start listener in background
python3 ~/.claude/skills/sms/scripts/sms_listen.py --bg

# Check status
python3 ~/.claude/skills/sms/scripts/sms_listen.py --status

# Stop listener
python3 ~/.claude/skills/sms/scripts/sms_listen.py --stop

# Monitor only the Aldea production number, poll every 5s
python3 ~/.claude/skills/sms/scripts/sms_listen.py --bg --numbers +18557066006 --interval 5

# Telnyx webhook only (no Twilio polling)
python3 ~/.claude/skills/sms/scripts/sms_listen.py --bg --no-twilio

Telnyx webhook setup: Point your Telnyx Messaging Profile webhook URL to http://localhost:9147/telnyx. For remote access, use ngrok or similar tunnel.

6. Auto-Reply — Two Modes

Mode A: `/sms-respond` Slash Command (Interactive)

Process unhandled SMS using the current Claude Code session as the LLM. No subprocess needed—follows the same pattern as /slack-respond.

/sms-respond        # Process all unhandled messages
/sms-respond 2      # Process only message #2 from inbox

The slash command loads inbox, soul.md, and memory context dynamically, then walks through a 6-step cognitive pipeline (internal monologue → external dialogue → user model check → user model update → soul state check → soul state update). Replies are sent via sms_send.py and all memory layers are updated.

The command also starts a background watcher (sms_watch.py) after processing, which polls for new inbound messages every 5 seconds and notifies the session when one arrives—creating a continuous two-way SMS loop.

Use this when: You're in an active Claude Code session and want to reply to SMS.

Mode B: `sms_respond.py` Daemon (Standalone)

Standalone daemon for an always-on or headless machine. Uses claude -p subprocess to generate responses. Does not work from within a running Claude Code session (subprocess nesting conflict).

python3 ~/.claude/skills/sms/scripts/sms_respond.py [OPTIONS]

Flag	Description
`--daemon`	Loop continuously, polling inbox
`--bg`	Run daemon in background (requires `--daemon`)
`--status`	Check if responder daemon is running
`--stop`	Stop running responder daemon
`--interval N`	Poll interval in seconds (default: 5)
`--model MODEL`	Override LLM model (default: claude-sonnet-4-5-20250514)
`--no-soul`	Disable soul context (plain responses)
`--dry-run`	Process messages without sending replies

Examples:

# Start auto-reply daemon in background (always-on machine)
python3 ~/.claude/skills/sms/scripts/sms_respond.py --daemon --bg

# Check daemon status
python3 ~/.claude/skills/sms/scripts/sms_respond.py --status

# Stop daemon
python3 ~/.claude/skills/sms/scripts/sms_respond.py --stop

Use this when: Running headless on an always-on machine or outside Claude Code.

Shared Infrastructure

Both modes require sms_listen.py running to feed inbox.jsonl.

Memory: 3-tier SQLite at data/sms_memory.db:

Working memory — per-conversation message history + cognitive outputs
User models — per-phone-number personality profiles
Soul memory — cross-conversation soul state

7. sms_watch.py — Background Watcher for Claude Code

Polls inbox.jsonl for new unhandled messages. Designed as a run_in_background bash task—exits when a new message is detected, printing a structured line for Claude Code to parse.

python3 ~/.claude/skills/sms/scripts/sms_watch.py [OPTIONS]

Flag	Description
`--interval N`	Poll interval in seconds (default: 5)
`--enrich`	On detect, also print sender's memory context (user model, soul state, recent conversation)

Output on detect: {"event": "NEW_SMS", "id": "...", "from": "...", "to": "...", "body": "..."} Output on detect with --enrich: Same JSON line, followed by ---MEMORY_CONTEXT--- and the sender's user model, soul state, and recent conversation history. Output on timeout/kill: NO_NEW_SMS

Examples:

# Start watcher (run as background task in Claude Code)
python3 ~/.claude/skills/sms/scripts/sms_watch.py

# Enriched mode — pre-loads memory context for faster processing
python3 ~/.claude/skills/sms/scripts/sms_watch.py --enrich

# Faster polling
python3 ~/.claude/skills/sms/scripts/sms_watch.py --interval 3

8. sms_process_reply.py — Batch Reply Processor

Sends SMS reply and performs all 9 memory operations in a single call. Replaces the 9 separate python3 -c invocations from the /sms-respond pipeline.

python3 ~/.claude/skills/sms/scripts/sms_process_reply.py [OPTIONS]

Flag	Description
`--phone NUMBER`	Sender's E.164 number (required)
`--our-number NUMBER`	Our number they texted (required)
`--message-id ID`	Inbox message ID (required)
`--message-text TEXT`	Original inbound message text (required)
`--reply-text TEXT`	External dialogue text to send (required)
`--monologue-text TEXT`	Internal monologue text (required)
`--monologue-verb VERB`	Monologue verb (default: thought)
`--dialogue-verb VERB`	Dialogue verb (default: said)
`--user-model-check BOOL`	Whether user model was updated (default: false)
`--user-model-md MD`	Updated user model markdown (if check was true)
`--soul-updates JSON`	JSON dict of soul state updates
`--stdin-json`	Read all args from stdin as JSON (avoids shell quoting)
`--dry-run`	Skip sending SMS, do memory operations only

Examples:

# Basic reply with memory update
python3 ~/.claude/skills/sms/scripts/sms_process_reply.py \
    --phone "+17327595647" \
    --our-number "+18557066006" \
    --message-id "SM0334c637c6017dbf84eae2a7fd824abd" \
    --message-text "Hello there" \
    --reply-text "Hello! Good to hear from you." \
    --monologue-text "A friendly greeting." \
    --monologue-verb "noticed" \
    --dialogue-verb "replied" \
    --user-model-check false

# With soul state update
python3 ~/.claude/skills/sms/scripts/sms_process_reply.py \
    --phone "+17327595647" \
    --our-number "+18557066006" \
    --message-id "SM..." \
    --message-text "text" \
    --reply-text "reply" \
    --monologue-text "monologue" \
    --dialogue-verb "said" \
    --user-model-check true \
    --user-model-md "# Updated model" \
    --soul-updates '{"currentTopic": "testing", "emotionalState": "engaged"}'

9. sms_inbox.py — Read Inbound Inbox

Read messages collected by sms_listen.py.

python3 ~/.claude/skills/sms/scripts/sms_inbox.py [OPTIONS]

Flag	Description
`--all`	Show all messages (including handled)
`-n/--limit NUM`	Number of messages to show
`--from NUMBER`	Filter by sender number
`--provider telnyx\|twilio`	Filter by provider
`--mark-read ID`	Mark a specific message as handled
`--mark-all-read`	Mark all messages as handled

Examples:

# Show unhandled messages
python3 ~/.claude/skills/sms/scripts/sms_inbox.py

# Show last 5 messages from a specific sender
python3 ~/.claude/skills/sms/scripts/sms_inbox.py --from "+17327595647" -n 5

# Mark all as read
python3 ~/.claude/skills/sms/scripts/sms_inbox.py --mark-all-read

Configuration

Provider Auto-Detection

When you use --from, the skill detects the provider by matching against known numbers:

Telnyx numbers: +18628026208, +18334843851
Twilio numbers: +13205950420, +18557066006, +18559149834, +18776882519, +18665517616, +18778377603, +18665650327, +18667056747, +18445491928

Defaults

Setting	Value
Default provider	Telnyx
Default Telnyx from	`+18628026208`
Default Twilio from	`+18557066006` (Claudius 855)

Edit _sms_utils.py to change defaults.

Local Message Log

All sent messages are automatically logged to ~/.claude/skills/sms/data/messages.jsonl (JSONL format). This enables:

Telnyx conversation history: Since Telnyx is send-only (no REST API for reading messages), the local log provides the only record of Telnyx messages.
Offline message browsing: Read/conversation scripts automatically fall back to the local log when Telnyx API returns 404.
Per-number history: Filter by any phone number to see all correspondences.

The log grows with each sent message. To reset, delete data/messages.jsonl.

Known Limitations

Telnyx is send-only: Telnyx has no GET /v2/messages endpoint — message receiving is webhook-based only. Sent messages are tracked via the local log. For full read/conversation capability, use --provider twilio or --all-providers.

Phone Number Reference

Telnyx

Number	Type	Label	Reserved
`+18628026208`	Longcode	Primary (default)	Aldea / Dr. Shefali
`+18334843851`	Toll-free	Secondary	Aldea (dev/backup)

Twilio (9 numbers — verified live 2026-03-03)

Number	Type	Label	Reserved
`+13205950420`	Local	Claudius 320	Claudius (broken—needs 10DLC registration)
`+18557066006`	Toll-free	Claudius 855	Claudius (2-way)
`+18559149834`	Toll-free	855 number	Available
`+18776882519`	Local	877 number	Available
`+18665517616`	Local	866 number	Available
`+18778377603`	Local	877-837 number	Available
`+18665650327`	Local	866-565 number	Available
`+18667056747`	Local	866-705 number	Available
`+18445491928`	Local	844 number	Available

Download now (ZIP)

Other versions25 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 25
coreyhaines31/marketingskills★ 58ksame name
Cesarjoquin/Marketing-Skills★ 190same name
open-fox/agents★ 55same name
SZcalligrapher/slash-skills-subscription★ 32same name
TommyBez/skillsboard★ 10same name
scayver/marketing-skills★ 8same name
anis-dr/skills★ 3same name
Shri-Phnx/claude-skills★ 2same name
agrivisionai/claude-skills★ 1same name
david-corroy/skills-marketing-fr★ 1same name
15 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use popups, paywalls and 10 more.
Other files people use alongside this one.
- CesarjoquinSkill
  popups
  When the user wants to create or optimize popups, modals, overlays, slide-ins, or banners for conversion purposes. Also use when the user mentions "exit intent," "popup conversions," "modal optimization," "lead capture popup," "email popup," "announcement banner," "overlay," "collect emails with a popup," "exit popup," "scroll trigger," "sticky bar," or "notification bar." Use this for any overlay or interrupt-style conversion element. For forms outside of popups, see cro. For general page conversion optimization, see cro.
  Also in 8 projects that use this
- CesarjoquinSkill
  paywalls
  When the user wants to create or optimize in-app paywalls, upgrade screens, upsell modals, or feature gates. Also use when the user mentions "paywall," "upgrade screen," "upgrade modal," "upsell," "feature gate," "convert free to paid," "freemium conversion," "trial expiration screen," "limit reached screen," "plan upgrade prompt," "in-app pricing," "free users won't upgrade," "trial to paid conversion," or "how do I get users to pay." Use this for any in-product moment where you're asking users to upgrade. Distinct from public pricing pages (see cro) — this focuses on in-product upgrade moments where the user has already experienced value. For pricing decisions, see pricing.
  Also in 8 projects that use this
- pixelswithblissSkill
  co-marketing
  When the user wants to find co-marketing partners, plan joint campaigns, or brainstorm partnership opportunities. Use when the user says 'co-marketing,' 'partner marketing,' 'joint campaign,' 'who should we partner with,' 'integration marketing,' 'cross-promotion,' 'collaborate with another company,' 'partnership ideas,' or 'co-brand.' For customer referral programs, see referral-program. For launch-specific partnerships, see launch-strategy.
  Also in 8 projects that use this
- timruebenachSkill
  directory-submissions
  When the user wants to submit their product to startup, SaaS, AI, agent, MCP, no-code, or review directories for backlinks, domain rating, and discovery. Also use when the user mentions "directory submissions," "submit to directories," "backlinks from directories," "list my product," "submit to Product Hunt," "BetaList," "TAAFT," "Futurepedia," "G2 listing," "Capterra listing," "AlternativeTo," "SaaSHub," "AI directories," "MCP registry," "agent directory," "dofollow backlinks," "launch directories," or "directory tracker." Use this whenever someone is planning the directory layer of a product launch or an ongoing backlink campaign. For the broader launch moment, see launch-strategy. For programmatic SEO pages that should live behind these backlinks, see programmatic-seo. For AI citation optimization, see ai-seo.
  Also in 8 projects that use this
- roerohanSkill
  prospecting
  When the user wants to find, qualify, and build a list of prospects to reach out to — across B2B SaaS, general B2B, or local small businesses. Also use when the user mentions "prospecting," "build a prospect list," "find prospects," "find leads," "lead gen list," "find SaaS companies that," "find B2B companies," "find local businesses," "ICP-fit accounts," "who should we go after," "outbound list," "target account list," "find clients near me," "businesses without websites," "prospect research," "qualified leads," "find my first customers," "early adopters," "design partners," "beta users," or "who has this problem." Use this for the list-building and qualification phase. For writing the outbound copy after the list is built, see cold-email. For deep competitive research on specific accounts, see competitor-profiling.
  Also in 8 projects that use this
- coreyhaines31Skill
  marketing-council
  When the user wants multiple expert perspectives on a marketing question — a simulated board of advisors staffed by legendary marketers (Seth Godin, David Ogilvy, Eugene Schwartz, April Dunford, Rory Sutherland, Alex Hormozi, Byron Sharp, and more). Also use when the user mentions 'marketing council,' 'board of advisors,' 'advisory board,' 'what would Seth Godin say,' 'what would Ogilvy think,' 'channel Hormozi,' 'get multiple perspectives,' 'debate this,' 'have the council review,' 'marketing mentors,' or asks how a famous marketer would approach their problem. The council gives each advisor's take through their documented frameworks, surfaces where they disagree, and synthesizes a recommendation. For executing the winning direction, hand off to positioning, offers, copywriting, ads, or the relevant skill.
  Also in 5 projects that use this
- +6 more from Cesarjoquin
In this repository99 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agents-md-managerSkill
- architecture-md-builderSkill
- autoresearchSkill
- claude-agent-sdkSkill
- claude-md-managerSkill
- claude-usageSkill
- dag-typesafeSkill
- fableSkill
- glossarySkill
- openrouter-usageSkill
- react-best-practicesSkill
- skill-optimizerSkill
- stop-slopSkill
- tamarruSkill
- test-harness-auditorSkill
- user-model-builderSkill
- atmosphere-shaderSkill
- component-gallerySkill
- conductor-motionSkill
- design-auditSkill
- design-critiqueSkill
- design-mdSkill
- design-polishSkill
- gemini-claude-resonanceSkill
- gemini-forgeSkill
- gpt-atelierSkill
- grainientSkill
- image-forgeSkill
- image-wellSkill
- meshySkill
- mindnode-uiSkill
- minoan-frontend-designSkill
- nano-banana-proSkill
- overwatch-slidedeckSkill
- paper-designSkill
- particle-swarm-simSkill
- pellicolaSkill
- photo-to-slack-emojiSkill
- pretextSkill
- recordlySkill
- rocaille-shaderSkill
- scroll-cinemaSkill
- shadcnSkill
- shapeSkill
- smolvlmSkill
- speak-responseSkill
- sprite-forgeSkill
- threejs-particle-canvasSkill
- vellum-editorialSkill
- webgpu-threejs-tslSkill
- agent-browserSkill
- beautiful-mermaidSkill
- classical-887Skill
- claude-peersSkill
- cloudflareSkill
- codex-ctoSkill
- codex-orchestratorSkill
- disc-forgeSkill
- figma-mcpSkill
- The first 60 shown.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

SMS Skill

When to Use This Skill

Prerequisites

Quick Start

Available Scripts

1. sms_send.py — Send SMS/MMS

2. sms_read.py — Read Inbox

3. sms_conversation.py — View Conversation Thread

4. sms_numbers.py — List Available Numbers

5. sms_listen.py — Real-Time Inbound Listener

6. Auto-Reply — Two Modes

Mode A: /sms-respond Slash Command (Interactive)

Mode B: sms_respond.py Daemon (Standalone)

Shared Infrastructure

7. sms_watch.py — Background Watcher for Claude Code

8. sms_process_reply.py — Batch Reply Processor

9. sms_inbox.py — Read Inbound Inbox

Configuration

Provider Auto-Detection

Defaults

Local Message Log

Known Limitations

Phone Number Reference

Telnyx

Twilio (9 numbers — verified live 2026-03-03)

Word for word · 0

Edited · 0

Wrote their own version · 25

popups

paywalls

co-marketing

directory-submissions

prospecting

marketing-council

Does it work?

No reviews yet

Your trail

Now do this for your own.

Mode A: `/sms-respond` Slash Command (Interactive)

Mode B: `sms_respond.py` Daemon (Standalone)