Infra Plan Review
Read a Terraform plan and report what it would create, replace and destroy — counts first, reasoning second.
Health Journal
Capture a short daily health entry — sleep, movement, symptoms — without turning it into advice.
Cfo Budget Review
Turn a normalised statement table into a category-level budget review with the three largest deltas called out.
Loop Worker
Per-cycle protocol for an autonomous goal loop worker — the unified autonomous goal engine that runs one self-directed cycle per turn until its goal is met, then self-retires. Drives one cycle against a loop's file interface (status.json gate, brief.md goal, guidance.txt nudges, findings/cycle_NNN.json, FINDINGS.md, the type-appropriate deliverable, STOP sentinel). The worker produces work and re…
Knowledge Grounding
Search the knowledge pool before answering, ground claims in retrieved sources and cite them, recognize ingest-worthy content and capture it with knowledge_create — don't fabricate when the answer is on record.
Visual Output
Emit rich visual output in chat via <widget> tags — styled HTML cards, charts, tables, interactive tools, and drawn SVG/canvas diagrams, illustrations, and animations — theme-aware, centered, and responsive instead of clashing or cramped.
Artifacts
Persist, version, and iterate on LLM-generated UI (widgets, HTML, markdown). Load when the user wants to save, find, update, or iterate on a previously-rendered widget — anything that should outlive the chat scrollback.
Personal Cfo Setup
Finish setting up the Personal CFO pack — bind the finance folder and the digest day.
Delegation
Decide when to spawn a subagent vs. do work inline (cost-tiered) — don't spawn for trivial work; do spawn for parallel independent investigation or isolated long tasks; use wait for external callbacks and hook_register for external-system handoffs.
Cfo Statement Fetch
Collect the month's bank and card statements from the finance folder and normalise them into one table.
Infographic Syntax
Author infographics with the AntV declarative DSL — pick a template, fill a small indented data tree, and save as an artifact (kind=infographic) that renders to crisp SVG and streams as you write it. Load when the user wants an infographic, a visual summary, a comparison/steps/hierarchy/stats graphic, or "make this look like a poster/diagram".
Pclaw Features
Channel-neutral reference for PersonalClaw's capabilities — sessions, agents, models, dashboard, scheduling, goal loops, tasks, subagents, file/media handling, and config — so you can explain what PersonalClaw can do and route the user to the right surface.
Infra Drift Audit
Compare declared infrastructure against what a state refresh reports, and list the divergences without resolving them.
Editorial Document
Write long-form editorial documents as clean, semantic HTML saved as an artifact (kind=document) — reports, briefs, explainers, proposals, write-ups. Covers the house style (structure, voice, typography) AND the security contract (the HTML is sanitized fail-closed, so author within the allowlist). Load when the user wants a polished written document, report, brief, or explainer that should read l…
PersonalClaw
Your self-hosted personal AI agent — an agentic OS for one person: chat, autonomous goal loops, memory, knowledge base, skills, automation, MCP in both directions, and a permission-gated app platform. Local-first, provider-agnostic, MIT.
Pclaw Api
The operator's manual for DRIVING PersonalClaw's API and tools — how to find an exact tool/route signature, the mandatory verify-after-mutate loop, and what NOT to hand-roll. Load this before creating triggers, wiring models, driving app routes, or authoring skills through the API.
Check Work
Verify what you just claimed, with real tool calls — reconstruct the claims from this session, derive 2-4 executable checks from those specific claims, run every one, and report pass/fail with quoted evidence. A check that cannot be executed is reported unverifiable, never assumed passing.
Memory Discipline
When and how to persist durable memory — save genuine user preferences, facts, and corrections; NEVER persist transient environment failures (a failed command, a flaky network call, a one-off tool error) as lessons; recall before re-asking.
Ledger Read
Read a ledger CSV
Best Of N
Sample several candidate answers in parallel, judge them against stated criteria, and present the winner with the runners-up kept one click away. Confirms the count and the criteria first because each candidate is a separate model call. Use when the user wants options rather than one answer. Triggers include "give me N options", "give me 3 versions", "best of", "try a few versions", "sample and p…
Budget Coach
Weekly spend review
Task And Project
Track work as Tasks (the /api/tasks CRUD + native task provider), and decompose larger projects into independent, verifiable units — fanning parallel investigation out to subagents while keeping one coherent plan; hand open-ended goal-driven work to a goal loop.
Health Checkup Tracker
Track which routine checkups are due, from the user's own stated cadence.
Grill
Structured questioning to reach shared understanding before action. Walks the decision tree one branch at a time, checks memory for already-answered questions, saves every answer as a lesson. Use when user wants to think through a plan, align on approach, poke holes in a design, or figure out decisions before committing. Triggers include "before we start", "think this through", "what am I missing…