Agent Skillsmarmelab/atomic-crm › ponytail-audit

ponytail-audit

GitHub

全仓库代码审计技能,旨在识别过度设计、冗余代码和可简化部分。扫描整个代码库而非仅差异,按优先级列出需删除或简化的内容,提供精简建议,不直接应用修复,生成一次性报告。

.claude/skills/ponytail-audit/SKILL.md marmelab/atomic-crm

Trigger Scenarios

audit this codebase audit for over-engineering what can I delete from this repo find bloat ponytail-audit /ponytail-audit

Install

npx skills add marmelab/atomic-crm --skill ponytail-audit -g -y
More Options

Non-standard path

npx skills add https://github.com/marmelab/atomic-crm/tree/main/.claude/skills/ponytail-audit -g -y

Use without installing

npx skills use marmelab/atomic-crm@ponytail-audit

指定 Agent (Claude Code)

npx skills add marmelab/atomic-crm --skill ponytail-audit -a claude-code -g -y

安装 repo 全部 skill

npx skills add marmelab/atomic-crm --all -g -y

预览 repo 内 skill

npx skills add marmelab/atomic-crm --list

SKILL.md

Frontmatter
{
    "name": "ponytail-audit",
    "description": "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."
}

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-implementation interfaces, factories with one product, wrappers that only delegate, files exporting one thing, dead flags and config, hand-rolled stdlib.

Output

One line per finding, ranked: <tag> <what to cut>. <replacement>. [path]. End with net: -<N> lines, -<M> deps possible. Nothing to cut: Lean already. Ship.

Boundaries

Complexity only, correctness bugs, security holes, and performance go to a normal review pass. Lists findings, applies nothing. One-shot. "stop ponytail-audit" or "normal mode" to revert.

Version History

  • 167a4cd Current 2026-08-20 13:20

Same Skill Collection

.claude/skills/adr-writing/SKILL.md
.claude/skills/backend-dev/SKILL.md
.claude/skills/delete-initial-resource/SKILL.md
.claude/skills/e2e-conventions/SKILL.md
.claude/skills/frontend-dev/SKILL.md
.claude/skills/grill-me/SKILL.md
.claude/skills/playwright-testing/SKILL.md
.claude/skills/ponytail-debt/SKILL.md
.claude/skills/ponytail-help/SKILL.md
.claude/skills/ponytail-review/SKILL.md
.claude/skills/resolving-rollback-conflicts/SKILL.md
.claude/skills/setup-interview/SKILL.md
.claude/skills/shadcn-customization/SKILL.md
.claude/skills/update-branding/SKILL.md
.claude/skills/worktree-detection/SKILL.md
.claude/skills/ponytail/SKILL.md

Metadata

Files
0
Version
167a4cd
Hash
c0f03b6e
Indexed
2026-08-20 13:20

- 위키
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-25 17:44
浙ICP备14020137号-1 $방문자$