메뉴
Quick-reference card for all ponytail modes, skills, and commands in Cursor. One-shot display, not a persistent mode. Trigger: @ponytail-help, "ponytail help", "what ponytail commands", "how do I use ponytail".
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Guide proper usage of Editor UI infrastructure including Drawers (ButtonDrawer, ModalDrawer, TableDrawer, etc.), Elements (drag-drop targets, ComponentSelector), FieldEditors, and EditorUIConstants. Use when implementing editor panels, component editors, or any ImGui UI code to ensure consistency and code reuse.
Use before complex creative work — new features, multi-component systems, or behavior changes with real design trade-offs. Explores user intent, requirements and design before implementation. DO NOT use for non-complex tasks (bug fixes, small tweaks, single-file changes, obvious one-path work) — that is overkill.
Whole-repo audit for over-engineering. Like ponytail-review, but scans the entire codebase instead of a diff: a ranked list of what to delete, simplify, or replace with stdlib/native equivalents. Use when the user says "audit this codebase", "audit for over-engineering", "what can I delete from this repo", "find bloat", "ponytail-audit", or @ponytail-audit. One-shot report; does not apply fixes.
Harvest every `ponytail:` comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals ponytail leaves behind get tracked instead of rotting into "later means never". Use when the user says "ponytail debt", @ponytail-debt, "what did ponytail defer", "list the shortcuts", "ponytail ledger", or "what did we mark to do later". One-shot report; changes nothing.
Show ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display, not a persistent mode, and not a per-repo number. Trigger: @ponytail-gain, "ponytail gain", "what does ponytail save", "show ponytail impact", "ponytail scoreboard".
Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "what can we delete", "is this over-engineered", "simplify review", or invokes @ponytail-review. Complements correctness-focused review; this one only hunts complexity.
| name | ponytail-help |
| description | Quick-reference card for all ponytail modes, skills, and commands in Cursor. One-shot display, not a persistent mode. Trigger: @ponytail-help, "ponytail help", "what ponytail commands", "how do I use ponytail". |
| disable-model-invocation | true |
Display this reference card when invoked. One-shot — do NOT change mode, write flag files, or persist anything.
| Level | How to trigger (Cursor) | What changes |
|---|---|---|
| Lite | Say "ponytail lite" or "@ponytail lite" | Build what's asked; name the lazier alternative in one line. |
| Full | Say "@ponytail" or enable via user rule | The ladder enforced: YAGNI → stdlib → native → one line → minimum. Default. |
| Ultra | Say "ponytail ultra" or "@ponytail ultra" | YAGNI extremist. Deletion before addition. Challenges requirements before building. |
Level sticks for the rest of the chat unless you say otherwise.
| Skill | Cursor trigger | What it does |
|---|---|---|
| ponytail | @ponytail or natural language ("be lazy", "yagni") | Lazy mode itself. Simplest solution that works. |
| ponytail-review | @ponytail-review | Over-engineering review: L42: yagni: factory, one product. Inline. |
| ponytail-audit | @ponytail-audit | Whole-repo over-engineering audit: ranked list of what to delete. |
| ponytail-debt | @ponytail-debt | Harvest ponytail: shortcut comments into a tracked ledger. |
| ponytail-gain | @ponytail-gain | Measured-impact scoreboard: less code, less cost, more speed. |
| ponytail-help | @ponytail-help | This card. |
Type @ in chat and pick a skill, or describe what you want — the agent
matches from each skill's description.
For every session without typing @ponytail, add a Cursor user rule with
the ponytail ladder (or copy the core rules from ponytail/SKILL.md). User
rules apply across chats; skills load per invocation or when auto-matched.
Say "stop ponytail" or "normal mode". Resume with @ponytail or your user
rule.
Project skills: .claude/skills/ponytail*/SKILL.md (this repo) or
.cursor/skills/ponytail*/SKILL.md. Personal skills: ~/.cursor/skills/.
Full docs + examples: https://github.com/DietrichGebert/ponytail
