Agent skills for Claude Desktop

Use when deciding which geb-* sub-skill to invoke next, or when sequencing manuscript work from topic selection through rebuttal for a…

Find failing PR checks, inspect logs or external check links, and apply focused fixes

Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes…

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds.

Graph-relational database with EdgeQL query language, code-first schema, link-based relations, computed properties, and fully typed…

Automates interactions with Google Gemini to generate high-quality text and images directly within Claude Code.

Use when integrating Google Gemini API into projects.

[Trigger] When PPT workflow needs SVG slide layout and aesthetic optimization via Gemini. [Output] Structured optimization suggestions…

Run Gemini Deep Research via browser automation.

Generate strong headline options for draft copy by running it through Google's Gemini model.

Generate and edit images using the Gemini API (Nano Banana).

Generate and edit images using the Gemini API (Nano Banana Pro).

Search research papers via Gemini for broad literature discovery.

Generate and conversationally edit short videos with Google Gemini Omni Flash (`gemini-omni-flash-preview`).

Internal guidance for presenting Gemini helper output back to the user

Validate code compliance with Gemini mod rules (core, modules, features, UI, WebSocket, state)

Remove the visible Gemini AI watermark from images using reverse alpha blending.

Standard disclaimer and attribution templates for AI-generated or AI-assisted data analysis outputs

Generates multi-page narrative manga and educational comics with standardized characters to explain Generative AI concepts and workplace…

Use when evaluating, comparing, researching, or preparing vendor questions for Generative AI platforms, AI services, orchestration layers…

Run Vendo's buy-vs-build generation benchmark — generation time + accuracy of the real Vendo pipeline vs raw-Claude baselines (diy…