Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/opendcai/dataflow-webui/prompt-template-buildernpx skills add OpenDCAI/DataFlow-WebUI --skill prompt-template-buildergit clone --depth 1 https://github.com/OpenDCAI/DataFlow-WebUIWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/opendcai/dataflow-webui/prompt-template-builder)<a href="https://agentmods.dev/skills/opendcai/dataflow-webui/prompt-template-builder"><img src="https://agentmods.dev/badge/skills/opendcai/dataflow-webui/prompt-template-builder.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00053 | $0.01390 |
| Opus 5 | $0.00026 | $0.00695 |
| Sonnet 5 | $0.00011 | $0.00278 |
| Haiku 4.5 | $0.00005 | $0.00139 |
Grade A, and why
prompt-template-builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Template Builder
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”。
Goal
当用户给出 Target 与 OP_NAME 时,本 skill 必须:
- 对齐目标算子的真实接口与参数要求。
- 生成符合规范的
prompt_template类代码。 - 输出可审计的两阶段结果(决策 JSON + 完整产物)。
- 使用静态验收清单完成质量门控(不执行子进程自动测试)。
Usage
/prompt-template-builder
/prompt-template-builder --spec path/to/prompt_spec.json
Scope
In Scope
- 针对已有算子的 prompt_template 新建或改写。
- 通过 AskUserQuestion 两轮结构化采集需求。
- 通过结构化提问两轮采集需求。
- 生成标准化 prompt 类、集成示例、静态验收结果。
- 接收用户反馈并进行定向改写(
revise_with_feedback风格)。
Out of Scope (v1)
- 自动子进程执行测试脚本。
- 自动运行 Gradio UI 或流水线脚本。
- 自动提交代码或发布。
Input Contract (MANDATORY)
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
Working Modes
Mode A: AskUserQuestion Interview (default)
固定两阶段批量提问:
Mode A: Structured Interview (default)
固定两阶段提问:
- Round 1: 结构层(目标、算子、输出契约、约束)
- Round 2: 实现层(参数签名、边界样例、验收偏好)
规则:
- 每个问题块提供推荐选项 + 简短理由。
- 只在高影响缺失/冲突时追问。
- 能映射到结构化字段就不提“游离问题”。
- 直接向用户文字提问,一次性列出所有需要确认的问题。
详见:
references/askuserquestion-rounds.md
Mode B: Direct Spec
若用户已提供完整 spec,跳过采访,直接进入生成与验收。
Required Workflow
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
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/filter_rewrite_finance.md 2.6 KB
- examples/multifield_scoring_prompt.md 2.3 KB
- examples/single_field_generation.md 2.1 KB
- references/acceptance-checklist.md 1.2 KB
- references/askuserquestion-rounds.md 1.8 KB
- references/gotchas.md 2.4 KB
- references/input-schema.md 1.8 KB
- references/output-contract.md 1.8 KB
- templates/decision_json_template.md 758 B
- templates/final_response_template.md 805 B
- templates/prompt_class_template.py.tmpl 738 B
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 155 lines · 53 tokens per session scan A 3ea9b8b87df8
prompt-template-builder is a skill published in the GitHub repository OpenDCAI/DataFlow-WebUI (231 stars, last pushed 9d ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,390 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…
omh-model-optimization
This is a Hermes-native model-optimization workflow skill.