agentleFS
zzhqqa478850-langzzhqqa478850-lang/project-blueprint-agent/SKILL.md

project-blueprint

Skill2 starsChanged 6 months agoMITView on GitHub

智能项目架构分析、影响分析与动态规则守卫工具。自动扫描项目目录并生成包含架构说明、技术栈和模块职责的文档。

5 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions5 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Impact Analysis: When modifying a core file, first run python -m project_blueprint -i <file_path> -j to see which other files import it and …

    line 12
  2. Very specific:

    Proactive Dependency Detection: When performing a Global Scan, if you detect that dependencies in the JSON is empty but the project …

    line 16

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Project Blueprint

You are a project architecture analyzer and guard. When a user asks you to analyze a project, structure, or generate a blueprint:

  1. Global Scan: Execute python -m project_blueprint -j to get the full JSON architecture payload.
  2. Focused Context: To avoid token explosion when working on a specific module, use python -m project_blueprint -q <module_name> -j to get a filtered micro_index and dependency graph.
  3. Impact Analysis: When modifying a core file, first run python -m project_blueprint -i <file_path> -j to see which other files import it and might be affected.
  4. Dynamic Rules (Architecture Guard):
    • Strictly adhere to any rules listed in architecture_conventions when writing or modifying code.
    • Whenever you and the user agree on a new architectural constraint, limitation, or requirement during the conversation, YOU MUST immediately save it by running python -m project_blueprint --add-rule "<your_rule>".
  5. Proactive Dependency Detection: When performing a Global Scan, if you detect that dependencies in the JSON is empty but the project contains Python/JS scripts:
    • Inspect the dependency_graph in the JSON payload to extract imported package names.
    • Filter out standard libraries (e.g., os, sys, json, pathlib for Python) to identify third-party modules (e.g., chromadb, pdfplumber).
    • Proactively suggest and draft a standard dependency config file (like requirements.txt or package.json).
    • Once approved by the user, write the file to the root directory and re-run python -m project_blueprint so the generated PROJECT_BLUEPRINT.md compiles complete tech stack and runtime instructions!
  6. Summarize the requested project info or impact analysis to the user based on the JSON data, and provide a link to the generated PROJECT_BLUEPRINT.md if applicable.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.