메뉴
This skill should be used when the user asks to 'research codebase', 'scan tech stack', 'import documents', 'discovery questions', or needs guidance on Phase 1 research. Also trigger on 'sdd research', 'brownfield scan', 'import transcript', or 'check ecosystem'.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | research-analyst |
| description | This skill should be used when the user asks to 'research codebase', 'scan tech stack', 'import documents', 'discovery questions', or needs guidance on Phase 1 research. Also trigger on 'sdd research', 'brownfield scan', 'import transcript', or 'check ecosystem'. |
Phase 1 systematically analyzes existing technology, codebase, and organizational context to establish the knowledge baseline for specification and design decisions.
Execute structured research in this sequence:
New project with no existing codebase. Characteristics:
Actions:
Extending existing codebase. Characteristics:
Actions:
For brownfield projects, automatically catalog:
Languages & Runtime
Web Frameworks
Databases
Infrastructure
DevOps & Quality
Security & Compliance
Generate tech stack report with version matrix and compatibility notes.
Aggregate all existing documentation and project history:
Specification Documents
Design & Architecture
Process & Compliance
Communications
Code & Artifacts
Import strategy:
Interview stakeholders to fill gaps using seven categories:
Document all answers in RESEARCH.md.
Map the project's external dependencies and integrations:
Outbound Integrations (services this system calls)
Inbound Integrations (services that call this system)
Data Flow Map
Compliance Ecosystem
Generate dependency graph and assess risk of each integration.
Structure the research artifact as:
# Research Phase Report
**Project:** [name]
**Date:** [YYYY-MM-DD]
**Phase:** 1 - Research
**Status:** Complete
## Executive Summary
[1-paragraph overview of key findings]
## Greenfield vs Brownfield Assessment
**Classification:** [Greenfield | Brownfield]
[2-3 paragraphs explaining rationale]
## Technology Stack (Brownfield)
[Catalog of existing tech with versions]
### Current Performance Metrics
[Uptime, response times, throughput]
## Imported Documents
- [Document 1]: [Summary]
- [Document 2]: [Summary]
## Ecosystem Integrations
### Outbound
[List with brief description]
### Inbound
[List with brief description]
## Discovery Findings
[Answers to 7 discovery question categories]
## Risk Assessment
- Technical risks: [list with mitigation]
- Organizational risks: [list]
- External dependency risks: [list]
## Recommendations
[Next phase readiness assessment]
## Appendix: Full Tech Stack
[Detailed technology inventory]
/specky:research --greenfield # Start new project
/specky:research --brownfield # Analyze existing code
/specky:research --tech-scan # Technology stack only
/specky:research --import-docs # Document aggregation
/specky:research --discovery # Stakeholder interviews
| Tool | Purpose |
|---|---|
sdd_scan_codebase | Detect language, framework, package manager, folder structure |
sdd_discover | Generate 7 structured discovery questions |
sdd_research | Investigate technical unknowns and produce findings |
sdd_import_document | Import PDF/DOCX/MD documents as research context |
sdd_import_transcript | Import VTT/SRT meeting transcripts |
sdd_batch_import | Batch import multiple documents |
sdd_check_ecosystem | Report recommended MCP server integrations |
@research-analyst — Phase 1 agent that calls these tools to build the knowledge baseline. Load this skill as first step.
Decision framework for designing production agentic systems on GitHub platform and Azure AI Foundry. Covers model routing tiers (mini to frontier), prompt caching and semantic caching, short and long term memory, context curation and RAG, tools and MCP, identity and guardrails, evaluation, observability (OpenTelemetry GenAI), and cost control. Use when architecting an AI agent or multi-agent system, choosing a model router, deciding a caching or memory strategy, planning context windows, or reviewing an agent design for reliability, security, and cost. Pairs with azure-managed-redis-cache, foundry-agent-blueprint, azure-api-center, apim-ai-gateway, and azure-architecture-diagrams.
Front model and tool backends with Azure API Management as an AI gateway: token rate limiting (token-per-minute and quota), multi-backend load balancing and circuit breaker across model deployments, semantic caching, token metric emission for cost attribution, managed identity to backends, and content safety integration. Use when designing the runtime gateway for an agentic platform, enforcing token budgets, load balancing across model endpoints, adding a semantic cache at the gateway, or governing tool API calls. Routes to the installed azure-aigateway skill for policy detail. Pairs with azure-api-center (governance), azure-managed-redis-cache (cache backend), and agentic-architecture-patterns.
Validate an architecture document (the {app}_Architecture.md produced by the Senior Cloud Architect agent) against a hard Definition of Done: required sections, the five required diagrams, well-formed Mermaid, the seven explanation parts per diagram, and the repository copy conventions. Use when producing, reviewing, or finishing an architecture document, or whenever you need to confirm a Mermaid-based architecture deliverable is complete and will render before presenting it.
Govern APIs and agent tools at enterprise scale with Azure API Center: a central catalog of APIs, versions, definitions (OpenAPI), environments, and deployments, plus registration of agent tools and MCP servers for discovery and reuse. Use when designing API governance for an agentic platform, building a tool or MCP registry for agents, enforcing API standards with the API Center linter, or making backend APIs discoverable to agent builders. Pairs with apim-ai-gateway (runtime gateway), foundry-agent-blueprint (tool consumption), and agentic-architecture-patterns (tools and MCP).
Produce complete, professional architecture diagrams that use the official Azure, Microsoft, and GitHub (Octicons) icon sets, output as editable draw.io (.drawio) files and exported SVG. Covers the official icon catalogs and their terms of use, the draw.io mxGraph file format, layout and connector conventions, and a bundled draw.io MCP server (Python FastMCP) that creates and edits .drawio diagrams programmatically (add nodes with official icons, connect edges, group, and lay out). Use whenever the deliverable includes an architecture diagram, a system context, a component or deployment diagram, or any cloud diagram that must use official vendor icons. Pairs with ai-native-engineer and agentic-architecture-patterns, and complements svg-professional for hand-crafted SVG.
Design and provision Azure Managed Redis as the cache, semantic cache, vector store, session store, and agent memory backend for AI-native systems. Covers SKU selection (Balanced, MemoryOptimized, ComputeOptimized, FlashOptimized), the fact that Redis Enterprise is retired for new creations, vector search and RedisVL for semantic caching and long term memory, session and short term state, tenant isolation, managed identity (Entra) access, private networking, and a Bicep sample. Use when an agent design needs caching, a semantic cache, a vector memory store, or session state on Redis. Pairs with agentic-architecture-patterns and apim-ai-gateway.