Content & Media

Comprehensive AI/LLM evaluation toolkit for production AI systems. Covers LLM output quality, prompt engineering, RAG evaluation, agent performance, hallucination detection, bias assessment, cost/token optimization, latency metrics, model comparison, and fine-tuning evaluation. Includes BLEU/ROUGE metrics, perplexity, F1 scores, LLM-as-judge patterns, and benchmarks like MMLU and HumanEval.

Use when building features with TCA (The Composable Architecture), structuring reducers, managing state, handling effects, navigation, or testing TCA features. Covers @Reducer, Store, Effect, TestStore, reducer composition, and TCA patterns.

Collecte et analyse les Pull Requests GitHub avec leurs commentaires d'agents de review IA (CodeRabbit, GitHub Copilot, Codex, etc.). Utilise GitHub CLI pour récupérer les données, extrait les métadonnées des agents avec jq, et génère une structure organisée par PR et par importance dans le dossier .scd du projet. Extensible pour supporter de nouveaux agents de review.

Guide for debugging and performance optimization of EDS blocks including error handling, FOUC prevention, Core Web Vitals optimization, and debugging workflows for Adobe Edge Delivery Services.

Create log entries with timestamps. Use this when documenting discoveries, research findings, meetings, code reviews, articles, videos, or significant events during development.

Domain UI/UX Expert - Enterprise design systems, component architecture, accessibility, icons, and theming integration

Use when editing ANY Neovim configuration including init.lua, plugins, keymaps, LSP settings, or theme configuration. Provides file structure guidance and VHS testing workflow.

Transcribe therapy session recordings to formatted text. Converts audio to clean, speaker-labeled transcripts (Me/Therapist format) with grammar correction and English translation. Use when processing therapy recordings, session audio, or any two-person conversation recording.

Framework for holding opposing positions in productive tension without premature synthesis. Use when facing paradoxes, contradictions, or when early synthesis would flatten necessary distinctions. Prevents convergence-based thinking that eliminates the contrast needed for genuine insight.

Validates compliance with 9 Constitutional Articles and Phase -1 Gates before implementation.Trigger terms: constitution, governance, compliance, validation, constitutional compliance,Phase -1 Gates, simplicity gate, anti-abstraction gate, test-first, library-first,EARS compliance, governance validation, constitutional audit, compliance check, gate validation.Enforces all 9 Constitutional Articles with automated validation:- Article I: Library-First Principle- Article II: CLI Interface Mandate- Article III: Test-First Imperative- Article IV: EARS Requirements Format- Article V: Traceability Mandate- Article VI: Project Memory- Article VII: Simplicity Gate- Article VIII: Anti-Abstraction Gate- Article IX: Integration-First TestingRuns Phase -1 Gates before any implementation begins.Use when: validating project governance, checking constitutional compliance,or enforcing quality gates before implementation.

Create irresistible offers and pitches using Alex Hormozi's methodology from $100M Offers. Guides through value equation, guarantee frameworks, pricing psychology, and creating offers "too good not to take" for any product or service.

実装タスク管理書（tasks.md）を作成・編集します。設計書からタスク分解、AIエージェント向けの具体的な実装指示、TDD手順の定義が必要な場合に使用してください。requirements.md、design.mdとの整合性を逆順レビューで確認します。

Guide user story creation using the standard template. User stories contain acceptance criteria, agent assignments, and technical details. Use when BA agent extracts stories from PRD, creates new stories, or validates story structure.

Maintain approved technology stack including TypeScript/Python languages, React/Tailwind frontend, Node.js/FastAPI backend, PostgreSQL/Redis persistence, and Ansible infrastructure automation with enforced quality gates. Use this skill when selecting technologies, adding dependencies, configuring tooling, or ensuring infrastructure-as-code practices. Applies to package.json, requirements.txt, CI/CD pipelines, Ansible playbooks, linters, formatters, testing frameworks, and all technology choices requiring documented approval and migration strategies.

Loads and extracts all content from web URLs. Use when the user asks to fetch, load, or retrieve content from a website or URL.

End-to-end health check for WaveCap-SDR captures. Use when captures are stuck in "starting" state, spectrum analyzer not updating, audio not playing, or to verify the system is working correctly.

Validate constitutional compliance for specifications, plans, tasks, code, and operationsusing the SDD Framework Constitution v1.5.0 (14 principles). Use when checking if workfollows constitutional requirements or executing compliance validation.This skill provides guidance on applying all 14 constitutional principles and runningautomated compliance checks. It ensures all work adheres to immutable, critical, andstandard principles governing architecture, quality, workflow, and safety.Triggered by: User request for "constitutional check", "compliance validation","does this follow the constitution?", or before major milestones (commit, PR, release).

Analyze PDF documents with table extraction, section identification, and content summarization. Use when reading technical documents, reports, or papers.This skill provides PDF analysis capabilities:- Text extraction and OCR- Table detection and CSV conversion- Section and heading identification- Key points summarization- Metadata extractionTriggers: "analyze PDF", "extract tables", "summarize document", "read PDF", "PDF解析", "テーブル抽出", "ドキュメント要約"

Implement JWT custom claims authentication for Supabase to reduce API database queries. Use when building Next.js API routes that need user authentication and authorization (role, company_id, facility_id). Embeds user metadata into JWT tokens to eliminate 40% of database queries per API request. Triggers when implementing authentication in API routes, optimizing Supabase queries, or setting up user session management.

Skill creation and validation framework ensuring compliance with Helix architectural standards.USE WHEN user says "create skill", "create a skill", "new skill", "build skill","make skill", "skill for X", "Create-A-Skill", or any request to create new Helix skills.