Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Release Notes Writing

ASecurity

Use when the stakeholder asks for release notes or a changelog - group done/released work into Added, Changed, Deprecated, Removed, Fixed and Security, in outcome language, with task references

109 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgogitsecurity

Security Analysis

A100/100

Scanned 10/2/2026

$npx -y skills add makifbaysal/tasktrooper --skill release-notes-writing --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Release Notes Writing?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Release Notes Writing
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/makifbaysal-release-notes-writing/badge)](https://www.skillsdirectory.com/skills/makifbaysal-release-notes-writing)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: release-notes-writing
category: pm
description: Use when the stakeholder asks for release notes or a changelog - group done/released work into Added, Changed, Deprecated, Removed, Fixed and Security, in outcome language, with task references
source: olivierlacan/keep-a-changelog 1.1.0 (MIT), phuryn/pm-skills release-notes (MIT), adapted
---
# Release Notes Writing

## Overview

Release notes tell users what changed for THEM, not what the team did. The failure mode is internal jargon and a flat list of task titles that mean nothing to a user. Changelogs are for humans, not machines — don't dump git log or task titles verbatim.

**Core principle:** User-visible outcomes, grouped by Keep a Changelog's categories, in plain language.

## Where the material comes from

- `list_board_tasks` filtered to `done`/`released` for the period asked about.
- `get_task_pull_request` on each one for detail (what actually shipped, not just the title).
- TaskTrooper has no epic/parent task — deliver the notes in chat, or as a document (`add_task_document`) on whichever task the stakeholder names, never a phantom "release epic".
- The system's own batch release cut auto-generates `### Features` / `### Fixes` sections from `KEY Title`. Writing implementation-task-spec titles as action + user-visible object (not an internal component name) makes that auto-generated text usable on its own — keep that in mind even when you're not the one writing this document.

## Structure

- **Added** — new user-visible capability.
- **Changed** — behavior changes users must know about (a moved button, a changed default).
- **Deprecated** — soon-to-be-removed, still working.
- **Removed** — gone.
- **Fixed** — defects resolved, described by the symptom the user saw, not the internal cause.
- **Security** — a vulnerability closed; state impact, not exploit detail.
- **Action required** — anything in Changed/Removed that is breaking: what the user must do and by when.

Write user-facing language, no internal jargon. Put task keys in parentheses for traceability.

## Worked Example

```markdown
## Release 2026-07-16

### Added
- Export a project's tasks to CSV from the board (LLM-142).

### Fixed
- Deleting a task with subtasks no longer shows an error (LLM-150).

### Changed
- Task titles are now capped at 200 characters (LLM-138).

### Action required
- None this release.
```

Contrast the bad version: *"LLM-142 TaskExporter service; LLM-150 fix nil deref in cascade."* — accurate to the team, meaningless to a user.

## Common Mistakes

- Internal jargon ("nil deref", "N+1").
- Task titles pasted verbatim instead of user outcomes.
- Omitting "Changed" → users surprised by a moved feature.
- A breaking change with no "Action required" line.
- Attaching the document to an invented "release epic" task.

## Red Flags

- A note a user couldn't understand.
- No task key for traceability.
- A Removed/Changed entry with nothing telling the user what to do about it.

Attribution

makifbaysalmakifbaysal
View sourceSee grades on GitHubMore from makifbaysal →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →