Agent skills for OpenAI Agents SDK

Use for a technical incident, disputed diagnosis, bug fix, or claim that a change works.

Verify a test-program change or conclusion through fresh deterministic evidence and iterative repair.

Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED…

Use when implementing or reviewing UI against Figma, screenshots, design tokens, or an existing component system.

How to check that a Minecraft plugin actually works on a running Paper/Purpur server using VitaminMCP - connecting a session, reading…

Use when about to run tests/builds for ctsnetwork-event, after editing any file in event/backend or event/frontend, or before reporting…

Boolean logic and digital circuits with exact results — truth tables, minimal simplification, Karnaugh maps, normal forms…

Semantic version parsing, bump strategies, and document version management.

Protect durable behavior across version changes.

Vets whether to build a feature from scratch, use an existing free/open-source solution, or pay for a third-party API/service.

Use after a brand direction and source of truth are confirmed to produce or maintain VI manuals, logo packages, brand assets, landscape…

Preliminary filter for any criminal action: establishes jurisdiction, the applicable procedure according to the date of the events, the…

Use when improving accessibility — WCAG 2.2 compliance across Perceivable, Operable, Understandable, Robust.

Use when designing APIs or module boundaries — contract-first, Hyrum Law, error semantics.

Use when making CEO decisions — vision, market, and organizational strategy.

Use when agent sessions generate long histories, context window limits are hit, or you need to preserve decisions and artifact trails…

Use when output quality drops or you switch tasks — feed agents the right information at the right time.

Use when making CTO decisions — tech debt, team scaling, architecture, and DORA metrics.

Use when running autonomous research — plan, search, read, and synthesize into reports.

Use when making architectural decisions, changing APIs, or shipping features — write Architecture Decision Records and API docs that…

Use when stakes are high — adversarial fresh-context review of every non-trivial decision.