Mobile

Use when implementing on-device AI with Apple's Foundation Models framework (iOS 26+), building summarization/extraction/classification features, or using @Generable for type-safe structured output.

Validates and reviews skills against the Agent Skills specification. Checks YAML syntax, naming conventions, description quality, file structure, and best practices. Provides improvement suggestions with before/after examples and optionally applies fixes. Use when validating skills, reviewing skill quality, checking skills before commit, or when `--check-skill`, `--validate-skill`, or `--review-skill` is mentioned.

Extracts and assesses research methodology, claims, evidence, and infrastructure from research papers in HASS disciplines. Evaluates transparency, reproducibility, and credibility through systematic extraction (eight-pass workflow, Pass 0-7) and credibility assessment (research approach classification, quality gating, and repliCATS Seven Signals evaluation adapted for HASS).

Generate appropriate commit messages based on Git diffs

Add a Swift file to an Xcode project without opening Xcode. Programmatically edits project.pbxproj to include the file. Use when adding new Swift files to iOS projects from command line.

Master machine learning, data engineering, LLMs, prompt engineering, AI agents, and MLOps. Covers Python ML libraries, data pipelines, LLM applications, and model deployment. Use for ML projects, data engineering, AI agent development, and ML system design.

Creating high-quality agent skills following Claude's official best practices. Use when designing, implementing, or improving agent skills, including naming conventions, progressive disclosure patterns, description writing, and appropriate freedom levels. Helps ensure skills are concise, well-structured, and optimized for context efficiency.

Systematic debugging for Rust applications. Root cause analysis, loggingstrategies, profiling, and issue reproduction. All debug changes removedbefore final report.

Run and debug a WebF app specifically in WebF Go (desktop/iOS/Android): load dev URLs, connect via devtools://, collect WEBF_NATIVE_LOG logs, clear WebF Go cache, and handle WebF Go limitations. Use when the user explicitly mentions WebF Go, devtools://, WEBF_NATIVE_LOG, the WebF Go debug button, or WebF Go settings (Clear Cache).

Compiles production-ready EU grant proposals from EU Grant Hunter briefs,UBOS narrative banks, partner commitments, and budget templates. Reuses theproven 1,850:1 ROI methodology that secured €6M Xylella funding. Coordinatesthe full assembly workflow: intelligence gathering, narrative compilation,budget construction, partner onboarding, compliance checks, quality scoring,and final packaging (PDF/LaTeX). Target score: ≥4.6/5 (Horizon 13.8/15). Usewhen preparing submissions, tracking proposal status, or managing consortiumdeliverables.

DEPRECATED umbrella Skill (backward compatibility). Use only when a Flutter host request spans multiple WebF integration areas (controllers + bundles + embedding + routing + caching/theming + perf). Prefer focused openwebf-host-* Skills.

Search GitHub for real-world code examples and implementation patterns. Use when user wants to find code examples on GitHub, search GitHub repositories, discover how others implement features, learn library usage patterns, or research architectural approaches. Fetches top results with smart ranking (stars, recency, language), extracts factual data (imports, syntax patterns, metrics), and returns clean markdown for analysis and pattern identification.

Coordinates data pipeline tasks (ETL, analytics, feature engineering). Use when implementing data ingestion, transformations, quality checks, or analytics. Applies data-quality-standard.md (95% minimum).

Enterprise Rust with ownership model and safety guarantees: Rust 1.91.1, Tokio 1.48, async/await, macro system, error handling, memory safety patterns; activates for systems programming, performance-critical code, concurrent applications, and safety-first development.

Process pending items from 0-inbox/ task queue.Assess scope and create appropriate KB artifacts (tickets, phases, PRDs).WHEN TO USE:- After completing primary work (ticket, phase, user request)- User says "check inbox", "process inbox", "what's pending"- Periodic inbox reviewSOURCES:- Direct user messages (not immediately actionable)- GitHub issues/PRs- Slack messages- External integrationsNOT during main workflow - only after primary directive complete.

Reads config.json and prompts user for application parameters. Merges configuration with defaults for project generation.

Senior business consultant expertise for strategic analysis, frameworks, and executive communication. Use when structuring arguments, applying business frameworks (MECE, pyramid principle, Porter's Five Forces), crafting executive summaries, or developing strategic recommendations.

Automatically applies when securing AI/LLM applications. Ensures prompt injection detection, PII redaction for AI contexts, output filtering, content moderation, and secure prompt handling.

SwiftUIを使ったiOSアプリのUI実装を支援するスキル。View +

Configure structured logging and telemetry for the .NET 8 WPF widget host app using Serilog, ETW, and Application Insights. Use when wiring logging sinks, correlation IDs, PII redaction, error reporting, and diagnostics exports.