skilld
All skills
github avatar

/acquire-codebase-knowledge

@9ce8148 official
by githubgithub/awesome-copilot40k stars
5,040

Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document this architecture", "onboard me to this repo", or "create codebase docs". Do not trigger for routine feature implementation, bug fixes, or narrow code edits unless the user asks for repository-level discovery.

Ask your Agent

Use this Skill: https://skilld.dev/gh/github/awesome-copilot/acquire-codebase-knowledge

This session only. Nothing lands on disk.

assetstemplatesSTRUCTURE.md

≈279 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Codebase Structure

Core Sections (Required)

1) Top-Level Map

List only meaningful top-level directories and files.

Path Purpose Evidence
[path/] [purpose] [source]

2) Entry Points

  • Main runtime entry: [FILE]
  • Secondary entry points (worker/cli/jobs): [FILES or NONE]
  • How entry is selected (script/config): [NOTE]

3) Module Boundaries

Boundary What belongs here What must not be here
[module/layer] [responsibility] [forbidden logic]

4) Naming and Organization Rules

  • File naming pattern: [kebab/camel/Pascal + examples]
  • Directory organization pattern: [feature/layer/domain]
  • Import aliasing or path conventions: [RULE]

5) Evidence

  • [path/to/root-tree-source]
  • [path/to/entry-config]
  • [path/to/key-module]

Extended Sections (Optional)

Add only when repository complexity requires it:

  • Subdirectory deep maps by feature/layer
  • Middleware/boot order details
  • Generated-vs-source layout boundaries
  • Monorepo workspace-level structure maps

Source: SKILL.md on GitHub

Third-party checks

No alerts15d4 checks · Risk SAFE
  • Gen Agent Trust Hub15d

    This skill facilitates codebase onboarding by scanning local project files and git history to generate documentation. It is generally safe and authored by a trusted vendor, but it carries an inherent low risk of indirect prompt injection if the analyzed codebase contains malicious instructions designed to influence the documentation process.

  • Socket15d

    No alerts

  • Snyk15d

    Risk: LOW · No issues

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Provenance

Signed by skilld at 9ce8148. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 20 hours ago.

Activeupdated 2 weeks ago

Capability

Other metadata
compatibility
Cross-platform. Requires Python 3.8+ and git. Run scripts/scan.py from the target project root.
metadata
{
  "version": "1.3",
  "enhancements": [
    "Multi-language manifest detection (25+ languages supported)",
    "CI/CD pipeline detection (10+ platforms)",
    "Container & orchestration detection",
    "Code metrics by language",
    "Security & compliance config detection",
    "Performance testing markers"
  ]
}
argument-hint
Optional: specific area to focus on, e.g. "architecture only", "testing and concerns"

Topics

README badge

README badge for github/awesome-copilot/acquire-codebase-knowledge

What it does

Scans a codebase with a Python script to extract stack, structure, architecture, conventions, integrations, testing setup, and known concerns, then populates seven markdown documents in docs/codebase/ with verified facts only. Targets onboarding scenarios where a developer or agent needs to understand an unfamiliar repository quickly.

Generated from the current SKILL.md.

Frequently asked

Does this skill work with monorepos?
Yes. The skill detects workspaces and packages directories, and maps each sub-package separately with independent dependencies and conventions.
What languages and platforms does this support?
Cross-platform (Windows, macOS, Linux). Requires Python 3.8+, git, and detects 25+ programming languages. Run scripts/scan.py from the target project root.
Does this document generated code and build artifacts?
No. The skill documents only source conventions and patterns, explicitly avoiding dist/, build/, generated/, .next/, out/, and __pycache__ directories.
What happens if the skill can't determine something about the codebase?
Unknown items are marked [TODO]. If the answer requires team intent or context, it is marked [ASK USER] and presented as a numbered question at the end.
What output does this skill produce?
Seven documented files in docs/codebase/: STACK.md, STRUCTURE.md, ARCHITECTURE.md, CONVENTIONS.md, INTEGRATIONS.md, TESTING.md, and CONCERNS.md, with evidence trails to source files.

Generated from the current SKILL.md. These answers refresh after source changes.