prompt-template-builder

prompt-template-builder is a skill for Claude Code, Codex from OpenDCAI/DataFlow-WebUI. It costs 53 tokens per session (1,390 once invoked), scanned A, original, Apache-2.0.

A workflow for creating reusable DataFlow prompt-template classes around existing operators. It collects requirements in two rounds and produces code with an auditable static review.

In plain words
What is it for?
Use it to create or revise prompt templates, define their parameters and outputs, add integration examples, and check them without running subprocess tests.
Why use it?
It helps turn a specific prompt requirement into a consistent template that matches the operator's real interface.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/opendcai/dataflow-webui/prompt-template-builder
Any agent
npx skills add OpenDCAI/DataFlow-WebUI --skill prompt-template-builder
Clone the repo
git clone --depth 1 https://github.com/OpenDCAI/DataFlow-WebUI

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for prompt-template-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/opendcai/dataflow-webui/prompt-template-builder.svg)](https://agentmods.dev/skills/opendcai/dataflow-webui/prompt-template-builder)
Your own site
<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>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,390 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 5d ago against content hash 3ea9b8b87df8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

skills/canonical/prompt-template-builder/SKILL.md · 155 lines

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 TargetOP_NAME 时,本 skill 必须:

  1. 对齐目标算子的真实接口与参数要求。
  2. 生成符合规范的 prompt_template 类代码。
  3. 输出可审计的两阶段结果(决策 JSON + 完整产物)。
  4. 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

Read the full file on GitHub · 155 lines

Changes

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.

  1. 5d ago First seen · 155 lines · 53 tokens per session scan A 3ea9b8b87df8

Subscribe to this mod's changes

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.

Related

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.

davila7/claude-code-templates · 54 tokens

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.

google-labs-code/stitch-skills · 41 tokens

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…

langwatch/langwatch · 105 tokens

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…

Jeffallan/claude-skills · 93 tokens

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…

digitalsamba/claude-code-video-toolkit · 99 tokens

omh-model-optimization

This is a Hermes-native model-optimization workflow skill.

rlaope/oh-my-hermes · 82 tokens