ops-whatsapp-biz
WhatsApp Business Cloud API — send approved template messages at scale, manage templates with approval tracking, and integrate product catalogs. Separate from wacli personal WhatsApp.
What this skill does
# OPS ► WHATSAPP BUSINESS
WhatsApp Business Cloud API — distinct from wacli personal WhatsApp.
**Key difference:** This skill uses the WhatsApp Business Cloud API (Meta Graph API) for business-to-customer messaging at scale. `wacli` is for personal WhatsApp messaging. Different credentials, different phone numbers, different use cases.
## Credential Resolution
```bash
PREFS_PATH="${CLAUDE_PLUGIN_DATA_DIR:-$HOME/.claude/plugins/data/ops-ops-marketplace}/preferences.json"
# WhatsApp Business credentials (separate from wacli personal)
WABA_TOKEN="${WHATSAPP_BUSINESS_TOKEN:-$(claude plugin config get whatsapp_business_token 2>/dev/null)}"
WABA_PHONE_ID="${WHATSAPP_PHONE_NUMBER_ID:-$(claude plugin config get whatsapp_phone_number_id 2>/dev/null)}"
WABA_ACCOUNT_ID="${WHATSAPP_BUSINESS_ACCOUNT_ID:-$(claude plugin config get whatsapp_business_account_id 2>/dev/null)}"
# Doppler fallback
if [ -z "$WABA_TOKEN" ]; then
WABA_TOKEN="$(doppler secrets get WHATSAPP_BUSINESS_TOKEN --plain 2>/dev/null)"
fi
if [ -z "$WABA_PHONE_ID" ]; then
WABA_PHONE_ID="$(doppler secrets get WHATSAPP_PHONE_NUMBER_ID --plain 2>/dev/null)"
fi
if [ -z "$WABA_ACCOUNT_ID" ]; then
WABA_ACCOUNT_ID="$(doppler secrets get WHATSAPP_BUSINESS_ACCOUNT_ID --plain 2>/dev/null)"
fi
```
**Credential check**: If `WABA_TOKEN` or `WABA_PHONE_ID` is empty, print:
`WhatsApp Business not configured. Run /ops:whatsapp-biz setup to configure credentials.`
and stop.
---
## Sub-command Routing
Route `$ARGUMENTS`:
| Input | Action |
|---|---|
| (empty), list-templates | List all templates with approval status |
| send-template | Send an approved template message to one or more recipients |
| create-template | Guided template creation wizard |
| check-template \<NAME\> | Poll approval status for a specific template |
| catalog | View and manage linked product catalog |
| setup | Configure WhatsApp Business API credentials |
---
## list-templates
List all message templates for the WhatsApp Business Account.
```bash
RESULT=$(curl -s "https://graph.facebook.com/v20.0/${WABA_ACCOUNT_ID}/message_templates?fields=name,status,category,language,components&limit=50" \
-H "Authorization: Bearer ${WABA_TOKEN}")
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
echo " WHATSAPP BUSINESS TEMPLATES"
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
echo ""
printf "| %-30s | %-10s | %-12s | %-8s |\n" "Template Name" "Status" "Category" "Language"
printf "|%s|%s|%s|%s|\n" "--------------------------------" "------------" "--------------" "----------"
echo "$RESULT" | jq -r '.data[]? | [.name, .status, .category, .language] | @tsv' 2>/dev/null | \
while IFS=$'\t' read -r name status category language; do
STATUS_ICON="○"
[ "$status" = "APPROVED" ] && STATUS_ICON="✓"
[ "$status" = "REJECTED" ] && STATUS_ICON="✗"
[ "$status" = "PENDING" ] && STATUS_ICON="…"
printf "| %-30s | %s %-9s | %-12s | %-8s |\n" "${name:0:30}" "$STATUS_ICON" "$status" "${category:0:12}" "$language"
done
TOTAL=$(echo "$RESULT" | jq '.data | length // 0')
APPROVED=$(echo "$RESULT" | jq '[.data[]? | select(.status == "APPROVED")] | length')
echo ""
echo "Total: ${TOTAL} templates | Approved: ${APPROVED}"
echo ""
echo "Note: Per-template pricing applies since July 2025. Check Meta pricing page for current rates."
```
---
## send-template
Send an approved template message to one or more recipients.
**Before sending**, collect via AskUserQuestion:
1. Template name (free text — use `list-templates` first to see available)
2. Recipient phone number(s) — free text (single number or comma-separated list, include country code, e.g. +14155552671)
If template has variables, ask for each parameter value via AskUserQuestion (free text).
**Cost note**: Always display approximate cost before sending. Utility templates: ~$0.005/msg; Marketing: ~$0.025/msg (US rates — varies by country). Show AskUserQuestion to confirm before bulk sends > 10 recipients.
```bash
# Parse recipients
IFS=',' read -ra RECIPIENTS <<< "$PHONE_NUMBERS"
RECIPIENT_COUNT=${#RECIPIENTS[@]}
# For bulk sends > 10, confirm
if [ $RECIPIENT_COUNT -gt 10 ]; then
# AskUserQuestion: "Send to ${RECIPIENT_COUNT} recipients? Estimated cost: ~$$(awk "BEGIN {printf \"%.2f\", $RECIPIENT_COUNT * 0.025}") for marketing templates." options [Send, Cancel]
[ "$CONFIRM" = "Cancel" ] && echo "Cancelled." && exit 0
fi
# Send to each recipient
SUCCESS=0; FAILED=0
for PHONE in "${RECIPIENTS[@]}"; do
PHONE=$(echo "$PHONE" | tr -d ' ')
RESP=$(curl -s -X POST "https://graph.facebook.com/v20.0/${WABA_PHONE_ID}/messages" \
-H "Authorization: Bearer ${WABA_TOKEN}" \
-H "Content-Type: application/json" \
-d "{
\"messaging_product\": \"whatsapp\",
\"to\": \"${PHONE}\",
\"type\": \"template\",
\"template\": {
\"name\": \"${TEMPLATE_NAME}\",
\"language\": {\"code\": \"en_US\"},
\"components\": ${TEMPLATE_COMPONENTS_JSON:-[]}
}
}")
MSG_ID=$(echo "$RESP" | jq -r '.messages[0].id // empty')
if [ -n "$MSG_ID" ]; then
SUCCESS=$((SUCCESS + 1))
else
FAILED=$((FAILED + 1))
ERR=$(echo "$RESP" | jq -r '.error.message // "unknown error"')
echo " Failed for ${PHONE}: ${ERR}"
fi
done
echo ""
echo "Sent: ${SUCCESS}/${RECIPIENT_COUNT} messages delivered"
[ $FAILED -gt 0 ] && echo "Failed: ${FAILED} — check phone number format (+country_code + number)"
```
**Template components format** (build `TEMPLATE_COMPONENTS_JSON` from user input):
For templates with header + body variables:
```json
[
{
"type": "header",
"parameters": [{"type": "text", "text": "{{header_value}}"}]
},
{
"type": "body",
"parameters": [
{"type": "text", "text": "{{var1}}"},
{"type": "text", "text": "{{var2}}"}
]
}
]
```
For templates with no variables: `TEMPLATE_COMPONENTS_JSON=[]`
---
## create-template
Guided template creation wizard.
Step 1 — Collect basic info:
AskUserQuestion: "Template category?" options `[MARKETING, UTILITY, AUTHENTICATION, More...]`
If More: AskUserQuestion: `[AUTHENTICATION, UTILITY, Skip]`
Step 2 — AskUserQuestion: "Template name (lowercase, underscores only, e.g. order_confirmation):" (free text)
Step 3 — AskUserQuestion: "Language?" options `[en_US, en_GB, es, fr]`
Step 4 — Collect body text (free text). Instruct user: "Use {{1}}, {{2}} etc for variables."
Step 5 — AskUserQuestion: "Add a header?" options `[Text header, Image header, No header, Video header]`
Step 6 — AskUserQuestion: "Add call-to-action button?" options `[URL button, Phone button, No button, Quick reply]`
```bash
# Build components array
COMPONENTS='[{"type":"BODY","text":"'"${BODY_TEXT}"'"}]'
# Add header if selected
if [ "$HEADER_TYPE" = "Text header" ]; then
HEADER_TEXT_INPUT="..." # collected via AskUserQuestion
COMPONENTS=$(echo "$COMPONENTS" | jq '. + [{"type":"HEADER","format":"TEXT","text":"'"${HEADER_TEXT_INPUT}"'"}]')
elif [ "$HEADER_TYPE" = "Image header" ]; then
COMPONENTS=$(echo "$COMPONENTS" | jq '. + [{"type":"HEADER","format":"IMAGE","example":{"header_handle":["<upload_handle>"]}}]')
fi
# Add button if selected
if [ "$BUTTON_TYPE" = "URL button" ]; then
BUTTON_URL="..." # collected via AskUserQuestion: "Button URL:"
BUTTON_TEXT="..." # collected via AskUserQuestion: "Button text:"
COMPONENTS=$(echo "$COMPONENTS" | jq '. + [{"type":"BUTTONS","buttons":[{"type":"URL","text":"'"${BUTTON_TEXT}"'","url":"'"${BUTTON_URL}"'"}]}]')
elif [ "$BUTTON_TYPE" = "Phone button" ]; then
BUTTON_PHONE="..." # collected via AskUserQuestion: "Phone number for button:"
BUTTON_TEXT="..."
COMPONENTS=$(echo "$COMPONENTS" | jq '. + [{"type":"BUTTONS","buttons":[{"type":"PHONE_NUMBER","text":"'"${BUTTON_TEXT}"'","phone_number":"'"${BUTTON_PHONE}"'"}]}]')
fi
RESP=$(curl -s -X POST "https://graph.facebook.com/v20.0/${WABA_ACCOUNT_ID}/message_templates" \
-H "Authorization: Bearer ${WABA_TOKEN}" \
-H "Content-Type: application/json" \
-d "{
\"name\": \"Related in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.