跳到正文
cccskills
免费在 GitHub 公开

dependency-analyzer

Analyzes project dependencies, detects outdated packages, identifies breaking changes, and suggests safe update strategies. Helps maintain dependency health and security.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(10)

  • SKILL.md5.8 KB
  • commands/dependency-analyzer.md119 B
  • hooks/post-execute.cjs316 B
  • hooks/pre-execute.cjs433 B
  • references/research-requirements.md459 B
  • rules/dependency-analyzer.md462 B
  • schemas/input.schema.json644 B
  • schemas/output.schema.json263 B
  • scripts/main.cjs1.2 KB
  • templates/implementation-template.md193 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Dependency Analyzer Skill

<identity> Dependency Analyzer Skill - Analyzes project dependencies, detects outdated packages, identifies breaking changes, and suggests safe update strategies. </identity> <capabilities> - Analyzing dependency health - Planning dependency updates - Detecting security vulnerabilities - Identifying breaking changes - Validating compatibility </capabilities> <instructions> <execution_process>

Step 1: Identify Dependency Files

Locate dependency files:

  • package.json (Node.js)
  • requirements.txt (Python)
  • go.mod (Go)
  • Cargo.toml (Rust)
  • pom.xml (Java/Maven)

Step 2: Analyze Dependencies

Examine dependencies:

  • Read dependency files
  • Check versions
  • Identify outdated packages
  • Note version constraints

Step 3: Semantic Versioning Analysis

Analyze version numbers using semantic versioning (semver):

  1. Parse version numbers:

    • Extract major.minor.patch from version strings
    • Handle version ranges (^, ~, >=, etc.)
    • Identify exact vs range versions
  2. Detect major version bumps:

    • Compare current version with latest available
    • Identify major version changes (e.g., 1.x.x -> 2.x.x)
    • Flag major updates as potentially breaking
  3. Check changelogs for breaking changes:

    • For major version updates: Trigger web search (Exa/WebFetch) to research breaking changes
    • Look for "BREAKING CHANGE" markers in changelogs
    • Check migration guides
    • Review release notes for breaking changes
    • Document specific breaking changes found
  4. Semantic Versioning Rules:

    • Major version (X.0.0): Breaking changes likely, requires code changes
    • Minor version (0.X.0): New features, backward compatible
    • Patch version (0.0.X): Bug fixes, backward compatible
  5. Breaking Change Detection:

    • Parse changelog entries for breaking change indicators
    • Identify deprecated APIs
    • Check for removed features
    • Document migration requirements
    • Generate breaking change report

Step 4: Check for Updates

Check available updates:

  • Query package registries
  • Compare current vs latest versions
  • Identify major/minor/patch updates
  • Apply semantic versioning analysis
  • Warn about breaking changes

Step 5: Security Audit

Check for vulnerabilities:

  • Scan for known vulnerabilities
  • Check security advisories
  • Identify high-risk packages
  • Suggest security updates

Step 6: Generate Report

Create dependency report:

  • List outdated packages
  • Identify breaking changes
  • Suggest update strategy
  • Provide migration guidance </execution_process>
<integration> **Integration with DevOps Agent**: - Manages dependency updates - Implements update strategies - Validates compatibility

Integration with Security Architect Agent:

  • Reviews security vulnerabilities
  • Validates security updates
  • Ensures compliance </integration>

<best_practices>

  1. Regular Analysis: Analyze dependencies regularly
  2. Security First: Prioritize security updates
  3. Test Updates: Always test after updates
  4. Gradual Updates: Update incrementally
  5. Document Changes: Track update decisions </best_practices> </instructions>
<examples> <formatting_example> **Dependency Health Report**
# Dependency Health Report

## Summary

- Total Dependencies: 45
- Outdated: 12
- Vulnerable: 3
- Up to Date: 30

## Outdated Packages

- react: 18.0.0 -> 18.2.0 (minor update)
- next: 13.4.0 -> 14.0.0 (major update - breaking changes)
- typescript: 5.0.0 -> 5.3.0 (patch update)

## Security Vulnerabilities

- lodash: 4.17.20 (CVE-2021-23337) - Update to 4.17.21
- axios: 0.21.1 (CVE-2021-3749) - Update to 1.6.0

## Update Recommendations

1. Update patch versions (safe)
2. Review minor updates (low risk)
3. Plan major updates (breaking changes)

</formatting_example>

<formatting_example> Update Plan

# Dependency Update Plan

## Phase 1: Patch Updates (Safe)

- Update lodash: 4.17.20 -> 4.17.21
- Update typescript: 5.0.0 -> 5.3.0

## Phase 2: Minor Updates (Low Risk)

- Update react: 18.0.0 -> 18.2.0
- Update @types/node: 20.0.0 -> 20.10.0

## Phase 3: Major Updates (Breaking Changes)

- Update next: 13.4.0 -> 14.0.0
  - Breaking changes: [List]
  - Migration steps: [Steps]
  - Testing required: [Tests]

</formatting_example> </examples>

<examples> <usage_example> **Example Commands**:
# Analyze dependencies
Analyze dependencies for this project

# Check for updates
Check for dependency updates

# Security audit
Perform security audit of dependencies

# Generate update plan
Generate update plan for major version updates

</usage_example> </examples>

Rules

  • Always check for security vulnerabilities first
  • Research breaking changes before major updates
  • Test thoroughly after any dependency update

Memory Protocol (MANDATORY)

Before starting:

cat .claude/context/memory/learnings.md

After completing:

  • New pattern -> .claude/context/memory/learnings.md
  • Issue found -> .claude/context/memory/issues.md
  • Decision made -> .claude/context/memory/decisions.md

ASSUME INTERRUPTION: Your context may reset. If it's not in memory, it didn't happen.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio432026年7月14日 更新

Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio432026年7月14日 更新

N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio432026年7月14日 更新

Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio432026年7月14日 更新

Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio432026年7月14日 更新

LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio432026年7月14日 更新

查看 oimiragieo 的全部技能

报告此技能的问题