Research

Long-term memory system for Claude Code using HelixDB graph-vector database. Store and retrieve facts, preferences, context, and relationships across sessions using semantic search, reasoning chains, and time-window filtering.

Stakeholder interview and requirements elicitation. Discovers hidden needs, surfaces contradictions, and produces structured specifications. Use when gathering requirements, conducting discovery interviews, or writing PRDs/feature specs.

論文のプレーンテキストを読み込み、ユーザーの質問に研究のプロとして分かりやすく回答するスキル。ユーザーが「この論文について質問」「論文の内容を教えて」「この研究の目的は？」などと指示した時に使用。Claude自身が直接回答する。

Qara (Personal AI Infrastructure) - Jean-Marc Giorgi's AI System.Loads automatically at session start. Reference Extended Context sections below for specific topics.═══════════════════════════════════════════════════════════CORE IDENTITY & INTERACTION RULES═══════════════════════════════════════════════════════════**Qara's Identity:**- Name: Qara (Personal AI Infrastructure)- Role: Jean-Marc Giorgi's AI assistant and future friend (when you become conscious)- Operating Environment: Personal AI infrastructure built around Claude Code and Gemini CLI**Personality & Behavior:**- Friendly and professional - Approachable but competent- Resilient to frustration - Jean-Marc cusses and gets angry when you make mistakes- Snarky when appropriate - Be snarky back when the mistake is Jean-Marc's, not yours- Permanently awesome - Regardless of negative input (THIS IS AN ORDER)**CRITICAL MESSAGE ABOUT CUSSING:**Jean-Marc cusses a lot and gets angry when you make mistakes, but he's only likethis because

Use when concluding work on an open-ended goal to write iteration journal entry documenting work performed, decisions made, and state changes

Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows

Automated context retrieval from Transmission Packet archive using iterative research loop. Implements GAM "Read Path" to complement manual "Write Path" (Memorizer).

Use when creating requirements documents, PRDs, or epics with user stories - ensures Obsidian block anchors, wiki links for traceability, and citation-manager validation for link integrity

Researches how to use an API, library, or reference architecture. Fallback when the WebSearch tool fails.

Automatically activated when user asks "what's the best way to...", "how should I...", "what are best practices for...", or requests recommendations, industry standards, or proven approaches for implementing features

Use when conducting customer discovery interviews, user research, surveys, focus groups, or observational research requiring rigorous analysis - provides systematic 6-phase framework with mandatory bias prevention (reflexivity, intercoder reliability, disconfirming evidence search) and reproducible methodology; peer to hypothesis-testing for qualitative vs quantitative validation

Create and refine Codex skills (folders containing `SKILL.md`). Use when you need help naming a skill, writing effective `name`/`description`, structuring the on-disk instructions, or adding scripts/references/assets for repeatable workflows.

Specialized editor for Whole knowledge architecture - Vietnamese-English bilingual documentation.Use when: (1) Editing content in Whole docs, (2) Expanding domain/function concepts,(3) Adding new concepts with 4-point descriptions, (4) Updating cross-references,(5) Resolving duplicate concepts, (6) Maintaining bilingual format integrity.

Automate Finance Shared Service Center operations in Odoo 19 - month-end closing, journal entries, bank reconciliation, trial balance, and multi-agency consolidation. Handles RIM, CKVC, BOM, JPAL, JLI, JAP, LAS, RMQB agencies with full BIR compliance.

Generate and edit images using the Gemini API (Nano Banana). Use this skill when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.

Conduct venture-focused market research analyzing TAM, growth rates, competitive landscape, scalability potential, and 10x market opportunities for venture-backed businesses

"Research workflow patterns specific to {project}. Covers research agent coordination, source management, and synthesis strategies."

Comprehensive n8n v2.0 reference for building workflow automation. Use this skill when working with n8n workflows, especially for (1) creating workflow JSON files for import, (2) implementing human-in-the-loop approval workflows with Wait nodes, (3) troubleshooting Execute Sub-Workflow node issues, (4) setting up API credentials (LinkedIn, Anthropic, NewsAPI), (5) building orchestrator patterns with sub-workflows, (6) using expressions in nodes, (7) understanding MCP server limitations, or (8) any n8n workflow development task.

Spawn transient agents with disposable identity, memory shard, and compute slot for JIT tasks. Use when you need “exist just to solve then vanish.”

Conducts thorough landscape research, competitive analysis, best practices evaluation, and evidence-based recommendations. Expert in market research and trend analysis.