SuperAPI AI Directory

soia-dev-draft-prd

General & other

View repository

Updated 10-16 08:37

About this skill

soia-dev-draft-prd

Transform vague internet product ideas into reviewable product requirements documents (PRDs). The input can be a one-sentence requirement or existing materials; the output is a PRD draft that clearly marks assumptions, scope, and open items, rather than an unverified implementation commitment.

Customer-readable explanation

What this skill can do

The customer wants The skill will do The customer can see
Turn a one-sentence idea into a PRD Use minimal follow-up questions to guide completion of key context and explicitly record unknowns A PRD draft with assumptions and open items
Organize existing requirements materials Summarize the problem, goals, user stories, scope, and acceptance conditions A reviewable structured requirements list
Prepare for requirements review Check scope boundaries, verifiability, dependencies, and risks Review questions, milestone suggestions, and a risk table

How customers use it

Directly describe the product opportunity, target users, problem to be solved, or expected outcome; existing interview summaries, requirement notes, or constraints may also be provided. Example:为 ExampleCorp 的示例产品起草一个 PRD:让新用户在移动端完成首次任务。

If the input is only one sentence, first ask no more than five questions ordered by impact, prioritizing confirmation of target users, problem evidence, success metrics, constraints, and launch window. If the customer cannot answer for the time being, use clear "assumption" placeholders to continue drafting, and do not write assumptions as facts.

Dependencies and installation

This is a pure methodology skill, with no hard dependencies, optional tool dependencies, or private configuration; it does not read company knowledge bases, and does not execute code, data, or remote system operations.

npx skills add soia-team/soia-open-dev-product-skills -g -a '*' -s soia-dev-draft-prd -y

The configuration convention uses schema v2:~/.config/soia-skills/soia-dev-draft-prd/config.yml. This skill does not require creating this file by default; if the customer wants to reuse document templates, glossaries, or default delivery formats over the long term, they can define them in their own configuration, and credentials or private business materials must not be placed in it.

Workflow

1. Establish the requirements boundary

Restate the known requirements and distinguish observed facts, reasonable inferences, and unverified assumptions. Confirm that what is being delivered is a draft, not a project initiation, scheduling, or R&D commitment; without customer authorization, do not make business, compliance, or release decisions on the customer's behalf.

2. Fill in the most critical information

Ask questions from the following dimensions, choosing the items with the largest information gaps: target users and usage scenarios, current problems and evidence, business goals and success metrics, time/platform/compliance constraints, existing capabilities, and explicit exclusions. Avoid asking questions just to fill out a template; place low-risk details that can already be reasonably assumed into open items.

3. Draft the problem, goals, and boundaries

Start with the user problem rather than a preset feature. Goals should include observable outcomes or measurement methods; non-goals should exclude adjacent matters that are easily misunderstood as part of this scope. If there is no baseline data, state the metrics to be collected and the collection method, and do not fabricate values.

4. Define user stories and functional scope

For each core scenario, write "As a <user>, I want <action>, so that <outcome>." Layer the functional scope by must, should, could, or explicitly will not do; explain key flows, exception paths, permission/state boundaries, and cross-team dependencies. Feature descriptions should focus on observable behavior and avoid locking in technical implementation in advance.

5. Write acceptable conditions

Define independently verifiable acceptance criteria for each must-have scope, covering normal paths, key failure paths, and boundary conditions. Use observable preconditions, actions, and results; expressions such as "good experience" or "fast performance" must be changed into verifiable metrics or listed as pending.

6. Plan milestones, risks, and open items

Organize milestones by verifiable results, such as "requirements confirmed," "prototype validated," "usable version," and "launch retrospective," without fabricating dates, resources, or commitments. Write risks as "trigger condition—impact—mitigation/verification action"; list unresolved issues separately, indicating the suggested owner or required evidence.

7. Self-check and delivery

Check from the opposite side: whether the goals can be supported by the functional scope, whether non-goals prevent scope creep, whether each must-have feature has acceptance criteria, and whether each fact has a source or is marked as an assumption. Before delivery, remove duplicate descriptions and unproven assertions, and state what needs client confirmation.

Output contract

By default, output in Markdown, including the following sections; an internal template required by the client may change the layout, but uncertainty markers must not be omitted:

# <产品/功能名称> PRD

## 背景与问题
## 目标与非目标
## 目标用户与场景
## 用户故事
## 功能范围
## 验收标准
## 里程碑
## 风险与缓解
## 开放项与假设
  • Background and problem: state only facts provided by the client or judgments marked as assumptions.
  • Goals and non-goals: goals include success signals; non-goals clearly define the scope not addressed this time.
  • User stories, functional scope, and acceptance criteria: mutually traceable; all must-have scope has at least one acceptance condition.
  • Milestones: described by outcomes and confirmation points; do not commit to specific dates or staffing without a basis.
  • Risks and open items: each item includes impact and next verification or decision information; unknowns are not disguised as conclusions.

Private information and intermediate data

  • Use only requirement information provided by the client in the current conversation or in explicitly authorized materials; do not read, infer, or repeat any unauthorized company knowledge base, account information, or personal data.
  • By default, generate drafts only in the conversation and do not write to the local disk. When the client requests saving, write to the location specified by the client; contact persons, real business data, and attachment links in the draft must be desensitized as required by the client.
  • This skill does not require credentials and does not record runtime status, cache, or temporary data. If the client sets up its own configuration, only non-sensitive format preferences are stored in the configuration, and the retention period is controlled by the client.

Logs and completion receipt

The final reply should briefly state: the input scope used, assumptions proposed or adopted, PRD sections generated, unresolved open items, and suggested next steps (for example, confirming metrics or reviewing scope). Do not claim to have completed user research, technical assessment, compliance review, or launch decisions unless the client has separately provided corresponding evidence.

Quality and safety boundaries

  • Use general internet product practices and fictional examples; do not rely on any organization-specific terminology, systems, processes, or data.
  • Do not fabricate user research, market data, metric baselines, client commitments, schedules, or legal conclusions.
  • When privacy, security, payment, medical, financial, or regulatory requirements are involved, mark them as risks pending professional review and do not provide substitute professional advice.
  • The output is requirements communication material; implementation plans, technical architecture, project schedules, and release authorization must be separately confirmed by the corresponding owners.

Agent Metadata

agents/openai.yaml Provides only interface display and example prompts; all portable execution requirements are governed by this document.

Verification

  • Static: confirm that frontmatter, directory structure, and Markdown links pass repository audit.
  • Content: Use a fictional requirement to check that eight required sections can be generated, and mark unknown information as assumptions or open items.
  • Security: Before submission, scan for private paths, credentials, and proprietary terms that should not appear.