Agent skills for OpenAI Agents SDK

Audit a research corpus for shallow stubs, missing sources, and doc-depth issues.

Assess source quality using GRADE methodology

VS-Enhanced Research Question Refiner - Prevents Mode Collapse and derives differentiated research questions Enhanced VS 3-Phase process…

Show research corpus health and statistics

Internal skill. Synthesis guidance loaded via SKILL_HINTS by planner and bug-investigator when research files are available.

Perform technical web research using authoritative sources, synthesize the results, and save a cited research note in the repo.

Execute multi-stage research workflows

Automates a multi-stage pipeline to generate and deploy specialized researcher agent specifications for technical investigations.

Research WoW addon development topics using CLI tools, Blizzard UI source, and documentation.

Resign the current chess game

Resize and crop a single image into platform-specific dimensions for social media.

Batch-resize images for web (WebP at 1920/1200/400px), social (center-cropped WebP at Instagram square/portrait, Twitter/X, LinkedIn)…

Use as the follow-up to brainstorm-beagle when a spec has an Open Questions section (or quietly carries latent gaps) that need closing…

Automate Respond IO tasks via Rube MCP (Composio).

Respond to review comments on a PR after evaluation and fixes

Structure point-by-point referee responses for the sewage-house-prices paper.

Assists with security incident response, investigation, and remediation.

Draft professional, empathetic customer-facing responses adapted to the situation, urgency, and channel.

Test website responsiveness across viewport widths using browser automation.

RESTful API design principles, versioning, pagination, HATEOAS, and documentation.

Drafts and refines first-person Chinese literary narratives using restrained reportorial prose, concrete details, and understated emotion.