Agent skills for OpenAI Agents SDK

Comprehensive project architecture blueprint generator that analyzes codebases to create detailed architectural documentation.

Complete testing strategy covering TDD workflow, test pyramid, unit/integration/E2E/property testing, framework best practices (Jest…

Use when calibrating completeness vs. selectivity and ensuring fairness across schools, authors, and controversies in a Journal of…

Use when appraising the credibility of the studies a Perspectives on Psychological Science (PoPS) piece synthesizes and calibrating…

Use when testing exhaustiveness, risk-of-bias, heterogeneity, and sensitivity for a Review of Educational Research (RER) review or…

Use when the user says 'tokenstack', 'compression', 'token savings', 'proxy status', or asks about context window usage.

Use to compress any agent-instruction file (AGENTS.md, CLAUDE.md, .claude/rules/*.md, legacy AIBOARDING.md) into terse, high-signal prose…

Manage reproducible computational environments

GPU compute programming skill for parallel algorithms and data processing.

COMSOL Multiphysics skill for continuum-scale nanomaterial and device modeling

Design progressive learning sequences that build foundational understanding before complexity.

Teaches programming concepts in Python and Go using intuitive real-world metaphors, progressive walkthroughs, and interactive slide decks.

Turn concepts into static HTML visuals exported as PNG or SVG files via HTML/CSS/SVG.

Analyze philosophical concepts through examination of necessary and sufficient conditions, identify counterexamples, clarify conceptual…

Use when the conceptual or analytical framework is the bottleneck for a World Development (WD) manuscript — development theory that…

Use when designing the conceptual exhibits of a Progress in Human Geography (PiHG) review essay — typologies, framework diagrams, concept…

Use when building the conceptual or analytical framework for a Global Environmental Change (GEC) manuscript.

Structures technical explanations with conclusion-first logic, explicit causal reasoning, and minimal tangential clutter.

Use when writing or editing any user-facing or agent-facing text, including docs, specs, README content, PR descriptions, UI copy…

Orchestrate a full band from a single directive

Conduct a defensible cybersecurity risk assessment using the NIST SP 800-30 Rev 1 methodology: prepare scope and a risk model, identify…