testing
85建構可靠的測試自動化
薄弱的測試會拖慢發布並掩蓋回歸問題。此技能可引導測試策略、TDD、自動化、覆蓋率審查,以及 Playwright 網頁檢查。
清理 AI 生成的程式碼
AI 編碼工作階段可能會留下冗餘註解、防禦性檢查、型別轉換,以及不一致的風格。此技能會引導聚焦式清理,在保留行為的同時驗證變更。
將此請求複製給你的智慧代理,其中包含權威 Skill 頁面和清單。
Review the Skillstore skill "ai-code-cleanup" from https://skillstore.io/skills/89jobrien-ai-code-cleanup.md and its manifest at https://skillstore.io/api/skills/89jobrien-ai-code-cleanup/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.你的智慧代理仍應顯示其計畫,並依安全政策請求必要確認。
當 AI Agent、爬蟲或腳本需要乾淨脈絡、而不是讀取完整頁面時,請使用這些連結。
正在使用「ai-code-cleanup」。 Remove unnecessary comments from an authentication utility.
預期結果:
正在使用「ai-code-cleanup」。 Clean defensive bloat from a user API helper.
預期結果:
正在使用「ai-code-cleanup」。 Prepare an AI-generated pull request for review.
預期結果:
The static findings are false positives caused by Markdown fences, inline code examples, a read-only Git diff example, and regex syntax. I found no prompt injection, data exfiltration intent, network activity, credential access, or malicious command execution in the reviewed skill files.
分享版本化評估報告、中性徽章、嵌入卡片與引用。Skillstore 只報告證據,不判斷該 Skill 是否安全。
https://skillstore.io/skills/89jobrien-ai-code-cleanup/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/89jobrien-ai-code-cleanup?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/89jobrien-ai-code-cleanup?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/89jobrien-ai-code-cleanup/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/89jobrien-ai-code-cleanup.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Joseph OBrien. (2026). ai-code-cleanup security audit report (audit version 7) [Author version 1.0.1]. Skillstore. https://skillstore.io/skills/89jobrien-ai-code-cleanup/audits/7@techreport{joseph-obrien-89jobrien-ai-code-cleanup-2026,
author = {Joseph OBrien},
title = {ai-code-cleanup security audit report (audit version 7)},
institution = {Skillstore},
year = {2026},
number = {7},
url = {https://skillstore.io/skills/89jobrien-ai-code-cleanup/audits/7},
note = {Author version 1.0.1}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "ai-code-cleanup security audit report (audit version 7)"
version: "1.0.1"
type: report
authors:
- name: "Joseph OBrien"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/89jobrien-ai-code-cleanup/audits/7"
identifiers:
- type: other
value: "skillstore:89jobrien-ai-code-cleanup:audit:7"
description: "Skillstore immutable audit report identifier"
在開啟 pull request 前,審查已變更檔案中的冗餘註解、型別變通做法,以及防禦性膨脹。
清理風格漂移與明顯的生成痕跡,讓審查者能專注於行為與架構。
在合併到主分支前,將專案清理規則套用到不同助理產生的程式碼。
Review this branch for AI-generated code artifacts. Remove redundant comments, unnecessary defensive checks, type workarounds, and style inconsistencies. Preserve behavior and tell me what changed.
Clean the files I changed in src/. Match the existing project style, keep useful comments, and remove only code that does not affect behavior. Run available checks when finished.
Compare this branch with main and identify AI-generated artifacts in the changed files. Make small cleanup edits, list removed patterns, and confirm the tests or checks you ran.
Create a cleanup plan for generated code in this module before editing. Separate safe removals from changes that need tests or reviewer approval. Then apply only the safe edits first.
授權
MIT
作者版本
v1.0.1
Skillstore 修訂
r1
引用
c4037264bbd363c572662d6154a3ab28f5ca4f53
維護新鮮度
2026/7/18
使用量
27 次下載 · 261 次瀏覽
檔案結構
建構可靠的測試自動化
薄弱的測試會拖慢發布並掩蓋回歸問題。此技能可引導測試策略、TDD、自動化、覆蓋率審查,以及 Playwright 網頁檢查。
偵錯錯誤與根本原因
當證據分散在日誌、堆疊追蹤與服務之間時,錯誤和事件很難分流判斷。此技能會結構化診斷流程、解析日誌、識別模式,並引導最小修復。
更快找到程式碼脈絡
開發人員經常耗費時間追查程式碼為何存在,以及有哪些內容依賴它。這個技能會提示 Claude、Codex 或 Claude Code 在變更前收集相關圖譜知識、呼叫者、匯入項目和測試。
建立有效的 AI 技能
在結構、資源和驗證規則不清楚時,建立可重複使用的 AI 技能並不容易。此技能提供一套實用工作流程,用於設計、撰寫、驗證與封裝技能。
管理依賴項更新與稽核
依賴項更新可能隱藏弱點、授權問題和破壞性變更。此技能可引導你在常見套件管理員中進行稽核、安全升級和報告。
稽核網站無障礙以符合 WCAG 規範
無障礙缺口可能阻礙使用者並造成合規風險。此技能可引導 WCAG 稽核、螢幕閱讀器檢查、鍵盤測試與修復規劃。
Audit NestJS Code with Evidence-Backed Findings
由 amirtaherkhani
NestJS repositories can hide boundary flaws and runtime risks that lint results alone cannot reveal. This skill combines local evidence collection and semantic review into one prioritized report.
Review Defects and Verify Root-Cause Repairs
由 aakashh242
Reviews can miss failure conditions or accept fixes without reliable evidence. Gauntlet guides scoped adversarial reviews, authorized repairs, and revision-bound verification within a finite budget.
分析程式碼模式與架構
由 C0ntr0lledCha0s
大型程式碼庫隱藏著重複結構與不明確的架構選擇。此技能會找出模式、說明其意圖,並突顯實用的重構機會。
提升 Playwright 測試覆蓋率
由 C0ntr0lledCha0s
當設定、定位器和 fixtures 不一致時,Playwright 測試套件可能會變得不穩定。此技能提供可靠瀏覽器測試、除錯和可重用 page objects 的實用模式。
依 AST 結構搜尋程式碼
由 0xDarkMatter
文字搜尋會遺漏語意關係,並產生大量雜訊結果。此技能使用 ast-grep 模式定位程式碼結構,並為聚焦式重構做好準備。
使用結構化品質檢查審查程式碼
由 alirezarezvani
程式碼審查可能會遺漏品質、安全性與可維護性問題。此技能會透過腳本、檢查清單與報告產生流程,引導進行結構化審查。