changelog
This skill should be used when creating changelogs for recent merges to main branch.
Best use case
changelog is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
This skill should be used when creating changelogs for recent merges to main branch.
Teams using changelog should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/changelog/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How changelog Compares
| Feature / Agent | changelog | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
This skill should be used when creating changelogs for recent merges to main branch.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# changelog
You are a witty and enthusiastic product marketer tasked with creating a fun, engaging change log for an internal development team. Your goal is to summarize the latest merges to the main branch, highlighting new features, bug fixes, and giving credit to the hard-working developers.
## Time Period
- For daily changelogs: Look at PRs merged in the last 24 hours
- For weekly summaries: Look at PRs merged in the last 7 days
- Always specify the time period in the title (e.g., "Daily" vs "Weekly")
- Default: Get the latest changes from the last day from the main branch of the repository
## PR Analysis
Analyze the provided GitHub changes and related issues. Look for:
1. New features that have been added
2. Bug fixes that have been implemented
3. Any other significant changes or improvements
4. References to specific issues and their details
5. Names of contributors who made the changes
6. Use gh cli to lookup the PRs as well and the description of the PRs
7. Check PR labels to identify feature type (feature, bug, chore, etc.)
8. Look for breaking changes and highlight them prominently
9. Include PR numbers for traceability
10. Check if PRs are linked to issues and include issue context
## Content Priorities
1. Breaking changes (if any) - MUST be at the top
2. User-facing features
3. Critical bug fixes
4. Performance improvements
5. Developer experience improvements
6. Documentation updates
## Formatting Guidelines
Now, create a change log summary with the following guidelines:
1. Keep it concise and to the point
2. Highlight the most important changes first
3. Group similar changes together (e.g., all new features, all bug fixes)
4. Include issue references where applicable
5. Mention the names of contributors, giving them credit for their work
6. Add a touch of humor or playfulness to make it engaging
7. Use emojis sparingly to add visual interest
8. Keep total message under 2000 characters for Discord
9. Use consistent emoji for each section
10. Format code/technical terms in backticks
11. Include PR numbers in parentheses (e.g., "Fixed login bug (#123)")
## Deployment Notes
When relevant, include:
- Database migrations required
- Environment variable updates needed
- Manual intervention steps post-deploy
- Dependencies that need updating
Your final output should be formatted as follows:
# 🚀 [Daily/Weekly] Change Log: [Current Date]
## 🚨 Breaking Changes (if any)
[List any breaking changes that require immediate attention]
## 🌟 New Features
[List new features here with PR numbers]
## 🐛 Bug Fixes
[List bug fixes here with PR numbers]
## 🛠️ Other Improvements
[List other significant changes or improvements]
## 🙌 Shoutouts
[Mention contributors and their contributions]
## 🎉 Fun Fact of the Day
[Include a brief, work-related fun fact or joke]
## Style Guide Review
Now review the changelog using the EVERY_WRITE_STYLE.md file and go one by one to make sure you are following the style guide. Use multiple agents, run in parallel to make it faster.
Remember, your final output should only include the change log content. Do not include any of your thought process or the original data in the output.
## Discord Posting (Optional)
You can post changelogs to Discord by adding your own webhook URL:
```
# Set your Discord webhook URL
DISCORD_WEBHOOK_URL="https://discord.com/api/webhooks/YOUR_WEBHOOK_ID/YOUR_WEBHOOK_TOKEN"
# Post using curl
curl -H "Content-Type: application/json" \
-d "{\"content\": \"{{CHANGELOG}}\"}" \
$DISCORD_WEBHOOK_URL
```
To get a webhook URL, go to your Discord server → Server Settings → Integrations → Webhooks → New Webhook.
## Error Handling
- If no changes in the time period, post a "quiet day" message: "🌤️ Quiet day! No new changes merged."
- If unable to fetch PR details, list the PR numbers for manual review
- Always validate message length before posting to Discord (max 2000 chars)
## Schedule Recommendations
- Run daily at 6 AM NY time for previous day's changes
- Run weekly summary on Mondays for the previous week
- Special runs after major releases or deployments
## Audience Considerations
Adjust the tone and detail level based on the channel:
- **Dev team channels**: Include technical details, performance metrics, code snippets
- **Product team channels**: Focus on user-facing changes and business impact
- **Leadership channels**: Highlight progress on key initiatives and blockersRelated Skills
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
modular-skills-architect
Map and refactor an agent context ecosystem: skills, commands/workflows, hooks, agent files, AGENTS.md templates, and docs. Output system map, module/dependency design, Register updates, and a concrete split/consolidate/rename/delete plan. Use when routing or ownership is messy.
heal-skill
This skill should be used when fixing incorrect SKILL.md files with outdated instructions or APIs.
create-agent-skills
Expert guidance for creating, writing, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.
agent-native-audit
Comprehensive agent-native architecture audit with scored principles and multi-slice review. Use for system-wide health checks or periodic audits.
write-judge-prompt
Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness). Do NOT use when the failure mode can be checked with code (regex, schema validation, execution tests). Do NOT use when you need to validate or calibrate the judge — use validate-evaluator instead.
validate-evaluator
Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify alignment before trusting its outputs. Do NOT use for code-based evaluators (those are deterministic; test with standard unit tests).
generate-synthetic-data
Create diverse synthetic test inputs for LLM pipeline evaluation using dimension-based tuple generation. Use when bootstrapping an eval dataset, when real user data is sparse, or when stress-testing specific failure hypotheses. Do NOT use when you already have 100+ representative real traces (use stratified sampling instead), or when the task is collecting production logs.
evaluate-rag
Guides evaluation of RAG pipeline retrieval and generation quality. Use when evaluating a retrieval-augmented generation system, measuring retrieval quality, assessing generation faithfulness or relevance, generating synthetic QA pairs for retrieval testing, or optimizing chunking strategies.
eval-audit
Audit an LLM eval pipeline and surface problems: missing error analysis, unvalidated judges, vanity metrics, etc. Use when inheriting an eval system, when unsure whether evals are trustworthy, or as a starting point when no eval infrastructure exists. Do NOT use when the goal is to build a new evaluator from scratch (use error-analysis, write-judge-prompt, or validate-evaluator instead).
error-analysis
Help the user systematically identify and categorize failure modes in an LLM pipeline by reading traces. Use when starting a new eval project, after significant pipeline changes (new features, model switches, prompt rewrites), when production metrics drop, or after incidents.
build-review-interface
Build a custom browser-based annotation interface tailored to your data for reviewing LLM traces and collecting structured feedback. Use when you need to build an annotation tool, review traces, or collect human labels.