Explore finance and payments skills for AI agents. Connect billing, subscriptions, and transaction workflows directly into Claude Code, Cursor, and automation agents.
This directory brings installable AI Agent skills into one place so you can filter by search, category, topic, and official source, then install them directly into Claude Code, Cursor, Windsurf, and other supported environments.
Generate todays journal note when the user says /today or asks for a daily log. Use template `00_inbox/日记模版.md` (fallback `00_inbox/日记模板.md`), create the note in `99_学习情况记录`, add a Chinese-first global situation dashboard (map + a concise table summary + finance/tech bullets under the map) for the latest 24 hours, list unfinished tasks from existing notes in `99_学习情况记录`, and list todays tasks extracted from `Overview & Study Record.md` as markdown checkboxes.
Investigate errors, incidents, or product ideas using both internet research and repo-wide codebase research, then propose a concrete changeset plan with clarifying questions before any implementation. Use when a user asks to investigate, root-cause, or plan changes, or when an Issue or PR is referenced and needs a plan.
Investigates failing Kubernetes pods and Flux HelmReleases to identify root causes of deployment issues in the home-ops cluster.
Plan code refactors by defining goals/non-goals, mapping dependencies, sequencing phases, and specifying verification and rollback checkpoints; triggers: refactor plan/restructure/rename/move modules.
When and how to edit InfoProviders lookup JSONs (company, country, treaty, ISIN). Use when fixing Failed processing stock lot, wrong country or company data, or adding fallbacks for unresolved identifiers.
Performance optimization playbook (measure → diagnose → fix → verify) for this repo (React + R3F + Three.js + Vite). Use when asked to improve FPS, reduce jank, lower draw calls, optimize loading/bundle size, or investigate CPU/GPU/memory bottlenecks.
AI-First Programming Protocol (APP) defines a capability-oriented architecture for building agent-operable software. Systems are organized into self-contained Cases with predictable surfaces, enabling humans and AI agents to discover, understand, and operate capabilities with low context cost.