NeVibeCode · repository · 19 items
poka-yoke: a set by rainmanjam
The rainmanjam/poka-yoke repository on GitHub: 19 cards with a description and an install command. They work in Claude Code, Codex, Cursor — 8 platforms in total.
About the repository
- GitHub
- rainmanjam/poka-yoke
- Stars
- ★ 26
- License
- MIT
- Source updated
- 2026-10-14
- In the catalog since
- 2026-10-27
design skill design — a skill for shaping a new interface together with its failure paths: the accepted range of every parameter, the checks, and what callers get when something breaks.
CX Codex +1
★ 26repo stars
defensive skill defensive is a Claude Code skill for validating inputs and handling failures. It activates when a request calls for code that is safer or less prone to crashes.
CX Codex +1
★ 26repo stars
audit skill This skill guides a review of unchecked inputs, missing timeouts, and other unhandled failure paths. Use it to audit an existing codebase.
CX Codex +1
★ 26repo stars
ux skill ux tells the agent how to split a screen into components, pick a state owner and keep markup away from business rules.
CX Codex +1
★ 26repo stars
retro skill retro guides post-incident code analysis to identify structural weaknesses and prevent entire classes of failures.
CX Codex +1
★ 26repo stars
design skill design is a Claude Code skill for shaping a new interface, module, schema, or type before other code depends on it. It guides design requests around names, parameters, dependencies, and testability.
CX Codex +1
★ 26repo stars
clean-code skill clean-code is a Claude Code skill that checks naming, cohesion, duplication and function size. It helps shape a new module before anyone calls it.
CX Codex +1
★ 26repo stars
authz skill authz guides access control architecture by separating permission decisions from enforcement.
CX Codex +1
★ 26repo stars
audit skill The audit skill reviews working code for structural issues and ranks findings by the cost of leaving them in place. Use it when planning a refactor and deciding which problems matter first.
CX Codex +1
★ 26repo stars
ux skill ux — a skill for building screens where users cannot make a costly mistake: forms, deletes, bulk actions, checkout.
CX Codex +1
★ 26repo stars
retro skill retro transforms an outage or bug into a structural constraint that stops the entire class of mistakes permanently.
CX Codex +1
★ 26repo stars
ops skill ops sizes up a deploy before you run it: what cannot be undone, what breaks mid-rollout, and how fast you can back out.
CX Codex +1
★ 26repo stars
llm skill llm guides mistakeproofing for user-facing AI features: structured outputs, tool validation, injection boundaries, and evals.
CX Codex +1
★ 26repo stars
guardrails skill guardrails is a Claude Code skill that turns project rules into checks enforced by hooks, CI, or database constraints. It activates when a team needs enforcement instead of another written guideline.
CX Codex +1
★ 26repo stars
design skill design is a Claude Code skill for shaping types and APIs so invalid states cannot be expressed. It activates while a new interface is being designed.
CX Codex +1
★ 26repo stars
data skill Guides data warehouse audits and dbt checks to turn silent number discrepancies into explicit pipeline stops before bad rows reach production dashboards.
CX Codex +1
★ 26repo stars
authz skill The authz skill finds cross-tenant access paths and helps enforce tenant checks in queries, repositories, and routes.
CX Codex +1
★ 26repo stars
audit skill audit scans code that already exists for spots where a wrong move slips through quietly: swapped arguments, silent fallbacks, deletes with no guard.
CX Codex +1
★ 26repo stars
agent-guardrails skill agent-guardrails stops AI agents from breaking repositories using PreToolUse hooks, permission deny rules, and verification gates.
CX Codex +1
★ 26repo stars