How do I install the Metapelet Elder Checkin skill?

Run npx skillmds@latest add calle-ai/metapelet-elder-checkin in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Metapelet Elder Checkin safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Metapelet Elder Checkin?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Metapelet Elder Checkin free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Metapelet Elder Checkin?

CALLE-AI (@calle-ai) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Metapelet Elder Checkin by calle-ai

Name: Metapelet Elder Checkin
Author: CALLE-AI

Metapelet Elder Checkin

Place one consent-based outbound CALL-E phone check-in for an older adult using the MetaPelet warm-companion persona (non-medical emotional support), then return structured mood, topics, and repeat-call interest for a family member or coordinator.

CALLE-AI Updated Sep 17, 2026

File contents

MetaPelet Elder Check-in

Use this skill when a caregiver or family member (with recipient consent) wants one friendly phone call to reduce loneliness between human visits — not a medical reminder and not a replacement for human care.

MetaPelet is an existing voice companion product; this skill packages its conversation rules for CALL-E outbound calls and a structured post-call summary.

When to use

One outbound wellbeing check-in to a phone the elder already uses (landline or mobile).
Conversation in Russian, Hebrew, or English (set in the request).
Return structured results: mood, topics discussed, whether they want another call soon.

When not to use

Medical reminders, triage, emergency response, or mental-health treatment.
Unsolicited outreach or lead generation.
Recurring schedules without a separate scheduler wrapper and explicit consent.

Workflow

Read references/safety.md and confirm recipient consent.
Fill a request JSON with E.164 phone, explicit CALL-E region and locale (see apps/python/metapelet-checkin/example_request.json).
Preview (no call): run the Python app without --execute.
Live call: set CALLE_API_KEY, pass --execute --confirm-recipient-opt-in.
Share the redacted structured result with the authorized caregiver only.

Persona and profile

Core persona: references/persona.en.txt (MetaPelet companion snapshot, English repository text).
Optional demo profile shape: references/profile-demo.en.txt.
Structured output schema: references/result-schema.json.

Runnable app

The reference runner lives at apps/python/metapelet-checkin/ (relative to this submission repository root). It builds the CALL-E task text from the persona files and calls the CALL-E Python SDK when explicitly executed.

Output

After a completed call, expect JSON fields:

mood — short mood summary
topics — array of main topics
wants_repeat_call — yes | no | unknown

Mask phone numbers in any user-facing summary.

---name: metapelet-elder-checkindescription: Place one consent-based outbound CALL-E phone check-in for an older adult using the MetaPelet warm-companion persona (non-medical emotional support), then return structured mood, topics, and repeat-call interest for a family member or coordinator.license: MIT---# MetaPelet Elder Check-inUse this skill when a **caregiver or family member** (with recipient consent) wants **one friendly phone call** to reduce loneliness between human visits — not a medical reminder and not a replacement for human care.MetaPelet is an existing voice companion product; this skill packages its **conversation rules** for CALL-E outbound calls and a **structured post-call summary**.## When to use- One outbound **wellbeing check-in** to a phone the elder already uses (landline or mobile).- Conversation in **Russian, Hebrew, or English** (set in the request).- Return **structured results**: mood, topics discussed, whether they want another call soon.## When not to use- Medical reminders, triage, emergency response, or mental-health treatment.- Unsolicited outreach or lead generation.- Recurring schedules without a separate scheduler wrapper and explicit consent.## Workflow1. Read `references/safety.md` and confirm **recipient consent**.2. Fill a request JSON with **E.164** `phone`, explicit CALL-E `region` and `locale` (see `apps/python/metapelet-checkin/example_request.json`).3. **Preview** (no call): run the Python app without `--execute`.4. **Live call**: set `CALLE_API_KEY`, pass `--execute --confirm-recipient-opt-in`.5. Share the redacted structured result with the authorized caregiver only.## Persona and profile- Core persona: `references/persona.en.txt` (MetaPelet companion snapshot, English repository text).- Optional demo profile shape: `references/profile-demo.en.txt`.- Structured output schema: `references/result-schema.json`.## Runnable appThe reference runner lives at `apps/python/metapelet-checkin/` (relative to this submission repository root). It builds the CALL-E task text from the persona files and calls the CALL-E Python SDK when explicitly executed.## OutputAfter a completed call, expect JSON fields:- `mood` — short mood summary- `topics` — array of main topics- `wants_repeat_call` — `yes` | `no` | `unknown`Mask phone numbers in any user-facing summary.

Frequently asked questions