skills.rest
tomw200082-collab
tomw200082-collabCOMMUNITY
Explore all skills by this author →
GitHub

ponytail-gain

Displays a one-shot ASCII scoreboard of benchmark-measured code, cost, and speed reductions.

Updated May 8, 2026
Search Tags:#benchmark#performance metrics#cost savings#scoreboard#code reduction#ascii chart
One-click install
npx skills add https://github.com/tomw200082-collab/gt-factory-os-production-brain --skill ponytail-gain-tomw200082-collab
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ponytail-gain
Source: https://github.com/tomw200082-collab/gt-factory-os-production-brain/tree/main/.claude/skills/ponytail-gain
Command: npx skills add https://github.com/tomw200082-collab/gt-factory-os-production-brain --skill ponytail-gain-tomw200082-collab

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Users evaluating the ponytail approach lack a quick, honest summary of its measured impact, and risk confusing benchmark medians with per-repo savings. ## Core Features & Use Cases - Benchmark Scoreboard: Renders plain ASCII bars showing measured medians for lines of code (80-94% less), cost (47-77% less), and speed (3-6x faster) across 5 tasks and 3 models. - Honesty Boundary: Refuses to invent per-repo savings numbers and instead points to /ponytail-debt and /ponytail-audit for real counted figures. - One-Shot Display: Changes no mode, writes no files, and persists nothing; use it when someone asks "what does ponytail save" or "show ponytail impact". ## Quick Start Ask the assistant to show the ponytail gain scoreboard to see the benchmark median savings for code, cost, and speed.

Frequently Asked Questions about ponytail-gain

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I see what ponytail saves on code and cost?▼

Invoke /ponytail-gain or ask "what does ponytail save" to render a one-shot ASCII scoreboard. It shows benchmark medians: 80-94% fewer lines of code, 47-77% lower cost, and 3-6x faster speed across 5 tasks and 3 models.

What tasks and models are the ponytail benchmarks based on?▼

The figures are medians from 5 everyday tasks (email validator, debounce, CSV sum, countdown timer, rate limiter) run across three models: Haiku, Sonnet, and Opus. The source data lives in the benchmarks directory and README.

Can ponytail-gain show savings for my specific repository?▼

No, it deliberately refuses to print per-repo savings because the unbuilt baseline version was never written, so no real subtraction is possible. For real per-repo figures, use /ponytail-debt for a counted ledger or /ponytail-audit for remaining cuttable code.

Does the ponytail scoreboard change modes or write files?▼

No, it is a strictly one-shot display that edits nothing, changes no mode, and writes no flag files. Saying "stop ponytail" or "normal mode" reverts any related mode separately.

Why does ponytail-gain refuse to estimate lines saved in my repo?▼

Because there is no real baseline to subtract from in a live repo, any per-repo number would be invented. The skill enforces an honesty boundary and redirects to counted tools instead of fabricating figures.

Related Skills

Explore More Software Engineering Skills→
epicodicepicodic

ponytail-gain

Displays a one-shot ASCII scoreboard of ponytail's benchmarked code, cost, and speed reductions.

Community
Basic
Xipher-LabsXipher-Labs
6

track-pending

Write deferred work entries into walter-pending.md with frontmatter metadata and TP IDs.

Official
Basic
zeyxxzeyxx

stats

Display real-time telemetry dashboards for CYNIC usage, latency, and system metrics.

Community
Intermediate
FlorianBruniauxFlorianBruniaux
5.7k

rtk-optimizer

Wrap high-verbosity commands with RTK to reduce token usage.

Community
Advanced