agentleFS
jpeslar1jpeslar1/john-peslar-ai-skills/.github/copilot-instructions.md

john-peslar-ai-skills

Copilot instructions12 starsChanged 4 months agoMITView on GitHub

This repository contains public agent skills for Codex, Claude Code, Cursor, and other tools that support the SKILL.md pattern. When adding a skill, update:

The file

We split this copilot-instructions.md into the rules it gives an agent

9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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. Distinctive:

    Every skill must live in a root-level folder named exactly like the skill.

    line 7
  2. Very specific:

    Every skill folder must include SKILL.md.

    line 8
  3. Very specific:

    Keep each SKILL.md concise.

    line 12
  4. Distinctive:

    Do not include private client details, API keys, internal repo paths, or proprietary credentials.

    line 13
  5. Distinctive:

    Use MIT license for public skills.

    line 14
  6. Distinctive:

    Write direct, practical copy for founders, operators, marketers, and builders.

    line 18
  7. Distinctive:

    Avoid hype that cannot be backed up.

    line 19
  8. Distinctive:

    Use normal hyphens instead of em dashes or en dashes.

    line 20
  9. Distinctive:

    When adding a skill, update:

    line 25

≈ “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

John Peslar AI Skills Repository Instructions

This repository contains public agent skills for Codex, Claude Code, Cursor, and other tools that support the SKILL.md pattern.

Skill Rules

  • Every skill must live in a root-level folder named exactly like the skill.
  • Every skill folder must include SKILL.md.
  • Frontmatter must include name, description, license, and metadata.
  • name must be lowercase hyphen-case and match the folder.
  • description should include practical trigger phrases.
  • Keep each SKILL.md concise. Move templates, examples, and source notes to references/.
  • Do not include private client details, API keys, internal repo paths, or proprietary credentials.
  • Use MIT license for public skills.

Copy Rules

  • Write direct, practical copy for founders, operators, marketers, and builders.
  • Avoid hype that cannot be backed up.
  • Use normal hyphens instead of em dashes or en dashes.
  • Make every skill useful as a standalone artifact.

Marketplace

When adding a skill, update:

  • README.md
  • EXAMPLES.md if the skill needs a user-facing example
  • .claude-plugin/marketplace.json
  • .agents/plugins/marketplace.json
  • The relevant plugins/<collection>/ folder

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.