计划执行与检查节点
executing-plans
按既定实施计划完成工作,保持过程检查和反馈。
prism-stack【效率与协作】Use when asked for framework-specific best practices, implementation guidelines for React/Vue/Svelte/Next.js, or stack-specific patterns. Examples: "React best practices", "Vue component patterns", "Next.js performance"
独立 GitHub 快照 · 自动分类 · 以原作者文档为准
Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.
User asks about framework-specific patterns, component architecture, or stack guidelines.
grep -r "\"react\"\|\"vue\"\|\"svelte\"\|\"next\"\|\"nuxt\"\|\"astro\"" package.json 2>/dev/null | head -5
python3 -m prism_agent.uiux search --domain stacks --query "{stack_name}" --limit 5
┌─ Stack Guidelines — {stack_name} {version} ─────────────────────────┐
│ Category │ Guideline │ Severity │
├──────────────────┼────────────────────────────────────┼───────────────┤
│ {category} │ {guideline} │ Critical │
│ {category} │ {guideline} │ High │
│ {category} │ {guideline} │ Medium │
└──────────────────┴────────────────────────────────────┴───────────────┘
Code example:
{code_block}
If output exceeds the 40-line CLI budget, invoke /atlas-report with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.