promptdriven/pdd

pdd-prompting

The PDD Prompting guide.

查看源码

使用方法

  1. 复制安装命令,在自己的智能体环境安装前先检查源码包。
  2. 从原始文档核对所需工具、凭据和支持的宿主。
  3. 说明输入材料与期望交付物,并对照来源检查输出。
npx skills add https://github.com/promptdriven/pdd --skill pdd-prompting

开始前需了解

  • 安装不包含模型订阅、API 额度或访问文件的权限。
  • 仓库星数和安装量反映活跃情况,不等于独立质量或安全测试。
仓库原始内容

按源仓库内容呈现,保留标题、案例、代码、表格、链接以及原文引用的演示图片。

PDD prompting

Each module's .prompt.md is the source; code implements it.

Core rules

  • Read RUNBOOK.md first, guide.md in full, and story-guide.md; skip runbook/*.md chapters unless a workflow step or lint error points to one.
  • Finish Prompt Space (pdd lint --local -> passing pdd test) before code; change no code and start no interactive pdd simulate unless asked.
  • One prompt per module: purpose, ## Domain decisions and failure edges. Give each rule one owner prompt. Link shared rules. For a CLI, say if a rule belongs to the whole-CLI prompt or to one module's prompt.
  • Inject outside effects (DB, files, net, clock, RNG, IDs) via inputs or <port>.<op> ports; never use prose counters or link kind: native-only adapters under ## Dependencies (RUNBOOK §21).
  • Linked .ui.svg is the layout spec: parts, words, order, ids and states. Check with pdd lint --local; render PNGs only if asked (RUNBOOK §13).
  • Write Short JSON scenarios with self-contained step inputs (seeds + $use/patch) for parallel steps; chain $step or world only for persistence, with 1 observable check per claim; never copy code output.
  • Show prompt, Story and cases first. Record actual chat approval with --said (RUNBOOK §2), never invent it.
  • Do not run pdd lint before pdd test; test includes lint. Report only real output.

Files

  • RUNBOOK.md: concise topic router and core commands (pdd test, pdd lint --local, pdd simulate).
  • guide.md: the Prompting guide.
  • story-guide.md: Story sizing and criteria rules.
  • review.md, verification-setup.md, verification-recipe.md, autopilot-job-rules.md: check, code and Autopilot references.

How to write

  1. Name applicable guide.md rules and find the owning prompt.
  2. Write or change the prompt. Use 0 Stories + "No Story:" for internal changes, edit the existing Story, or write 1 cohesive standalone-loop Story in the person's words, with no function calls or type names.
  3. Derive normal, limit and error cases (<= 15 steps; align simulation_overrides ports) and run pdd files + pdd lint --local.
  4. Show drafts and open choices.
  5. After changing prompt, Story and tests, run pdd test as RUNBOOK.md says, and show the person the Prompt tests line(s) and the report link(s). Offer pdd simulate STORY. If a check fails, show it; never change the expected value yourself.

Without prompts, use code, callers and tests as evidence. Change no code until asked.

Workflow skills: pdd-small-change, pdd-bug, pdd-feature and pdd-product.

来自同一仓库

更多 Skills

全部 Skills