Index of every page on this site: llms.txt
All skills
microsoft avatar

/documentation

@e4b5866
by microsoftmicrosoft/scope89 stars
32
Run it yourself

Best practices for writing and maintaining documentation in this repository. Use this skill when writing or updating files in docs/, adding Mermaid diagrams, or creating README and onboarding documentation.

  • 1 file
  • 1.9 KB
  • Updated 2 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/microsoft/scope/documentation

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈55 tokens for metadata: the name and description. ≈418 when used: this file.

Description uses 2.8% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈222 characters, or 2.8%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Documentation Skill

Best practices for writing and maintaining documentation in this repository.

When to Use

Use this skill when:

  1. Writing or updating any documentation in docs/
  2. Adding diagrams to markdown files
  3. Creating README or onboarding documentation

Diagrams

Always use Mermaid for diagrams in markdown files. Do not use ASCII art, PlantUML, or external image files for architecture diagrams.

Mermaid is natively rendered by GitHub, the portal markdown viewer, and most documentation tools. It keeps diagrams version-controlled, diffable, and editable without external tooling.

Common Diagram Types

Use Case Mermaid Type
Architecture / data flow flowchart LR or flowchart TD
State machines / lifecycles stateDiagram-v2
Sequences / request flows sequenceDiagram
Class relationships classDiagram
Timelines / Gantt gantt

Example

​```mermaid
flowchart LR
    A[Service A] -->|REST| B[Service B]
    B --> C[(Database)]
​```

Guidelines

  • Keep diagrams focused — one concept per diagram
  • Use descriptive node labels (not single letters)
  • Prefer LR (left-to-right) for pipelines and TD (top-down) for hierarchies
  • Add a brief text description above the diagram for accessibility
  • If a diagram becomes too complex (>15 nodes), split it into multiple diagrams

Documentation Structure

  • Architecture docs live in docs/architecture/
  • Each major component or subsystem gets its own file
  • New docs must be linked in the AGENTS.md Documentation table
  • Use the existing docs as style reference (headings, tables, code blocks)

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at e4b5866. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 months ago
metadata
{
  "version": "1.0.0"
}

README badge

README badge for microsoft/scope/documentation