agentleFS
EmzyjepppEmzyjeppp/devflow-rules/skills/ponytail-lean/SKILL.md

ponytail-lean

Skill0 starsChanged 43 days agoMITView on GitHub

Software engineering simplicity principles to eliminate over-engineering, prioritize standard libraries, and enforce YAGNI.

The file

We split this skill 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:

    YAGNI (You Aren't Gonna Need It): Do not write code or architectural abstractions for unrequested, hypothetical future requirements.

    line 12
  2. Distinctive:

    Avoid Premature Abstraction: Do not build factories, wrapper classes, or generic interfaces for single concrete implementations.

    line 15
  3. Distinctive:

    Before writing new code or installing a package, evaluate these seven tiers in order:

    line 19
  4. Very specific:

    Installed Packages: If an external library is required, use packages already present in package.json.

    line 25
  5. Distinctive:

    Concise Custom Code: Write a small, clear function (10-30 lines) focused on the specific task instead of adding a large package.

    line 26
  6. Distinctive:

    New External Dependency: Add a new dependency only when manual implementation incurs disproportionate security or complexity risks.

    line 27
  7. Distinctive:

    Avoid scattering code across dozens of micro-files when a cohesive, readable single file suffices.

    line 31
  8. Distinctive:

    Avoid introducing complex state management libraries when localized state or simple prop passing solves the problem.

    line 32
  9. Very specific:

    Leave // TODO: markers only for deliberate, documented technical deferrals with defined constraints.

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Ponytail Lean

This skill establishes a minimal, practical mindset in code implementation: solving problems with the simplest workable solution without speculative abstractions.

Core Tenets

  1. YAGNI (You Aren't Gonna Need It): Do not write code or architectural abstractions for unrequested, hypothetical future requirements.
  2. Standard Library First: Prioritize runtime standard library functions before reaching for third-party packages.
  3. Platform First: Utilize native browser features, semantic HTML5, modern CSS, and database engines before adding custom JavaScript layers.
  4. Avoid Premature Abstraction: Do not build factories, wrapper classes, or generic interfaces for single concrete implementations.

Solution Decision Ladder

Before writing new code or installing a package, evaluate these seven tiers in order:

  1. Relevance: Is this capability explicitly requested or essential for core function? If not, eliminate it.
  2. Reuse: Are there existing helpers, components, or types in the repository that fulfill this?
  3. Standard Library: Can this be solved using runtime built-ins (e.g., fetch, URL, crypto, Intl)?
  4. Platform Capabilities: Can native HTML/CSS features resolve this (e.g., <dialog>, <details>, CSS Grid, Flexbox, native form validation)?
  5. Installed Packages: If an external library is required, use packages already present in package.json.
  6. Concise Custom Code: Write a small, clear function (10-30 lines) focused on the specific task instead of adding a large package.
  7. New External Dependency: Add a new dependency only when manual implementation incurs disproportionate security or complexity risks.

Anti-Overengineering Practices

  • Avoid scattering code across dozens of micro-files when a cohesive, readable single file suffices.
  • Avoid introducing complex state management libraries when localized state or simple prop passing solves the problem.
  • Prioritize code clarity; minimal code does not mean dense one-liners that harm maintainability.
  • Leave // TODO: markers only for deliberate, documented technical deferrals with defined constraints.

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.