repro-first-debugging
78Debug Failures With Reproducible Evidence
Bug fixes based on guesses can miss the cause and introduce regressions. This skill guides reproduction, hypothesis testing, focused fixes, and verification with recorded evidence.
Upgrade Dependencies With Release Note Verification
Dependency upgrades can introduce breaking changes and obscure existing failures. This skill guides focused upgrades through release notes, baseline checks, targeted edits, and verification reports.
将此请求复制给你的智能体,其中包含权威 Skill 页面和清单。
Review the Skillstore skill "dependency-upgrade" from https://skillstore.io/skills/agentkitco-dependency-upgrade.md and its manifest at https://skillstore.io/api/skills/agentkitco-dependency-upgrade/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.你的智能体仍应展示其计划,并按安全策略请求必要确认。
当 AI Agent、爬虫或脚本需要干净上下文,而不是读取完整页面时,请使用这些链接。
正在使用“dependency-upgrade”。 Plan a major-version dependency upgrade before editing.
预期结果:
正在使用“dependency-upgrade”。 Summarize a completed dependency upgrade and its verification.
预期结果:
All five static findings are false positives: Markdown backticks mark routine package queries, code searches, and a rollback report template. Version discovery concerns project dependencies, not system reconnaissance. No evidence found of prompt injection, credential theft, or data exfiltration in SKILL.md.
分享版本化评估报告、中性徽章、嵌入卡片和引用。Skillstore 只报告证据,不判断该 Skill 是否安全。
https://skillstore.io/skills/agentkitco-dependency-upgrade/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/agentkitco-dependency-upgrade?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/agentkitco-dependency-upgrade?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/agentkitco-dependency-upgrade/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/agentkitco-dependency-upgrade.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>agentkitco. (2026). dependency-upgrade security audit report (audit version 1) [Author version 1.0]. Skillstore. https://skillstore.io/skills/agentkitco-dependency-upgrade/audits/1@techreport{agentkitco-agentkitco-dependency-upgrade-2026,
author = {agentkitco},
title = {dependency-upgrade security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/agentkitco-dependency-upgrade/audits/1},
note = {Author version 1.0}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "dependency-upgrade security audit report (audit version 1)"
version: "1.0"
type: report
authors:
- name: "agentkitco"
date-released: "2026-10-17"
url: "https://skillstore.io/skills/agentkitco-dependency-upgrade/audits/1"
identifiers:
- type: other
value: "skillstore:agentkitco-dependency-upgrade:audit:1"
description: "Skillstore immutable audit report identifier"
每位作者的技能都保持为独立的可安装项。推荐变体按 Skillstore 证据排序。
为什么此变体排名第一
agentkitco-dependency-upgrade
2026-10-17
Upgrade one application package, trace changed APIs, and compare verification results with the baseline.
Review major-version migration notes, identify runtime requirements, and plan focused changes with an application smoke check.
Upgrade a dependency and cite security advisories only when confirmed by official advisories or release notes.
Find the installed version of [package] from the lockfile and resolve the latest available version. Report both before making changes.
Plan an upgrade of [package] from [current] to [target]. Review intermediate release notes, link breaking changes, and list affected files before editing.
Upgrade [package] to [target]. Record baseline checks, update through the package manager, apply required migrations, and compare verification results. Ask before runtime changes.
Upgrade [package] to [target] with required peers only. Show transitive conflicts and options without overrides. Request approval for runtime or peer version increases.
作者
agentkitco许可证
MIT
作者版本
v1.0
Skillstore 修订
r1
版本提示
作者声明的版本不符合 SemVer 规范。
引用
743429f75b17204d47661a86b577a575ad67517f
维护新鲜度
2026/10/17
使用量
0 次下载 · 0 次浏览
文件结构
📄 SKILL.md
Debug Failures With Reproducible Evidence
Bug fixes based on guesses can miss the cause and introduce regressions. This skill guides reproduction, hypothesis testing, focused fixes, and verification with recorded evidence.
Verify Tests Ran Before Reporting Completion
Completion claims can hide skipped tests, stale results, or checks that never exercised a change. This skill guides fresh verification and reports evidence for each claim.
Write Pull Request Descriptions From Real Changes
Reviewers need clear explanations of changes, testing, and risk. This skill turns Git diffs and commits into structured pull request descriptions grounded in available evidence.
Preserve Progress Across Agent Sessions
Long sessions and agent changes can lose important project context. This skill creates a concise handoff with verified state, decisions, and ordered next steps.
Review Code Changes for Security Risks
Security defects can hide in small changes to input handling, authentication, and configuration. This skill guides scoped code triage with evidence, realistic severity, and actionable fixes.
Review Your Git Changes Before a Pull Request
Unreviewed changes can hide correctness, security, and compatibility problems. This skill guides an evidence-based review with prioritized findings and clearly reported validation results.
构建可靠的测试自动化
由 89jobrien
薄弱的测试会拖慢发布并掩盖回归问题。此技能可指导测试策略、TDD、自动化、覆盖率审查以及 Playwright Web 检查。
审查代码的安全性和质量
由 AutumnsGrove
手动代码审查可能会遗漏安全、性能和测试问题。此技能为 Claude、Codex 和 Claude Code 提供带有检查清单和辅助扫描指导的结构化审查工作流。
在整个代码库中规划可靠测试
由 0xDarkMatter
此技能帮助团队选择测试策略、mocks、数据 fixtures、覆盖率门禁和 CI 模式,同时避免混淆测试范围。它为 Claude、Codex 和 Claude Code 提供针对单元、集成、端到端、TDD 和流水线测试的结构化指导。
系统化调试软件问题
由 Asmayaseen
无结构的错误修复会浪费时间,并可能掩盖真正的故障。此技能会引导 Claude、Codex 和 Claude Code 进行基于证据的根因分析。
构建更好的 Go 测试
由 89jobrien
Go 团队需要在单元测试、集成测试、mock、基准测试和覆盖率方面保持一致的测试实践。此 skill 提供实用的 Go 测试模式,Claude、Codex 和 Claude Code 可在开发过程中应用这些模式。
强制执行瀑布式阶段门
由 Chemiseblanc
AI 编码会话在压力上升时可能会跳过需求、设计或测试。此技能通过文档化的关卡,将工作保持在严格的瀑布式流程内。