A lightweight, self-hosted personal finance app with a user-friendly interface and powerful bookkeeping features.

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.

Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).

Maintain durable, evidence-based repository context whenever an agent initializes a repository, implements or fixes behavior, refactors code, changes an interface, checkpoints or switches tasks, resumes or hands work to another AI tool, collaborates across parallel task sessions, Git branches, or worktrees, prepares a pull request, or completes a coding task. Use this skill to bridge Codex, Claude, Cursor, GitHub Copilot, Grok, and other coding agents through native instruction adapters, private session-isolated handoff drafts, atomic completed-change publication, a shared Context Manifest, language-aware Context Packs, stable feature specifications, verified change history, coverage gates, and managed README summaries without asking the user to run bookkeeping commands.

Place a one-off welcome and onboarding call to a customer who just signed up, capture a structured result such as business type, goal, pain points, sentiment, and activation status, then write that result back to a CRM and queue a human follow-up task when the customer asks for one.

DORMANT (ADR-0017, 2026-07-20) - the TERMINAL VELOCITY scroll-film was retired and apps/landing is a static site with no GL surface; this skill is preserved for any future WebGL rebuild (conventions, verified version pins, playhead/scroll-rig/VAT/Gerstner/post-chain patterns, budgets, gate + semantic-layer machinery). Do not load for current apps/landing work - the static site routes to project-steward.