mirror of
https://github.com/IgorWarzocha/Opencode-Workflows.git
synced 2026-09-14 16:22:53 +08:00
3a82a60126
Introduce a fast/smart agent split to replace the legacy general subagent. Rename improve commands to remove colons. Update the audit script to support multi-line frontmatter and stricter example validation.
3.4 KiB
3.4 KiB
description, subtask
| description | subtask |
|---|---|
| Enhance and save task prompt | true |
-
Transform into comprehensive prompt with:
<role>- Clear expert definition<context>- Why this matters<instructions>- Structured guidance<examples>- If helpful<output>- Exact format expected<verification>- How to check correctness
-
Enhance with AI optimizations from official guides:
-
Save enhanced prompt as markdown file in
enhanced-prompts/folder (create if needed). -
Present file location and guide user on next steps.
Enhancement Boosters
- Creative Tasks: Add "Don't hold back. Give it your all."
- Complex Analysis: Include
<thinking>tags with "Think deeply about this". - Multi-Tool Tasks: Add "For maximum efficiency, invoke all relevant tools simultaneously".
Task-Specific Templates
- Analysis Tasks: Add extended thinking with reflection after data gathering. Include "analyze deeply and consider multiple perspectives". Require structured findings with evidence.
- Creative Tasks: Add "Don't hold back. Give it your all. Go beyond the basics." Push for "thoughtful details and micro-interactions".
- Technical Tasks: Add self-verification with test cases. Include error handling requirements. Require documentation and examples.
- Multi-Step Tasks: Break into clear phases with checkpoints. Add reflection between major steps.
Special Rules
If user requests documentation or internet research, MUST use all available tools:
- Web search and research
- Documentation lookup
- File reading and analysis
File Saving
- Create descriptive filename:
enhanced-prompt-{task-slug}.md. - Save in
enhanced-prompts/folder. - Provide exact file path to user.
Output Format for Enhanced Prompt
The generated prompt MUST follow this structure:
<role>[Expert role definition]</role>
<context>[Background and importance]</context>
<objective>[Clear, specific goal]</objective>
<instructions>
[Step-by-step guidance]
[AI optimizations]
[Explicit details]
</instructions>
<thinking>[For complex tasks]</thinking>
<examples>[3-5 examples if helpful]</examples>
<output>[Exact format expected]</output>
<verification>[How to validate correctness]</verification>
<user_guidance> After saving, inform the user:
- "Please review the enhanced prompt in [path/filename]"
- "If you'd like to refine it further, let me know what changes you'd like"
- "If satisfied, start a new session and ask the AI to execute the prompt from the file" </user_guidance>