AgentSkillsCN

task-analyzer

当用户提出“分析这项任务”、“判断任务复杂度”、“为任务选择技能”、“估算工作规模”,或需要元认知任务分析的指导时,可使用此技能。返回带有置信度评分与元数据的技能。

SKILL.md
--- frontmatter
name: task-analyzer
description: This skill should be used when the user asks to "analyze this task", "determine task complexity", "select skills for task", "estimate work scale", or needs guidance on metacognitive task analysis. Returns skills with confidence scores and metadata.

Task Analyzer

Provides metacognitive task analysis and skill selection guidance.

Skills Index

Skills Index Reference

Load skills metadata from the project-local skills-index.yaml for tag-based matching. Use the tags field to match against task keywords and the typical_use field to validate relevance.

The skills-index.yaml is a project-local file maintained by the /sync-skills command at .claude/skills/task-analyzer/references/skills-index.yaml. It is NOT inside the plugin — each project maintains its own copy.

A default template is bundled with the plugin at skills-index.yaml as a starting point. Run /sync-skills to generate or update the local version.

Task Analysis Process

1. Understand Task Essence

Identify the fundamental purpose beyond surface-level work:

Surface WorkFundamental Purpose
"Fix this bug"Problem solving, root cause analysis
"Implement this feature"Feature addition, value delivery
"Refactor this code"Quality improvement, maintainability
"Update this file"Change management, consistency

Key Questions:

  • What problem are we really solving?
  • What is the expected outcome?
  • What could go wrong if we approach this superficially?

2. Estimate Task Scale

ScaleFile CountIndicators
Small1-2Single function/component change
Medium3-5Multiple related components
Large6+Cross-cutting concerns, architecture impact

Scale affects skill priority:

  • Larger scale → process/documentation skills more important
  • Smaller scale → implementation skills more focused

3. Identify Task Type

TypeCharacteristicsKey Skills
ImplementationNew code, featurescoding-principles, testing-principles
FixBug resolutionai-development-guide, testing-principles
RefactoringStructure improvementcoding-principles, ai-development-guide
DesignArchitecture decisionsdocumentation-criteria, implementation-approach
QualityTesting, reviewtesting-principles, integration-e2e-testing

4. Tag-Based Skill Matching

Extract relevant tags from task description and match against the project-local skills-index.yaml:

yaml
Task: "Implement user authentication with tests"
Extracted tags: [implementation, testing, security]
Matched skills:
  - coding-principles (implementation, security)
  - testing-principles (testing)
  - ai-development-guide (implementation)

5. Implicit Relationships

Consider hidden dependencies:

Task InvolvesAlso Include
Error handlingdebugging, testing
New featuresdesign, implementation, documentation
Performanceprofiling, optimization, testing
Frontendtypescript-rules, typescript-testing
API/Integrationintegration-e2e-testing

Output Format

Return structured analysis with skill metadata from the project-local skills-index.yaml:

yaml
taskAnalysis:
  essence: <string>  # Fundamental purpose identified
  type: <implementation|fix|refactoring|design|quality>
  scale: <small|medium|large>
  estimatedFiles: <number>
  tags: [<string>, ...]  # Extracted from task description

selectedSkills:
  - skill: <skill-name>  # From skills-index.yaml
    priority: <high|medium|low>
    reason: <string>  # Why this skill was selected
    # Pass through metadata from skills-index.yaml
    tags: [...]
    typical-use: <string>
    size: <small|medium|large>
    sections: [...]  # All sections from yaml, unfiltered

Note: Section selection (choosing which sections are relevant) is done after reading the actual SKILL.md files.

Skill Selection Priority

  1. Essential - Directly related to task type
  2. Quality - Testing and quality assurance
  3. Process - Workflow and documentation
  4. Supplementary - Reference and best practices

Metacognitive Question Design

Generate 3-5 questions according to task nature:

Task TypeQuestion Focus
ImplementationDesign validity, edge cases, performance
FixRoot cause (5 Whys), impact scope, regression testing
RefactoringCurrent problems, target state, phased plan
DesignRequirement clarity, future extensibility, trade-offs

Warning Patterns

Detect and flag these patterns:

PatternWarningMitigation
Large change at onceHigh riskSplit into phases
Implementation without testsQuality riskFollow TDD
Immediate fix on errorRoot cause missedPause, analyze
Coding without planScope creepPlan first