Agent skills for OpenAI Agents SDK

Create and manage engineering tasks on the project host (GitHub or GitLab Issues) and optional ClickUp product/tracking tickets.

Generate comprehensive, meaningful tests for a given piece of code

Pre-implementation analysis of the code tied to an issue, for two kinds.

Disciplined diagnosis loop for hard bugs and performance regressions.

Deconstruct any live website into reusable recipe — extract HTML, CSS, JS, design tokens, animations.

Review changed code for reuse, quality, and efficiency, then fix any issues found.

Transforms articles into animated hand-drawn whiteboard diagram B-roll videos using AI video models like Seedance 2.0.

Audit, design, categorize, distribute, and measure agent skills using lessons from Anthropic's Lessons from building Claude Code: How we…

Create or update shared project skills with ClickUp task tracking, README registration, validation, scoped staging, and commit-message…

Orchestrate multi-skill workflows with prompt-based skill chaining.

CI/CD accessibility pipeline patterns with axe-core CLI, SARIF output, PR annotations, baseline management, and multi-platform CI templates.

Create new skills, modify and improve existing skills, and measure skill performance.

Comprehensive guide to designing reliable, scalable data systems covering databases, streaming, and consistency

Use when the user wants their agent setup graded from real conversation history, asks which installed skills are actually working, or…

Use when creating new Rune skills, editing existing skills, or verifying skill quality before deployment.

Install Claude skills from GitHub repositories with automated security scanning.

Stand up a self-contained second-brain "OS" that lives entirely inside a Claude skill — a short SKILL.md router plus context files, no…

Light with overcast, soft, shadowless daylight.

Enrich leads via Perplexity.ai with Playwright when scrapers are blocked.

Run a full 6-phase autonomous replication of a biomedical/epidemiology paper against UK Biobank or similar cohort data, producing Python…