Loading...
Loading...
Found 2,394 Skills
Use when starting any RLM requirement to set up an isolated git worktree. REQUIRED before Phase 1 - creates isolated workspace, verifies clean test baseline, and prevents main branch pollution.
Detects and visualizes geometric intersections in OpenSCAD models using built-in techniques (intersection(), debug modifiers), BOSL2 utilities (debug_this, ghost), and reusable collision check patterns. Use when checking drawer clearances, door swing interference, shelf spacing, hinge collisions, or any geometric overlap in woodworking projects. Triggers on "check collision", "detect interference", "drawer clearance", "door swing", "check overlap", "assembly interference", or "fits in cabinet". Works with .scad files, woodworkers-lib patterns, BOSL2 attachments, and OpenSCAD 2025 Manifold engine.
Domain-oriented architecture for Laravel without external package dependencies, based on concepts from "Laravel Beyond CRUD" (Spatie). Use this skill when the user wants to structure a Laravel project using DDD, domain-oriented architecture, or organize code by business concepts instead of technical properties. Also activate when the user asks about: Actions, Data Objects (DTOs), lean models, States with enums, ViewModels (Blade or API), HTTP Query builders, application layer, or scaling Laravel projects beyond simple CRUD. Activate for any mention of "domain layer", "application layer", "beyond CRUD", "domain-oriented", or requests to refactor a Laravel project into domain structure. Even if the user asks "how to organize a large Laravel project", this skill is relevant.
Systematic documentation audit and maintenance. This skill should be used when documentation may be stale, missing, or misorganized — after feature work, refactors, dependency upgrades, or as a periodic health check. It prescribes folder structure for docs/ and manual/, dispatches haiku subagents for codebase/doc scanning, and routes doc creation to specialized agents (reference-builder, technical-writer, learning-guide) with docs-architect as quality gate.
A micro-prompt that reminds the agent that it is an interactive programmer. Works great in Clojure when Copilot has access to the REPL (probably via Backseat Driver). Will work with any system that has a live REPL that the agent can use. Adapt the prompt with any specific reminders in your workflow and/or workspace.
Use when creating frosted glass effects, transparent overlays, or modern glass UI. Covers blur, layering, colored shadows.
Respond in Chinese to user requests; when the user's message is fully in English (ignoring punctuation, digits, emojis, and whitespace), append a brief Chinese evaluation plus a 1-10 score.
Specialized business logic evaluator for the Evaluate-Loop. Use this for evaluating tracks that implement core product logic — pipelines, dependency resolution, state machines, pricing/tier enforcement, packaging. Checks feature correctness against product rules, edge cases, state transitions, data flow, and user journey completeness. Dispatched by loop-execution-evaluator when track type is 'business-logic', 'generator', or 'core-feature'. Triggered by: 'evaluate logic', 'test business rules', 'verify business rules', 'check feature'.
Create diverse synthetic test inputs for LLM pipeline evaluation using dimension-based tuple generation. Use when bootstrapping an eval dataset, when real user data is sparse, or when stress-testing specific failure hypotheses. Do NOT use when you already have 100+ representative real traces (use stratified sampling instead), or when the task is collecting production logs.
Create and manage a git worktree for parallel feature development, then open the new worktree in the editor (code/Cursor) for a second Codex session. Use when the user asks to work on another feature simultaneously, run multiple features in parallel, spin up a parallel workspace, or open a new worktree even if they do not mention worktree explicitly.
TikTok Ads deep analysis covering creative quality, tracking, bidding, campaign structure, and TikTok Shop. Evaluates 25 checks with emphasis on creative-first strategy, safe zone compliance, and Smart+ campaigns. Use when user says "TikTok Ads", "TikTok marketing", "TikTok Shop", "Spark Ads", "Smart+", or "TikTok campaign".
Help users integrate and troubleshoot weapp-tailwindcss in uni-app, taro, uni-app x and native mini-program projects. Use when users mention weapp-tailwindcss, invalid Tailwind in mini-programs, arbitrary rpx values, JS string class, space-y/space-x, weapp-tw patch, content/@source, twMerge/cva/tv.