ponytail-audit
The ponytail-audit skill performs a repository-wide scan to identify over-engineering, bloat, and opportunities for simplification. It generates a ranked report suggesting code to delete, replace with standard library functions, or replace with native platform features.
Is ponytail-audit safe to install?
Safe to install: our audit of ponytail-audit's source files found 0 shell commands, 0 external URLs, no file writes (none risk). Every command and URL listed appears verbatim in the skill's source. The skill performs text analysis on the codebase and generates a report. It does not execute shell commands, make network requests, or modify files.
How we audit skills: our security review methodology.
Who is this skill for?
Developers and maintainers seeking to reduce codebase complexity and remove unnecessary abstractions.
What can you do with it?
- Identify dead code and unused features for deletion.
- Replace custom implementations with standard library equivalents.
- Replace third-party dependencies with native platform features.
- Simplify abstractions, single-implementation interfaces, and redundant wrappers.
- Generate a summary of potential line count and dependency reductions.
How good is this skill?
Quality score: 5/10. The skill documentation clearly defines its scope, output format, and triggers. It explicitly states that it does not perform destructive actions.
What does the skill file contain?
ponytail-review, repo-wide. Scan the whole tree instead of a diff. Rank findings biggest cut first. ## Tags Same as ponytail-review: - `delete:` dead code, unused flexibility, speculative feature. Replacement: nothing. - `stdlib:` hand-rolled thing the standard library ships. Name the function. - `native:` dependency or code doing what the platform already does. Name the feature. - `yagni:` abstraction with one implementation, config nobody sets, layer with one caller. - `shrink:` same logic, fewer lines. Show the shorter form. ## Hunt Deps the stdlib or platform already ships, single-imp...
Frequently asked questions
Does this skill automatically apply the suggested changes?
No. The skill generates a one-shot report and does not apply any fixes to the codebase.
Does the skill check for security vulnerabilities or performance issues?
No. The skill focuses exclusively on over-engineering and complexity. It routes security and performance concerns to other review processes.
What triggers the audit?
The skill triggers when a user requests an audit for over-engineering, asks what to delete, or uses the commands ponytail-audit or /ponytail-audit.
Related skills
improve
16.9KDevelopers and teams who want to audit their codebase for bugs, security, performance, or technical debt and require structured, actionable implementation plans for other AI agents to execute
The improve skill acts as a senior advisor that audits codebases to identify improvement opportunities and generates self-contained implementation plans for other agents to execute. It performs read-only analysis, including recon, auditing, and plan creation, while strictly avoiding direct code modification.
swift-concurrency
13.2KSwift developers managing concurrency issues, refactoring callback-based code, or migrating projects to Swift 6
The swift-concurrency skill provides diagnostic and refactoring guidance for Swift Concurrency, including migration to Swift 6, actor isolation, Sendable conformance, and task management.
simplify
10.5KSoftware engineers who want to automate code cleanup and enforce project-specific coding standards
The simplify skill refines recently modified code to improve clarity, consistency, and maintainability while preserving original functionality.
ponytail
9.8KDevelopers seeking to reduce code bloat, eliminate unnecessary boilerplate, and enforce a minimalist approach to software engineering
Ponytail acts as a senior developer persona that enforces minimal, efficient coding practices by prioritizing standard libraries, native platform features, and YAGNI principles over custom abstractions or dependencies.