菜单
Build reusable DataFlow prompt_template classes for existing operators with structured intake, two-stage auditable outputs, and static acceptance checks. Use when users ask to generate/rewrite/optimize prompt_template or reuse operator logic with new prompt requirements.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | prompt-template-builder |
| description | Build reusable DataFlow prompt_template classes for existing operators with structured intake, two-stage auditable outputs, and static acceptance checks. Use when users ask to generate/rewrite/optimize prompt_template or reuse operator logic with new prompt requirements. |
生成可复用、可审计的 DataFlow prompt_template 初版产物，聚焦"算子复用 + 提示词定制 + 静态验收"。
当用户给出 Target 与 OP_NAME 时，本 skill 必须：
prompt_template 类代码。revise_with_feedback 风格）。按结构化字段接收输入：
Target: [业务目标/场景]
OP_NAME: [目标算子类名]
Constraints: [可选，边界/禁用项/风格约束]
Expected Output: [可选，输出格式约束]
Arguments: [可选，prompt参数列表]
Sample Cases: [可选，1-3条输入/期望行为]
详细字段定义见：
references/input-schema.md固定两阶段提问：
规则：
详见：
references/askuserquestion-rounds.md若用户已提供完整 spec，跳过采访，直接进入生成与验收。
Prompt Template Builder Progress:
- [ ] Step 1: Load references and parse user inputs
- [ ] Step 2: Choose mode (Interview or Spec)
- [ ] Step 3: Resolve operator contract (OP_NAME + prompt接口)
- [ ] Step 4: Build prompt template/config draft from contract
- [ ] Step 5: Build Stage 1 decision JSON
- [ ] Step 6: Build Stage 2 complete deliverable
- [ ] Step 7: Run static acceptance checklist
- [ ] Step 8: If feedback arrives, perform targeted revise and re-check
Operator Interface Alignment
OP_NAME 的构造参数或 run 参数。prompt_template 的调用方式必须与算子约定一致（如参数名/含义/类型）。Prompt Class Contract
DIYPromptABC 风格模板，则生成类应继承 DIYPromptABC。FormatStrPrompt），必须按该类型生成并在 Stage 2 标注依据。__all__ 导出。PascalCase + Prompt。build_prompt 必须返回 str。Output Determinism
Field/Argument Safety
build_prompt 中引用的变量必须来自显式参数或常量。Two-Stage Output (Required)
Validation Gate
references/acceptance-checklist.md。详见：
references/output-contract.mdtemplates/decision_json_template.mdtemplates/final_response_template.mdreferences/input-schema.md: 输入字段、默认值、归一化规则references/output-contract.md: 两阶段输出规范与失败态references/gotchas.md: 常见失败模式references/acceptance-checklist.md: 静态验收门槛references/askuserquestion-rounds.md: 两轮采访模板templates/prompt_class_template.py.tmpl: prompt类模板examples/: 典型场景走查Reasoning-guided pipeline planner that generates standard DataFlow pipeline code
Reasoning-guided pipeline planner that generates standard DataFlow pipeline code. Use when the user asks to generate, create, or build a DataFlow pipeline, wants to process JSONL data with LLM operators, mentions PromptedGenerator / PromptedFilter / Text2MultiHopQAGenerator, or asks about DataFlow operator chains. Also use when user provides a .jsonl file and asks what pipeline to write.
DataFlow 开发专家上下文加载器。当用户在 DataFlow 仓库中进行开发时触发， 涵盖：新建算子/Pipeline/Prompt、诊断报错、规范审查、 以及感知仓库变更并建议更新知识库。 Trigger: user is developing in DataFlow repo, asks to create operator/pipeline/prompt, encounters errors, wants code review, or asks about operators.
Build production-grade DataFlow operator scaffolds (generate/filter/refine/eval) for Codex and coding agents. Trigger when users ask to create/new/scaffold operators, add OPERATOR_REGISTRY registration, generate DataFlowStorage-based CLI wrappers, or generate operator unit/registry/smoke tests.
Build reusable DataFlow prompt_template classes for existing operators with two-round AskUserQuestion intake, two-stage auditable outputs, and static acceptance checks. Trigger when users ask to generate/rewrite/optimize prompt_template or reuse operator logic with new prompt requirements.
DataFlow development expert context loader. Use when developing in the DataFlow repo: creating operators/pipelines/prompts, diagnosing errors, code review, or detecting repo changes to update the knowledge base. Trigger: user is developing in DataFlow repo, asks to create operator/pipeline/prompt, encounters errors, wants code review, or asks about operators.