Agent skills for OpenAI Agents SDK

Design and implement formative, summative, and developmental evaluations using logic models and mixed methods

Programmatic SEO planning and analysis for pages generated at scale from data sources.

HTML-first development with CSS-only interactivity patterns.

Progressive L1-L6 refactoring hierarchy, 22 code smell taxonomy, atomic transformations, test code smells, and Fowler refactoring catalog

Progressive verification methodology for debugging complex systems.

Progressive Web Apps with service workers, web manifest, offline support, installation prompts.

Use when creating, updating, auditing, or standardizing a repository-level AGENTS.md.

Standardizes project architecture, coding patterns, and deployment workflows for Claude Code to ensure consistent development across the…

Enable collaboration and invite specified Manus account holders to an existing Manus project or task.

Creates core project docs (requirements, architecture, tech stack, patterns catalog).

Conducts Phase 0 assessments of codebases to evaluate project health, architectural integrity, and potential risks before starting new…

Coordinates project documentation creation with single context gathering and project type detection.

Run a critical, multi-dimensional quality review of the project using parallel adversarial agents.

Researches any project idea against live data from GitHub and Dev.to to surface what already exists, how mature the space is, and where…

Enforce domain knowledge mapping, intent elicitation, and progressive decision navigation before project initiation.

Use this skill for \"initialize project\", \"set up project\", \"scaffold project\", \"create AGENTS.md\", \"create CLAUDE.md\", \"set up…

Streamlines the initialization of new software repositories by scaffolding directory structures, project-specific agent guidelines, and…

Coordinate secure, specification-driven projects through hierarchical subagent delegation and durable project records.

Builds and maintains a compact, on-demand "project map" so coding agents remember a codebase's structure and spend fewer tokens during…

Generate CLAUDE.md project memory files that transfer institutional knowledge, not obvious information.

Run a structured onboarding interview to generate USER.md and PROJECT.md — capturing developer preferences, project constraints, access…