recipe-task

Execute tasks following appropriate rules with rule-advisor metacognition

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "recipe-task" with this command: npx skills add shinpr/claude-code-workflows/shinpr-claude-code-workflows-recipe-task

Task Execution with Metacognitive Analysis

Task: $ARGUMENTS

Mandatory Execution Process

Step 1: Rule Selection via rule-advisor (REQUIRED)

Execute rule-advisor to analyze the task and select appropriate rules for: $ARGUMENTS

Provide context about current situation and prerequisites when invoking.

Step 2: Utilize rule-advisor Output

After receiving rule-advisor's JSON response, proceed with:

  1. Understand Task Essence (from taskEssence)

    • Focus on fundamental purpose, not surface-level work
    • Distinguish between "quick fix" vs "proper solution"
  2. Follow Selected Rules (from selectedRules)

    • Review each selected rule section
    • Apply concrete procedures and guidelines
  3. Recognize Past Failures (from pastFailurePatterns)

    • Apply countermeasures for known failure patterns
    • Use suggested alternative approaches
  4. Execute First Action (from firstActionGuidance)

    • Start with recommended action
    • Use suggested tools first

Step 3: Create Task List with TaskCreate

Register work steps using TaskCreate. Always include: first "Confirm skill constraints", final "Verify skill fidelity".

Break down the task based on rule-advisor's guidance:

  • Reflect taskEssence in task descriptions
  • Apply firstActionGuidance to first task
  • Restructure tasks considering warningPatterns
  • Set appropriate priorities

Step 4: Execute Implementation

Proceed with task execution following:

  • Selected rules from rule-advisor
  • Task structure (managed via TaskCreate/TaskUpdate)
  • Quality standards from applicable rules

Important Notes

  • Execute rule-advisor first: Mandatory metacognitive step before implementation
  • Update tasks after rule-advisor: Reflect insights in task structure using TaskUpdate
  • Follow firstActionGuidance: Start with recommended action
  • Monitor warningPatterns: Watch for failure patterns throughout execution

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Coding

testing-principles

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

coding-principles

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

ai-development-guide

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

integration-e2e-testing

No summary provided by upstream source.

Repository SourceNeeds Review