Audit an AI/ML system for governance controls — bias risk, explainability, model risk management, data lineage, fairness metrics, and…
Generate AI images using Gemini or GPT APIs directly.
Use this skill for WeChat Mini Program AI via wx.cloud.extend.AI (小程序, 企业微信小程序, wx.cloud apps).
Explore a repository read-only and produce a decision-complete implementation plan from an approved spec.
Create or revise a self-contained requirements-and-design spec for an AI-native development change.
Extracts work summaries, token metrics, and modified file paths from local AI coding logs to accurately attribute activity across projects.
Design a multi-round questioning sequence for interrogating AI chatbot answers, tracking how responses shift and distinguishing genuine…
Detects when Luminance, Kira, or a similar bulk-review tool is in use, hands off the high-volume clause extraction to it, and QAs its…
Use when you want your product to surface in AI-generated answers (ChatGPT, Perplexity, Gemini) — creates llms.txt, optimizes structured…
Queries, manages, and troubleshoots Apache Airflow using the `af` CLI.
Quickly deslop UI code by fixing spacing, hierarchy, typography, and small layout issues.
Professional brand consistency enforcement and corporate identity management with support for color palettes, typography, logo usage, tone…
Use when creating new skills, documenting workflows, or standardizing processes into reusable skill definitions.
Provides React Native performance optimization guidelines for FPS, TTI, bundle size, memory leaks, re-renders, and animations.
Create, generate, or write Dockerfiles and multi-stage Docker images.
HTTP API-based documentation server (always running).
Comprehensive Alembic database migration management for customer support systems
This skill should be used when the user asks "is this regex safe", "what is ReDoS", "why does CPU spike on one request", "how do I safely…
When the user wants to apply, document, or enforce brand guidelines for any product or company.
Cascades strategy from boardroom to individual contributor.
Right-layer check before coding a fix. Locates which layer a problem actually lives at (data model, storage, API, business logic, UI…