Project Doc Analyst

    1

    Deep-reads an entire codebase and generates engineering semantic documentation for both humans and AI, staged by priority: overview and architecture first, then design rationale and code examples.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    project-doc-analyst

    Example session with this skill installed

    Analyze this project / generate project documentation.

    • Read your context and instructions
    • Compiled the project-doc-analyst

    A staged documentation set: project overview, technical architecture, design rationale, and code examples, ready for humans and AI agents.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Deep-reads the entire codebase and generates engineering semantic asset documentation for both humans and AI. Staged by priority: P0 (project overview and technical architecture) first, then P1 (design rationale, product analysis, code examples), with optional docs and deep dives. Ideal for preparing onboarding docs, AI context files, and architecture reviews. Works with Claude Code, Cursor, OpenClaw, Codex and any agent that reads SKILL.md.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Technical Documentation.

    Requires local repository access. Large projects (>200 files) use sampling. Cannot perform code refactoring or bug fixes. Evidence is limited to what exists in the provided file tree.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 14 days ago

    • Free with an Agensi account

    Permissions

    Network Access
    Read Files
    Listed14 days ago

    What's inside

    Frequently Asked Questions

    The Project Doc Analyst specializes in the 'why' behind the code, extracting engineering philosophy and technical tradeoffs that standard READMEs miss. While generic tools summarize files in isolation, this skill maps system-wide dependencies and data flows to build a cohesive mental model of your architecture.

    This skill is language-agnostic and works with any project containing standard manifest files like package.json, Cargo.toml, or pyproject.toml. It uses a tiered sampling strategy to handle large codebases, prioritizing core logic and entry points to ensure accuracy even in repositories with hundreds of files.

    The output is a suite of structured Markdown documents, including Mermaid-based architectural diagrams and module responsibility maps. These assets are specifically formatted to be high-density and low-ambiguity, making them perfect for both human onboarding and priming other AI coding agents.

    The skill features a built-in refinement loop that allows you to request targeted updates to specific sections without re-analyzing the entire repository. This ensures your documentation can evolve alongside your code without consuming unnecessary processing tokens.

    Project Doc Analyst is designed to be compatible with any AI agent platform that supports repository access and Markdown processing. It functions as a specialized 'researcher' that provides the necessary context for your existing coding or debugging agents to perform more accurately.

    New in Technical Documentation

    Free