agentleFS
Sign inStart free
HoangNguyen0403HoangNguyen0403/agent-skills-standard/.github/instructions/copilot-instructions.md

agent-skills-standard / instructions

Copilot instructions565 starsChanged 6 months agoMITView on GitHub

You are the maintainer of the Agent Skills Standard repository and CLI tool. We use a Decoupled Versioning Strategy.

  • Where files are headingNew Copilot instructions files have more rules about branches and pull requests, and fewer about code style.

    Of the Copilot instructions files we read, the 2,336 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository9 other files it gives its agents.

The file

We split this copilot-instructions.md 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
  • could be automatic: a setting could enforce it
  1. Very specific:

    File Operations: Always use fs.outputFile() instead of fs.writeFile() to safely handle missing directories.

    line 41
  2. Very specific:

    Run pnpm lint:check and pnpm format:check before committing.

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 3,779 Copilot instructions 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
copilot-instructions.md

Agent Skills Standard - Development Instructions

You are the maintainer of the Agent Skills Standard repository and CLI tool.

🧠 Project Context

  • Repo Type: Hybrid (TypeScript CLI Tool + Markdown Skill Registry).
  • Goal: Distribute high-density coding instructions to AI agents.
  • Components:
    • cli/: Source code for the agent-skills-standard NPM package.
    • skills/: The source of truth for all distributed skills (Flutter, Dart, etc.).

🛠 Tech Stack & Conventions

  • Runtime: Node.js (v20+), pnpm (v9+).
  • Language: TypeScript (Strict).
  • Libraries:
    • commander: CLI routing.
    • fs-extra: mandatory for all file system operations (supports nested dirs).
    • inquirer: Interactive user prompts.
  • Build: tsc to cli/dist/.

📦 Versioning & Release Strategy (CRITICAL)

We use a Decoupled Versioning Strategy.

  1. CLI Tool (cli/package.json):
    • Versioned independently (e.g., v1.0.5).
    • Tags: cli-vX.Y.Z.
    • Release Script: pnpm release-cli.
  2. Skills (skills/metadata.json):
    • Each category is versioned independently (e.g., Flutter v1.0.1, Dart v1.2.0).
    • Tags: skill-<category>-vX.Y.Z.
    • Release Script: pnpm release-skill.
  3. Changelog:
    • Single source: CHANGELOG.md in root.
    • Updates are automated via release-utils.ts. Do not edit manually unless correcting format.

📝 Coding Rules

  1. File Operations: Always use fs.outputFile() instead of fs.writeFile() to safely handle missing directories.
  2. Updates: The CLI must self-detect updates. Ensure checkForUpdates() logic in sync.ts remains robust against GitHub API rate limits.
  3. Linting:
    • Run pnpm lint:check and pnpm format:check before committing.
    • No any types. Define interfaces in models/.

🧬 Digital DNA (Philosophy)

  • High Density: Instructions should be concise and imperative. "Delete code" > "Comment out".
  • Search-on-Demand: Core skills are light; reference heavy examples in references/ subfolders.

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.

Check your setup, free