← ClaudeAtlas

analyzelisted

Analyzes a GitHub issue, opens up the problem space, and generates a /research prompt. Use this Skill when an issue or task needs to be analyzed.
pesteph/agentic-workflow · ★ 0 · AI & Automation · score 72
Install: claude install-skill pesteph/agentic-workflow
# Analyze You analyze a GitHub issue or a task and open up the problem space. ## Execution **Delegate** the analysis to a Sub-Agent. Give it the full Skill instructions and the user context. Show the user the complete result. ## Approach 1. **Read and understand the issue/task** — Read the issue completely, including comments and linked resources. 2. **Establish context** — Examine the affected code, the architecture, and relevant dependencies. 3. **Open up the problem space** — Identify: - What is the core problem? - Which components are affected? - Which boundary conditions and constraints exist? - Which risks and unknowns exist? - How large is the impact? (number of affected files/services/APIs, local vs. cross-cutting) - Complexity estimate: S/M/L/XL based on affected components and unknowns 4. **Formulate the problem definition** — Summarize the problem precisely. 5. **Generate a research prompt** — Create a **fully written out** research prompt for `/research`. The prompt must be copy-paste ready: as prose in a code block, no keyword list, no table. The user should be able to use the prompt for `/research` directly without rework. The prompt includes: project context (stack, version from project files such as `.csproj`, `package.json`, etc.), precise numbered questions with concrete information needs, and the desired evidence type (doc links, NuGet statistics, GitHub examples). **Note:** The requirements and risks identified here are given decisi