Loading...
Loading...
Found 9,900 Skills
Runtime performance audit worker (L3). Checks blocking IO in async, unnecessary allocations, sync sleep in async, string concat in loops, missing to_thread for CPU-bound, redundant data copies. Returns findings with severity, location, effort, recommendations.
Mindmap Generator - Auto-activating skill for Visual Content. Triggers on: mindmap generator, mindmap generator Part of the Visual Content skill category.
Generate Xiaohongshu copy and accompanying images. Use this when users need to create Xiaohongshu posts, generate social media copy, or produce Xiaohongshu operation content
This skill should be used when user asks to "create a PR", "make a pull request", "open PR for this branch", "submit changes as PR", "push and create PR", or runs /create-pr or /pr-creator commands.
Wield Google's Gemini CLI as a powerful auxiliary tool for code generation, review, analysis, and web research. Use when tasks benefit from a second AI perspective, current web information via Google Search, codebase architecture analysis, or parallel code generation. Also use when user explicitly requests Gemini operations.
Creates visual design philosophies and expresses them as static art in PNG and PDF formats using composition, color theory, typography, and graphic design principles. Use when asked to "create a poster", "design artwork", "make a visual design", "create static art", or "design a graphic piece". Develops aesthetic movements through form, space, color, and minimal text as visual accents. Works with PDF and PNG output files plus markdown design manifestos. Produces original visual designs using design philosophy methodology rather than copying existing artists.
Generates diagrams from text using Kroki unified API. Supports PlantUML, Mermaid, D2, C4, GraphViz, DBML, and 20+ formats. Use when creating UML diagrams, architecture diagrams, flowcharts, ERDs, sequence diagrams, or state machines.
Test-driven development for Laravel with PHPUnit and Pest, factories, database testing, fakes, and coverage targets.
Autonomous multi-round research review loop. Repeatedly reviews via Codex MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.
Implement reviewer feedback on a Canva design. Reads all comment threads, synthesises what reviewers want, makes the clear-cut changes directly, and flags anything that needs a human decision. Use when the user asks to "implement feedback on my deck", "address comments on a design", "apply review feedback", "fix the comments on my presentation", or "implement the feedback".
Full content production pipeline from blank page to publish-ready piece. Covers competitive research, content briefs, drafting, SEO optimization, readability scoring, editorial quality gates, and internal linking. Use when writing blog posts, articles, guides, or long-form content end-to-end, or when user mentions write a post, draft an article, create content, content pipeline, editorial workflow, content operations, content calendar management, repurposing, or content at scale.
Jito bundle submission for MEV protection on Solana — bundle building, tip strategies, block engine endpoints, and landing rate optimization