Skip to content
Content
Skill

/ponytail-dev

Use to implement or review software with minimal code and proportional checks.

BOOST
From plugin
claude-skills-journalism
43272 skills1 agent22 commands1 hook
Install
$ npx -y skills add jamditis/claude-skills-journalism --skill ponytail-dev --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/ponytail-dev

Context preview

The summary Claude sees to decide when to auto-load this skill.

Use to implement or review software with minimal code and proportional checks.

SKILL.md

ponytail-dev.SKILL.md
name: ponytail-dev
description: Use to implement or review software with minimal code and proportional checks.
license: MIT

Ponytail dev

Use this skill for software implementation, fixes, refactoring, infrastructure, tests, and technical review. In mixed work, treat the approved design as fixed input and apply this skill only to implementation.

Do not make or simplify visual, UX, interaction, brand, or editorial design decisions. Do not reduce design quality to save code.

Understand the affected flow before choosing a change. Prefer an existing pattern, the standard library, native platform features, or an installed dependency. Add only the code that the current requirement needs. Avoid speculative abstractions, compatibility layers, configuration, and extension points.

For a bug, find the root cause and inspect relevant callers. Fix a shared cause when the evidence supports that scope.

Verification

Use the smallest evidence that proves the result. Prefer an existing relevant test, focused command, build, type check, linter, temporary probe, or direct behavior check. Run broader checks when the changed scope, risk, repository rules, or CI behavior requires them.

Add a persistent test when it protects a likely repeat failure, stable public contract, non-obvious logic, or high-impact behavior. Static and trivial edits usually need direct inspection only.

Boundaries

Do not simplify away security controls, trust-boundary validation, data-loss protection, required error handling, accessibility, or an explicit requirement. Match the proof to the impact, uncertainty, and recovery cost.

Keep the handoff short. State the change, the evidence, and any known limit that affects the user's decision.

Related skills: `vibe-coding` (dev-toolkit) covers broader AI-assisted development, and `verification-before-completion` (superjawn) covers final proof before a completion claim.

Credit: Adapted from [DietrichGebert/ponytail](https://github.com/DietrichGebert/ponytail) under the MIT license.

Read more
Ships withclaude-skills-journalism

A collection of Agent Skills for journalists, researchers, academics, media professionals, and communications practitioners. The same repository serves Claude Code and Codex while keeping Claude-only commands, agents, and hooks clearly labeled.

Get the whole plugin

Other skills on claude-skills-journalism.