daycare

Create and update robust Daycare tasks (task_create/task_update + task_trigger_add) and permanent agents (create_permanent_agent) with minimal Python orchestration, explicit parameter schemas, reproducible exec/process usage, and performance-first skip() behavior. Use when users ask for cron/webhook automation, recurring checks, scheduled reports, permanent agents, or resilient background task workflows.

Create reusable Daycare voice agents with the hidden-by-default `voice_agent_create` tool. Use when users want a new voice persona, a realtime call prompt, client-side voice tools, or a saved voice agent that appears in the app Voice screen.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Daycare's capabilities with specialized knowledge, workflows, or tool integrations.

Understand what Daycare tasks are, how cron and webhook triggers work, and when to use each. Use when users ask about tasks, scheduling, triggers, or want to inspect existing tasks.

Friendship mechanics for daycare agents. Use when the user wants to add friends, manage friend requests, send messages to friends, share or unshare subusers with friends, or understand what nametags are.

Work with user-scoped PostgreSQL databases (PGlite). Use when the user asks to store structured data, create tables, query rows, track records, build a database, or manage any tabular/relational information. Covers database creation, additive schema design, CRUD operations, and SQL queries.

Create or update UI fragments using the json-render widget catalog. Use when users ask to build a widget, card, panel, modal, or any reusable UI component.

Understand what UI fragments are, browse existing fragments, and read their specs. Use when users ask what fragments are, want to list or inspect existing fragments, or need to understand the fragment system.

Write implementation plans in the Ralph loop format with exact files, validation commands, and bite-sized tasks. Use before multi-step changes or before delegating work to subagents.

Delegate coding work to the Claude Code CLI. Use for isolated implementation or review tasks when the CLI is installed and authenticated.

Delegate coding work to the Codex CLI. Use for isolated implementation, review, or refactor tasks when Codex is installed and the target directory is a git repo.

Generate text or image-based ASCII art with local CLI tools and simple fallback APIs.

Create hand-drawn diagrams in Excalidraw JSON format. Use for architecture diagrams, flows, concept maps, and quick visual explanations.

Search Tenor for reaction media and download the result you need. Prefer video formats like mp4 or webm unless the user explicitly needs a GIF.

Fetch YouTube transcripts and turn them into summaries, chapters, threads, quotes, or blog posts.

Search arXiv papers and retrieve abstracts or PDFs. Use for academic literature lookup, paper triage, and citation gathering.

Track RSS and Atom feeds with the blogwatcher CLI. Use for monitoring blogs, changelogs, and recurring research sources.

Passive domain reconnaissance with bundled Python helpers. Use for subdomains, SSL expiry, DNS records, WHOIS, and lightweight availability checks.

Write docs like code — Minto pyramid, MECE sections, BFO ontology, Mermaid diagrams, ground truth sources. Applies to any .md file.

Review code changes for correctness, regressions, security risks, and missing tests. Use whenever the user asks for a review or before merging non-trivial work.

Software development workflows for multi-agent parallel work. Use when asked to develop code, fix bugs, implement features, or work on any codebase task. Covers checkout, worktree isolation, syncing with remote, and PR creation.

Use after finishing meaningful code changes. Run a deliberate self-check, then ask a fresh reviewer agent to inspect the work before merge.

Execute a plan through focused background agents. Use for multi-step implementation work where tasks can be isolated and reviewed one by one.

Debug by reproducing, isolating, and proving root cause before changing code. Use for test failures, runtime bugs, flaky behavior, and broken integrations.