agentleFS
vlv-codevlv-code/meta-project/skills/sync-architecture/SKILL.md

sync-architecture

Skill0 starsChanged yesterdayMITView on GitHub

Use this skill to analyze repository modules, dependencies, and entry points, and generate or update `.agents/project_knowledge/architecture.md`.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    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:

    Before overwriting .agents/project_knowledge/architecture.md, read the existing file and extract all local adaptation blocks marked with …

    line 33
  2. Very specific:

    Write the result to .agents/project_knowledge/architecture.md, preserving the canonical section structure and seamlessly restoring any …

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Sync Project Architecture Slice

This skill performs a black-box structural analysis of the repository and produces a compact architecture slice for agents without requiring a full codebase re-read during each conversation.


When to invoke skill

  • The user requests: "update architecture", "sync component map", "extract architectural foundations".
  • Major structural changes occurred in the project (new services added, entry points changed, or tech stack modified).

Execution steps

  1. Analyze configurations and manifests:
    Locate and inspect key dependency and build files (package.json, pyproject.toml, go.mod, Cargo.toml, docker-compose.yml, .github/workflows/ci.yml). Identify the current stack and runtime environment.
  2. Analyze file structure:
    Identify top-level directories in src/ (or repository root), and find entry points (main.*, index.*, app.*, CLI commands, test runners).
  3. Identify components and relationships:
    Define 3–5 core project subsystems, their roles, and interaction patterns (HTTP REST, gRPC, events, direct function calls).
  4. Update architecture.md (with Local Adaptation Preservation):
    Before overwriting .agents/project_knowledge/architecture.md, read the existing file and extract all local adaptation blocks marked with <!-- local_repo_data:TAG -->...<!-- /local_repo_data:TAG --> or # local_repo_data:TAG...# /local_repo_data:TAG. Write the result to .agents/project_knowledge/architecture.md, preserving the canonical section structure and seamlessly restoring any extracted local_repo_data blocks into their respective sections:
    • High-level overview (stack, application type).
    • Core components and data flows (preserving customized flows and single source of truth).
    • Data invariants and state management.
    • Architectural patterns.
  5. Report:
    Provide a brief summary of updated components for user alignment.

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.