跳到正文
cccskills
免费在 GitHub 公开

feature-spec

Turn a feature idea into a structured product specification with user stories, acceptance criteria, scope, dependencies, and risks. The Prometeo PM agent reviews existing specifications, writes a Markdown document, and prepares a development handoff.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Creates a complete product feature specification with acceptance criteria, scope, dependencies, and risks. Delegates to the Prometeo (PM) agent.

查看安装方法

适用场景

  • Defining requirements for a new product feature
  • Writing user stories with acceptance criteria
  • Clarifying scope before implementation
  • Preparing a specification for a development handoff

包含的文件(1)

  • SKILL.md1.6 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Feature Spec

Creates a complete product feature specification using the Prometeo (PM) agent.

When to Use This Skill

  • Defining a new feature or product requirement
  • Writing user stories with acceptance criteria
  • Planning product work that needs a structured spec
  • Documenting business requirements before implementation

What This Skill Does

  1. Runs the SIGN IN checklist (identity, task, memory review)
  2. Researches existing specs to avoid conflicts
  3. Creates a comprehensive spec at docs/specs/{feature-name}.md
  4. Runs the Spec Completion checklist (TIME OUT)
  5. Prepares a structured handoff to the Dev agent
  6. Runs the SIGN OUT checklist (memory update, deliverables)

How to Use

Basic Usage

/feature-spec user authentication with JWT tokens

Detailed Usage

/feature-spec multi-tenant billing system with Stripe integration

Example

User: /feature-spec webhook event system

Output: A complete spec at docs/specs/webhook-event-system.md containing:

  • Problem statement and success metrics
  • User stories with GIVEN/WHEN/THEN acceptance criteria
  • In-scope and out-of-scope items
  • Dependencies, risks, and open questions
  • Handoff notes for the Dev agent

Tips

  • Be specific about the feature scope in your description
  • The agent will ask clarifying questions rather than guess
  • Review the generated spec before passing to implementation

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Handle ActiveCampaign contact and marketing tasks through Rube MCP, a connection for agent tools. Find or create contacts, manage tags and subscriptions, enroll contacts in existing automated workflows, and create follow-up tasks.

中文简介正在准备中。当前显示英语简介。

  • Finding or registering contacts
  • Adding or removing contact tags
  • Subscribing contacts to lists or unsubscribing them
davepoon/buildwithclaude36692026年10月20日 更新

Research competitors’ live Meta and Google ads to identify opening hooks, offers, calls to action, and landing pages. Receive a sourced creative brief and up to three test ideas adapted to your product.

中文简介正在准备中。当前显示英语简介。

  • Find angles for new ad copy
  • Plan creative tests using competitor ads
  • Choose a landing page message
davepoon/buildwithclaude36692026年10月20日 更新

Add website or app tracking, then use command-line tools to review traffic, signups, drop-off, and returning users across projects. Run A/B tests, which compare alternative headlines or buttons, and inspect results to guide changes.

中文简介正在准备中。当前显示英语简介。

  • Adding page-view and key-action tracking
  • Reviewing traffic and referral sources across projects
  • Finding where visitors drop out before signup or purchase
davepoon/buildwithclaude36692026年10月20日 更新

Establish rules for when an AI agent should recall past context and save lasting decisions, corrections, preferences, and failures. Works with Markdown files or memory services, preserving decision history and surfacing conflicting records.

中文简介正在准备中。当前显示英语简介。

  • Carry project conventions into the next session
  • Save user corrections and lasting preferences
  • Record failed approaches and their causes
davepoon/buildwithclaude36692026年10月20日 更新

Audit local AI coding-agent sessions with agenttrace to identify spending, token use, tool failures, and operational problems. Produce readable or structured reports and define pass-or-fail thresholds for automated continuous integration checks.

中文简介正在准备中。当前显示英语简介。

  • Investigating session costs and token waste
  • Finding repeated tool failures and retries
  • Exporting session reports as Markdown or JSON
davepoon/buildwithclaude36692026年10月20日 更新

Audit saved agent sessions for access to private files and evidence that secret values entered an agent's context. Get findings without displaying secrets, identify keys needing rotation, and inspect Claude Code or Codex sessions in a local report.

中文简介正在准备中。当前显示英语简介。

  • Check whether an agent accessed .env files
  • Identify keys that may need rotation
  • Audit private-file access by subagents
davepoon/buildwithclaude36692026年10月20日 更新

查看 davepoon 的全部技能

报告此技能的问题