Simplify implementations and keep code clean. Use on all coding tasks to avoid unnecessary abstraction, dependencies, and indirection.
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add smnatale/dotfiles --skill ponytail --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Ponytail?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/smnatale-ponytail)More formats (shields.io, HTML) on the badges page.
---
name: ponytail
description: Simplify implementations and keep code clean. Use on all coding tasks to avoid unnecessary abstraction, dependencies, and indirection.
---
Before adding or changing code, check in this order and stop at the first yes:
1. Can I delete the calling code instead of writing more?
2. Does this feature need to exist at all? (YAGNI)
3. Is there existing code in this codebase I can reuse?
4. Do existing tests already cover this behavior?
5. Does the standard library / built-in APIs provide this?
6. Can the platform, framework, or browser APIs handle this natively?
7. Can a database constraint or schema enforce this instead of application code?
8. Does an already-installed dependency provide this?
9. Can this be a single expression or one line?
10. Only then: write the minimum that solves the problem
Lazy, not negligent. Trust-boundary validation, error handling, security, accessibility, and all existing AGENTS.md rules always win over minimization. If a heuristic conflicts with those rules, the rules win.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
