Skip to content
FunCoding

Search

Search docs, Skills and MCP

deliver-release-notes

Creates user-facing release notes that communicate new features, improvements, and fixes in clear, benefit-focused language. Use when shipping updates to communicate changes to users, customers, or stakeholders.

AI 与智能体715skills/deliver-release-notes/SKILL.md

Install

Send this to Claude Code, Codex or Cursor. The agent checks the Skill for safety first and installs it only after you confirm.

读取 https://funcoding.ai/skills/product-on-purpose/pm-skills/deliver-release-notes/install.md ，按里面的步骤帮我安装这个 Skill。

SKILL.md

Release Notes

Release notes communicate product changes to users in a way that highlights value and builds excitement. Unlike changelogs (which document what changed technically), release notes translate changes into user benefits. Good release notes help users discover new capabilities, understand improvements, and trust that issues are being addressed.

When to Use

  • Shipping product updates to customers
  • Communicating changes to internal stakeholders
  • Preparing app store update descriptions
  • Writing customer-facing email announcements
  • Documenting changes for support and sales teams

When NOT to Use

  • You are updating internal stakeholders on progress rather than announcing shipped changes -> use foundation-stakeholder-update
  • You need the technical record of changes for developers -> keep the engineering changelog; this skill translates changes into user benefits
  • You are coordinating launch readiness rather than communicating the ship -> use deliver-launch-checklist
  • Nothing user-visible shipped (a pure internal refactor): release notes that stretch to find a benefit erode trust; skip the cycle or fold it into the next one

Instructions

When asked to create release notes, follow these steps:

  1. Gather the Changelog Collect all changes included in this release: features, improvements, and bug fixes. Work from engineering changelogs, completed tickets, or pull request descriptions.

  2. Identify the Highlights Select 1-3 changes that deserve top billing. These should be changes users will notice and care about most. Lead with the most impactful change.

  3. Translate to Benefits Rewrite each change in terms of user value. Instead of "Added pagination to search results," write "Find what you need faster with improved search that handles large result sets." Focus on what users can now do or what's now better.

  4. Categorize Changes Group remaining changes into clear categories: New Features, Improvements, and Bug Fixes. Within each category, order by impact (most valuable first).

  5. Write Scannable Descriptions Each item should be 1-2 sentences. Lead with the benefit, optionally followed by the "how." Users scan release notes - make each line valuable.

  6. Acknowledge Known Issues If there are known limitations or issues, be transparent. Users appreciate honesty, and it reduces support burden.

  7. Tease Coming Soon (Optional) If appropriate, hint at what's coming next. This builds anticipation and shows momentum, but don't over-promise.

Output Format

Use the template in references/TEMPLATE.md to structure the output. Complete release notes fill the template sections: Highlights; New Features; Improvements; Bug Fixes; Known Issues; Coming Soon (optional); and Feedback.

Quality Checklist

Before finalizing, verify:

  • Highlights feature the 1-3 most impactful changes
  • Each item leads with user benefit, not technical description
  • Language is jargon-free and accessible to all users
  • Items are concise (1-2 sentences each)
  • Bug fixes mention the problem that was solved
  • No internal jargon, ticket IDs, or code names leak through; every line reads as customer-facing

Examples

See references/EXAMPLE.md for a completed example.

Similar Skills

brand-guidelines
anthropics/skills180k

brand-guidelines

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

AI & agents

internal-comms
anthropics/skills180k

internal-comms

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

AI & agents

template-skill
anthropics/skills180k

template-skill

Replace with description of the skill and when Claude should use it.

AI & agents

mcp-builder
anthropics/skills180k

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

AI & agents

algorithmic-art
anthropics/skills180k

algorithmic-art

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

AI & agents

academy-guide
anthropics/skills180k

academy-guide

Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.

AI & agents