원클릭으로
source-command-enhance
Enhance a prompt for better outputs
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Enhance a prompt for better outputs
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Security and quality audit of application codebase
Autonomous agent execution mode
Bridgebuilder — Autonomous PR Review
Triage a bug report through structured phases and create micro-sprint
L2 cost-budget enforcer — daily token cap with fail-closed semantics under uncertainty (billing-API primary, internal counter fallback, periodic reconciliation cron)
L5 cross-repo status reader — reads structured cross-repo state via gh API with TTL cache + stale fallback, BLOCKER extraction from NOTES.md, per-source error capture, p95 <30s for 10 repos
| name | source-command-enhance |
| description | Enhance a prompt for better outputs |
Use this skill when the user asks to run the migrated source command enhance.
Analyzes and enhances your prompt to improve output quality using the PTCF framework (Persona + Task + Context + Format).
/enhance <your prompt here>
/enhance --analyze-only <prompt>
/enhance --task-type code_review <prompt>
| Option | Description |
|---|---|
--analyze-only | Show analysis without enhancement |
--task-type <type> | Force a specific task type |
| Type | Use For |
|---|---|
debugging | Fixing errors, bugs, issues |
code_review | Reviewing code quality |
refactoring | Improving code structure |
summarization | Condensing information |
research | Investigating topics |
generation | Creating new content |
general | Everything else (fallback) |
/enhance review the code
Output shows:
/enhance --analyze-only review the code
Output shows analysis without enhancement - useful for learning.
/enhance --task-type security review auth.ts
Uses security-focused code review template.
| Score | Quality |
|---|---|
| 0-1 | Invalid (no task verb) |
| 2-3 | Minimal (task only) |
| 4-5 | Acceptable (task + context) |
| 6-7 | Good (task + context + format) |
| 8-10 | Excellent (all components) |
See .loa.config.yaml:
prompt_enhancement:
enabled: true
auto_enhance_threshold: 4
show_analysis: true