Claude Skills by zhengbingquant

Mandatory safety protocol for working in any environment that might be attached to production: real money, live trading or brokerage, payments, real customer traffic, physical hardware, or scheduled jobs. Consult BEFORE the first state-changing command on an unfamiliar host or repo, BEFORE starting, stopping, restarting, or killing any process or service, BEFORE running an entry point (main.py, a server, a deploy script), BEFORE editing config or env files, and BEFORE acting on any 'task fini...

Bootstrap a new Python project from a proven scaffold. Use whenever the user asks to start, create, scaffold, or set up a new Python tool, library, CLI, package, service, or experiment repo — or says 'set up a project the usual way'. Do NOT hand-roll a project structure from memory when this skill is available: run its script instead. Produces a src-layout package with pyproject.toml, tests, Makefile, an agent contract (AGENTS.md + CLAUDE.md), operating docs, a review checklist, and a definit...

Disciplined-execution playbook for non-trivial engineering work. Consult BEFORE writing code whenever a task touches more than one file, an unfamiliar codebase, a bug whose cause is not yet proven by evidence, a refactor, a migration, or any state-changing operation — not only when the user asks for a plan. Applies even when the request sounds quick or trivial ('just', 'simple', 'quick fix'). Rule of thumb: if you cannot already name the exact command that will prove the change works, read th...