研究

Synthesize Reflector insights into structured delta proposals for playbook updates, following ACE paper's Curator architecture

Automate ML workflows with Airflow, Kubeflow, MLflow. Use for reproducible pipelines, retraining schedules, MLOps, or encountering task failures, dependency errors, experiment tracking issues.

Professional LaTeX document generation for papers, reports, books, and presentations. Multi-agent orchestration via claude-flow. Use UK English spelling throughout.

Creates professional API documentation using OpenAPI specifications with endpoints, authentication, and interactive examples. Use when documenting REST APIs, creating SDK references, or building developer portals.

Generate comprehensive Product Requirement Plans (PRPs) for feature implementation with thorough codebase analysis and external research. Use when the user requests a PRP, PRD, or detailed implementation plan for a new feature. Conducts systematic research, identifies patterns, and creates executable validation gates for one-pass implementation success.

Toolkit for performing deep research on complex topics using multiple AI research providers (OpenAI, Falcon, Perplexity, Consensus). Emphasizes explicit speed vs depth trade-offs.

Write comprehensive markdown documentation from analyzed media content with structured sections, quotes, timestamps, and citations. Use after media-reviewer analysis to create final documentation.

Perplexity AI research assistant with real-time web search, source citations, and optimized UK-centric prompts. Access live web data, current events, market research, and comprehensive analysis backed by verified sources.

Consult external AIs (Gemini 2.5 Pro, OpenAI Codex, Claude) for second opinions. Use for debugging failures, architectural decisions, security validation, or need fresh perspective with synthesis.

Deploy production recommendation systems with feature stores, caching, A/B testing. Use for personalization APIs, low latency serving, or encountering cache invalidation, experiment tracking, quality monitoring issues.

This skill should be used when the user needs to search for information, find files, look up content online, or retrieve data without providing input files. Trigger phrases include: - "search for", "find", "look up", "research" - "search the web", "search online", "fetch from URL" - "search files", "scan codebase", "find in project", "grep for" - "get news from", "read hacker news", "check what's trending" Supports multiple search modes: - local: Search local filesystem using Glob, Grep, Read, Bash - web: Search web content using WebSearch, WebFetch - future: Pluggable providers (jina.ai, firecrawl, exa.ai) This is an input-less skill - it executes search missions autonomously.

Invoke BEFORE writing database queries or working with Selection API, ActiveRow in Nette.

Set up GPU sandboxes for interpretability research. Use when writing setup.py scripts with Sandbox, SandboxConfig, ModelConfig, or create_notebook_session. Provides the exact API for Modal GPU environments - MUST read before writing any sandbox setup code.

Perform gene set enrichment analysis using AI research providers. Analyzes lists of genes to identify biological themes, pathways, and functional associations.

Complete Liquid templating language reference including syntax, filters, objects, control flow, loops, and conditionals for Shopify themes. Use when working with .liquid files, creating theme templates, implementing dynamic content, debugging Liquid code, working with sections and snippets, or rendering product/collection/cart data in Shopify stores.

Looplia writer skill for generating content ideas with personalization. Reads user profile for context. Generates hooks, angles, and thought-provoking questions. Use after media-reviewer to transform analysis into creative content ideas.

ユーザーがGitHub Actionsのタグ参照をSHA参照に変換するよう要求したときに発動してください。uses:フィールドのタグ参照を自動的にSHA参照（コミットハッシュ + コメント付きバージョン）に変換します。

Master the know CLI tool for managing specification graphs. Use when working with spec-graph.json, understanding graph structure, querying entities/references/meta, managing dependencies, or learning graph architecture. Teaches dependency rules, entity types, and graph operations.

Systematic debugging with hypothesis-driven investigation. Use when something is broken, tests are failing, unexpected behavior occurs, or errors need investigation. Triggers on: "this is broken", "debug", "why is this failing", "unexpected error", "not working", "bug", "fix this issue", "investigate", "tests failing", "trace the error", "use debug mode". Full access mode - can run commands, add logging, and fix issues.

SettingsKit for SwiftUI settings interfaces (iOS, macOS, watchOS, tvOS, visionOS). Use for settings/preferences screens, searchable settings, nested navigation, @Observable/@Bindable state, or encountering settings update errors, navigation state issues.