Total 44,222 skills
Showing 12 of 44222 skills
Pragmatic coding standards - concise, direct, no over-engineering, no unnecessary comments
This skill should be used when the user asks to "create financial projections", "build a financial model", "forecast revenue", "calculate burn rate", "estimate runway", "model cash flow", or requests 3-5 year financial planning for a startup.
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
Build scalable design systems with design tokens, theming infrastructure, and component architecture patterns. Use when creating design tokens, implementing theme switching, building component libraries, or establishing design system foundations.
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. Provides patterns for recognizing and mitigating context failures.
MSW search integration — (1) vector search for API docs and implementation guides (msw-guide-mcp or curl against mlua_Document_Retriever / mlua_API_Retriever), (2) REST API search for resources (sprite / animation / sound / resource pack / avatar). Use for 'find details, examples, or related APIs not in .d.mlua', 'need a SpriteRUID', 'monster sprite', 'background image', 'find a sound', 'avatar rendering', etc. Keywords: document search, API details, examples, guide, retriever, resource, sprite, animation, sound, RUID, resource pack, avatar.
Guides consumption and understanding of Fusion backend services, APIs, and patterns for frontend/client developers, integrators, and architects. Shows reference implementations, explains architectural decisions, and clarifies contracts. USE FOR: understanding Fusion backend APIs, learning implementation patterns, exploring reference code, choosing the right integration point, and understanding authorization/validation/async patterns. DO NOT USE FOR: modifying backend services, creating new endpoints, database changes, or backend-specific development (use fusion-services-develop or backend service repo instead).
Wires the Navigation component from @cognite/dune-industrial-components/navigation into a Dune app. Use when adding a navigation header, top nav bar, sticky header, nav items, active page, nav links, navigation component, theme toggle, or dark mode support to a Dune app.
Generates eval test cases from an eval suite plan (output of /eval-suite-planner) or a plain-English agent description. Supports both single-response and conversation (multi-turn) evaluation modes. Outputs a Copilot Studio test set table, a CSV file for import (single-response only), and a docx report for human review.
Xiaohongshu (RED) title formula tool. It helps you select the suitable formula from 75 proven hit templates, use it correctly and understand the logic behind the formula selection. Trigger methods: /dbs-xhs-title, /xiaohongshu-title, "help me write a Xiaohongshu title", "Xiaohongshu title formula" Xiaohongshu title formula tool. Pick the right formula from 75 proven templates. Trigger: /dbs-xhs-title, "xiaohongshu title", "RED title formula"
OpenInference semantic conventions and instrumentation for Phoenix AI observability. Use when implementing LLM tracing, creating custom spans, or deploying to production.
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.