agentleFS
dss-timedss-time/repo-doctor-skills/skills/dependency-upgrade-analysis/SKILL.md

dependency-upgrade-analysis

Skill1 starsChanged 4 months agoMITView on GitHub

Explicit-invocation analysis of one defined dependency upgrade using manifests, lockfiles, repository usage, and verified official release evidence, covering compatibility, security, licensing, validation, and rollback. Do not trigger for ordinary code changes or modify manifests or lockfiles. 仅显式调用:基于 manifest、锁文件、仓库用法和已验证官方发布资料分析一个已定义的依赖升级,覆盖兼容、安全、许可证、验证和回滚。不得因普通代码变更而触发,也不修改 manifest 或锁文件。

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Default to standard; explicit invocation is required.

    line 10
  2. Distinctive:

    Use network sources only when allowed and necessary.

    line 22
  3. Distinctive:

    Never invent release notes, vulnerabilities, licenses, or compatibility claims.

    line 23

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

English

Execution Contract

Default to standard; explicit invocation is required. Complete one primary task by default. Continue an authorized end-to-end workflow within each Skill's permissions; Router remains recommendation-only. Pause for new material decisions or scope, not authorization already given. For a human-only blocker, give location, action, success signal and resume step; never request secret values or assume completion. Validate according to actual risk; security, production, migrations, releases and other high-risk work use audit. Read references/execution-modes.en.md only when mode selection is unclear.

Dependency Upgrade Analysis

Analyze one defined dependency upgrade. Keep manifests, lockfiles, code, configuration, and CI unchanged.

Boundary

  • Route broad change impact to change-impact-analysis and implementation to safe-fix-implementation.
  • Identify current and target versions, direct versus transitive status, package manager, manifests, lockfiles, runtime, compiler, and platform constraints.
  • Use network sources only when allowed and necessary; prefer official documentation, release notes, advisories, standards, and original sources. Record URL and access date. Mark unavailable evidence unverified.
  • Never invent release notes, vulnerabilities, licenses, or compatibility claims.

Workflow

  1. Establish the upgrade target and repository evidence for current resolution and usage.
  2. Map imported APIs, plugins, peers, build tools, generated code, configuration, deployment, and transitive dependencies.
  3. Compare breaking changes, API behavior, runtime/compiler requirements, security advisories, license changes, and ecosystem compatibility.
  4. Classify each claim as repository evidence, verified official evidence, inference, or unknown.
  5. Assess build, test, configuration, deployment, and rollback impact.
  6. Recommend staged upgrade, focused validation, compatibility controls, rollback point, and stop conditions without editing files.

Output Contract

  1. Scope and versions
  2. Evidence and sources with access dates
  3. Direct, transitive, and usage map
  4. Findings with severity, impact, confidence, and change class
  5. Runtime, API, security, license, and ecosystem risks
  6. Staged recommendation, validation, and rollback
  7. Unknowns

简体中文

执行契约

默认使用 standard;仅允许用户显式调用。 默认完成一个主任务。用户已授权完整流程时,在各 Skill 权限内连续完成;Router 仍只推荐。新重大决策或超出授权时暂停,不重复索取已有授权。 必须由用户完成的阻塞步骤:给出操作位置、具体动作、成功标志、恢复步骤;不要求粘贴秘密值,不代替用户确认完成。 按实际风险选择验证;安全、生产、迁移、发布等高风险工作使用 audit。模式不明确时才读取 references/execution-modes.zh-CN.md。

依赖升级分析

分析一个明确的依赖升级,保持 manifest、锁文件、代码、配置和 CI 不变。

职责边界

  • 广泛影响交给 change-impact-analysis,实施交给 safe-fix-implementation。
  • 识别当前与目标版本、直接/间接依赖、包管理器、manifest、锁文件、运行时、编译器和平台约束。
  • 仅在允许且必要时联网;优先官方文档、发布说明、安全公告、标准和原始资料,记录 URL 与访问日期。无法访问时标为未验证。
  • 不得编造发布说明、漏洞、许可证或兼容性结论。

工作流程

  1. 明确升级目标及当前解析版本和用法的仓库证据。
  2. 映射导入 API、插件、peer、构建工具、生成代码、配置、部署和间接依赖。
  3. 比较破坏性变更、API 行为、运行时/编译器要求、安全公告、许可证变化和生态兼容性。
  4. 将主张分类为仓库证据、已验证官方证据、推断或未知。
  5. 评估构建、测试、配置、部署和回滚影响。
  6. 不修改文件,给出分阶段升级、聚焦验证、兼容控制、回滚点和停止条件。

输出契约

  1. 范围与版本
  2. 证据及来源和访问日期
  3. 直接、间接依赖与用法映射
  4. 发现、严重度、影响、置信度和变更类型
  5. 运行时、API、安全、许可证和生态风险
  6. 分阶段建议、验证和回滚
  7. 未知项

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.