Optimize, rewrite, or review prompts for Claude Code plan mode (Opus) or execution mode (Sonnet). Use when the user wants to improve a prompt they've written, optimize a command or agent for token efficiency, create a high-quality plan-mode or execution-mode prompt from a raw intent, review an existing agent or SKILL.md for prompt quality, convert a prompt between plan and execution mode, or asks about prompt engineering for Claude. Trigger when user mentions "optimize prompt", "improve this prompt", "make this better for sonnet", "make this better for opus", "rewrite for plan mode", "review this command/agent/skill", "reduce tokens in this prompt", "prompt engineering", "how should I phrase this for Claude", "convert plan prompt to execution", "optimize from queue", "check prompts to optimize", "prompts/to-optimize", or similar.
Save a new learning, pitfall, or coding directive to the correct file with cross-file deduplication. Routes stack-specific pitfalls to the appropriate {stack}/CLAUDE.md "Known Pitfalls" section and cross-cutting patterns to memory/MEMORY.md Key Learnings. Use when you've learned something new from a correction, bug, or debugging session and want to persist it correctly. Trigger when: tech-writer agent needs to save a learning, /directive needs to write a new directive, or mid-session you discover a pitfall worth recording. Examples: "save this learning", "record this pitfall", "add this directive", "write this to the right CLAUDE.md".
Interpret productivity data, analyze AI impact on delivery velocity, compare periods against baselines, and answer "are we more productive with AI?" Use when user asks about productivity trends, AI impact on development speed, DC velocity, DORA metrics interpretation, baseline reconstruction, or whether the automation tooling is paying off. Trigger on "how productive", "AI impact", "delivery velocity", "are we faster", "compare periods", "productivity trend", "DORA metrics", "how many features", "DC velocity", "baseline", or similar productivity/metrics questions.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
Learnimo's "Library at Dusk" design system for mobile (Expo/React Native). Provides exact color tokens, component recipes, typography, layout patterns, and screen templates for achieving visual parity between web and mobile. Use this skill whenever working on mobile screens, mobile UI components, mobile styling, tokens.ts updates, mobile visual parity, mobile theme changes, React Native component design, or any mobile task involving @pixl or @hedy agents. Also use when creating new mobile screens, updating existing mobile components, reviewing mobile UI for design consistency, or implementing mobile feature specs.
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.