adr
CommandWrite an Architecture Decision Record documenting a significant technical decision.
Analyze an AI prompt for clarity, effectiveness, and potential issues.
$ npx -y skills add rohitg00/awesome-claude-code-toolkit --agent claude-code
Analyze an AI prompt for clarity, effectiveness, and potential issues.
1. Read the prompt text provided by the user 2. Assess prompt structure: system instruction, context, task, format, examples 3. Check for clarity: ambiguous language, vague instructions, missing context 4. Evaluate specificity: are constraints clearly defined (length, format, tone) 5. Identify missing elements: examples, output format, edge case handling 6. Check for conflicting instructions that could confuse the model 7. Assess the prompt length: too short (underspecified) or too long (diluted focus) 8. Evaluate the role or persona definition if present 9. Check for proper few-shot examples if the task requires them 10. Identify potential failure modes: hallucination triggers, unsafe content risks 11. Score the prompt on: clarity (1-10), specificity (1-10), completeness (1-10) 12. Provide specific improvement recommendations ranked by impact
The most comprehensive toolkit for Claude Code -- 135 agents, 35 curated skills (+400,000 via SkillKit), 42 commands, 176+ plugins, 20 hooks, 15 rules, 7 templates, 15 MCP configs, 26 companion apps, 53 ecosystem entries, and more.
Write an Architecture Decision Record documenting a significant technical decision.
Conduct a structured design review of a module, feature, or system component.
Generate Mermaid diagrams from codebase analysis or description.
Plan and execute a framework or library migration incrementally.
Create a structured implementation plan for the requested feature or change.
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.