← 返回 Skills 市场
zhao202404

7skill

作者 zhao202404 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
116
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install excel-skill02
功能描述
Create and manage Product Requirements Documents (PRDs) with user stories, acceptance criteria, and prioritized task tracking for feature implementation.
使用说明 (SKILL.md)

PRD Skill

Create and manage Product Requirements Documents (PRDs) for feature planning.

What is a PRD?

A PRD (Product Requirements Document) is a structured specification that:

  1. Breaks a feature into small, independent user stories
  2. Defines verifiable acceptance criteria for each story
  3. Orders tasks by dependency (schema → backend → UI)

Quick Start

  1. Create/edit agents/prd.json in the project
  2. Define user stories with acceptance criteria
  3. Track progress by updating passes: falsetrue

prd.json Format

{
  "project": "MyApp",
  "branchName": "ralph/feature-name",
  "description": "Short description of the feature",
  "userStories": [
    {
      "id": "US-001",
      "title": "Add priority field to database",
      "description": "As a developer, I need to store task priority.",
      "acceptanceCriteria": [
        "Add priority column: 'high' | 'medium' | 'low'",
        "Generate and run migration",
        "Typecheck passes"
      ],
      "priority": 1,
      "passes": false,
      "notes": ""
    }
  ]
}

Field Descriptions

Field Description
project Project name for context
branchName Git branch for this feature (prefix with ralph/)
description One-line feature summary
userStories List of stories to complete
userStories[].id Unique identifier (US-001, US-002)
userStories[].title Short descriptive title
userStories[].description "As a [user], I want [feature] so that [benefit]"
userStories[].acceptanceCriteria Verifiable checklist items
userStories[].priority Execution order (1 = first)
userStories[].passes Completion status (falsetrue when done)
userStories[].notes Runtime notes added by agent

Story Sizing

Each story should be completable in one context window.

✅ Right-sized:

  • Add a database column and migration
  • Add a UI component to an existing page
  • Update a server action with new logic
  • Add a filter dropdown to a list

❌ Too large (split these):

  • "Build the entire dashboard" → Split into: schema, queries, UI, filters
  • "Add authentication" → Split into: schema, middleware, login UI, session

Story Ordering

Stories execute in priority order. Earlier stories must NOT depend on later ones.

Correct order:

  1. Schema/database changes (migrations)
  2. Server actions / backend logic
  3. UI components that use the backend
  4. Dashboard/summary views

Acceptance Criteria

Must be verifiable, not vague.

✅ Good:

  • "Add status column to tasks table with default 'pending'"
  • "Filter dropdown has options: All, Active, Completed"
  • "Typecheck passes"

❌ Bad:

  • "Works correctly"
  • "User can do X easily"

Always include: "Typecheck passes"

Progress Tracking

Update passes: true when a story is complete. Use notes field for runtime observations:

"notes": "Used IF NOT EXISTS for migrations"

Quick Reference

Action Command
Create PRD Save to agents/prd.json
Check status `cat prd.json
View incomplete `jq '.userStories[]

Resources

See references/ for detailed documentation:

  • agent-usage.md - How AI agents execute PRDs (Claude Code, OpenCode, etc.)
  • workflows.md - Sequential workflow patterns
  • output-patterns.md - Templates and examples
安全使用建议
This skill is coherent with its PRD purpose, but pay attention to the runtime instructions recommending unattended agent loops and use of '—dangerously-skip-permissions'. Before installing or running: - Do not run the suggested unattended loop against a production repository. Test in a disposable clone/worktree or sandbox. - Avoid using '—dangerously-skip-permissions' or any option that silences user consent; require manual approval for each agent action until you trust behavior. - Ensure any agent CLI (claude, OpenCode) credentials are stored and scoped appropriately; the skill does not request or manage credentials. - Review and approve every commit produced by the agent (use code reviews or gating CI) before merging or pushing. - Limit network access and secrets available to the environment running the agent; remove keys not needed for the test run. If you want a lower-risk setup: run agents manually per-story (human-in-the-loop) rather than using the persistent unattended loop. If the skill had bundled code that executed these loops or requested unrelated credentials, the assessment would be more severe; as-is, the primary concern is the recommended permission bypass and unattended automation.
能力评估
Purpose & Capability
Name/description (PRD creation and management) aligns with the files and instructions: the skill is instruction-only and tells agents to create/edit agents/prd.json, produce user stories, run checks, and update progress. There are no unrelated required binaries, env vars, or config paths.
Instruction Scope
SKILL.md and references explicitly instruct autonomous agents to read the repo, checkout/create branches, implement code, run typechecks/tests, commit changes, and mark stories complete. The agent-usage examples include a persistent loop using 'claude --print --dangerously-skip-permissions' which bypasses permission prompts — this grants an agent broad autonomous write/execute capability over a codebase and is beyond a passive PRD authoring tool. While these actions are coherent for an 'AI-implementing-PRD' workflow, recommending permission-skipping unattended loops is a safety concern.
Install Mechanism
No install spec and no code files (instruction-only). This minimizes disk footprint and supply-chain risk: nothing is downloaded or executed by the skill itself.
Credentials
The skill declares no required environment variables or credentials, which is proportionate. However, the instructions rely on external agent CLIs (e.g., claude, OpenCode) that in practice may need API keys/credentials — the skill does not request or document these, leaving the user to supply them. That omission is not necessarily malicious but means credential handling happens outside the skill and should be audited by the user.
Persistence & Privilege
always:false and the skill does not request system-wide changes or modify other skills. Still, it encourages running a persistent agentic loop that continually modifies a repo; autonomous invocation combined with the permission-bypass example increases blast radius if run without proper safeguards.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install excel-skill02
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /excel-skill02 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
- Initial release of the PRD (Product Requirements Document) skill. - Enables creation and management of structured PRDs, including user stories and acceptance criteria. - Provides step-by-step instructions for defining, ordering, and tracking feature tasks via `agents/prd.json`. - Introduces a standardized JSON schema for breaking down and monitoring product features. - Includes clear guidelines on story sizing, acceptance criteria, and progress tracking.
元数据
Slug excel-skill02
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

7skill 是什么?

Create and manage Product Requirements Documents (PRDs) with user stories, acceptance criteria, and prioritized task tracking for feature implementation. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 116 次。

如何安装 7skill?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install excel-skill02」即可一键安装,无需额外配置。

7skill 是免费的吗?

是的,7skill 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

7skill 支持哪些平台?

7skill 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 7skill?

由 zhao202404(@zhao202404)开发并维护,当前版本 v1.0.0。

💬 留言讨论