agentsclimarketplace
Sign in

Project analyze

Skill uluserdar/claude-ecosystem/skills/project-analyze

Use to generate a structured set of project analysis/documentation Markdown files under docs/analyze/ in the current project, covering system, database, backend, frontend, and test aspects — either by interviewing the user about a new/empty project's intended design, or by reading an existing codebase and reporting what's actually there. ALWAYS trigger on phrases like "analyze this project", "analyze the codebase", "proje analizi yap", "sistem analizi yap", "generate analysis docs", "document this project's architecture", "create an ER diagram for this project", "bu proje için analiz dokümanı oluştur", "veritabanı analizi yap", "backend/frontend analizi yap", "create API documentation for this project", "document the Docker setup". Also trigger on requests to document technology stack, architecture diagrams, folder structure, naming conventions, or refactor/improvement suggestions for the current project. Do NOT trigger for release/feature planning (use create-plan instead) or for one-off questions about a single file that don't call for generated documentation.From its SKILL.md

Install
npx -y skills add uluserdar/claude-ecosystem --skill project-analyze

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.4 KB, as published. Nobody here has run it

project-analyze

This skill's only job is to hand off to the analyzer subagent, which owns the entire mode detection, interview/analysis, and documentation-generation flow. Do not analyze the codebase yourself, do not interview the user yourself, and do not write any files yourself.

Instructions

  1. Invoke the analyzer subagent via the Agent tool, passing along:
    • The user's stated request, verbatim.
    • Any relevant project context already established in the conversation.
    • Model: read agentModel["analyzer"] from .claude/claude-ecosystem-settings.json, falling back to agentModel.default; pass whichever resolves as the model parameter, or omit model entirely if neither is set.
  2. analyzer owns mode detection (new/empty project vs. existing project), the interview or codebase analysis, technology-skill gap detection and resolution, and delegating document generation to create-analyze — do not duplicate or second-guess its work.
  3. Once analyzer finishes, relay its summary and output paths back to the user.
<constraints> - This skill delegates 100% of analysis and generation work to `analyzer`. It has no standalone analysis logic of its own beyond routing. - This skill does not manage or update progress status on existing suggestion/refactor checklists — that is left to manual editing. </constraints>

Keep looking

Skills are one crate of 627,801. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.