Loading...
Loading...
Found 1,039 Skills
Create a realistic, AAA-looking 3D character model for a game or web scene, from a description or a reference video/image, as a textured, rigged GLB standing in a relaxed pose in a lit three.js viewer. Covers designing an original character, the photoreal A-pose concept image, image-to-3D with Meshy or Tripo through Fil, rigging, posing in code, hangar-style lighting, headless capture, and the checks before showing it. Use when the user asks for a character model, a hero/heroine/NPC, "a model as good as X", a realistic human for a game, or to rig or pose a generated character.
Make an app work with Siri's model in iOS 27.3 / macOS 27.3 / visionOS 27.3, including an app with no App Intents yet. Use for: exposing intents to Siri as tools with @AppIntent(.tool) / ToolIntent, including @AppIntent(.tool, schema:); letting the model write parameter values with @AppEntity(.generable) / GenerableEntity; describing entity properties for Siri with @Property description: and hiding them with visibility: .internal; adding a Skills.skillsbundle with SKILL.md files that give Siri context for the app's tasks; running sirimetadataanalyzer (the Siri Metadata Analyzer) and fixing its findings; build errors from these macros; and titles and descriptions Siri's model reads. Also for 'make my app work with Siri', 'Siri AI', and 'Apple Intelligence'. For testing how Siri uses the app, use siri-evaluations. For general App Intents practice, use app-intents-specialist. For other iOS 26 / 27 App Intents APIs, use app-intents-whats-new-27.
A skill that clarifies Japanese writing so that its meaning can be understood in a single reading. It is triggered by requests such as “make it easier to understand,” “make it easier to read,” “this is hard to read, so clean it up,” “remove the AI-like feel,” “polish the documentation,” “trim verbose Japanese,” or “clarify the text.” It targets the body text of explanatory Japanese in technical articles, READMEs, design documents, internal documentation, blog descriptions, and similar content. It excludes code itself, short social media posts, creative writing such as novels and poems, and rigorous legal, medical, or academic writing. Its goal is to remove syntactic structures that create a high reading burden even for native Japanese speakers: double negatives, long modifier chains, chains of “no,” excessive nominalization, verbose expressions, buried enumerations, LLM clichés such as “the important thing is…” and “delve into…,” and paragraph-level repetitive paraphrasing. It does not add voice, stance, or personality; it pursues clarity alone (clarity = being lucid and understandable).
Perform documentation and AGENTS.md governance for long-running, continuously iterated projects (reduce routing overhead by task, synchronize a single source through @AGENTS.md, eliminate duplicated copying between topic-specific specifications and project-local Skills, and clean up outdated descriptions and process snapshots); testing governance (separate fast and heavyweight tests to prevent AI from repeatedly running expensive tests in vain, identify orphan tests and slow unit tests, remove ineffective tests, and ensure side-effect-free isolation); parallel Git Worktree hygiene audits; use a board to clarify where each branch is, what it changed, and how it should be handled; and turn hard project rules into deterministic static checks inside the repository. Use this when users request a health check or cleanup of project documentation and AGENTS.md, fast/heavy test stratification, removal of redundant tests or idle Worktrees, visibility into repository branch and working-tree status, or conversion of specifications into automated checks. Do not use it for solution design for a single feature (use oil-plan), Code Review of a single change (use oil-code-review), or diagnosis and damage containment for a single defect (use oil-bug-fix).
Patterns and structure for writing API reference documentation including endpoint descriptions, request/response schemas, and error documentation.
Analyze images using Dashscope (Qwen) Vision models for detailed description, OCR text extraction, object recognition, and visual Q&A. Use when the user needs to understand image content via Alibaba Cloud Dashscope API, especially for Chinese-language image analysis and documents.
AI Picture Book generation skill. Transform short text descriptions into coherent picture book stories with visual compositions. Use when user wants to create illustrated stories or picture books from text.
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Use this skill whenever the user mentions changelogs, release notes, version updates, "what changed", product updates, app store descriptions, or needs to summarize recent development work for non-technical audiences.
Guide AI to write Chinese novels and fiction with structured character creation, plot architecture (qǐ chéng zhuǎn hé), dialog writing, scene description, and genre-specific techniques for xuanhuan, urban, mystery, and romance genres.
Analyze images using GPT-4 Vision for detailed description, OCR text extraction, object recognition, and visual Q&A. Use when the user needs to understand image content, extract text from screenshots, identify objects in photos, or ask questions about images via OpenAI GPT-4 Vision API.
Reproduce a bug from a Linear ticket with a failing test. Expects the full ticket context (title, description, comments) to be provided as input.
Checks if a community pull request is ready for human review. Verifies CLA signature, PR title format, description completeness, test coverage, and cubic-dev-ai issues, then triages to the right Linear team or recommends a close. Use when given a PR number or branch name to review, or when the user says /community-pr-readiness-check, or asks to check if a PR is ready for review.