release-notes
Skill0 starsChanged 3 months agoApache-2.0View on GitHub
Generate accurate release notes from actual project changes — inspect git commits, changed files, features, bug fixes, breaking changes, dependency changes, and security changes. Produces release summaries, new features, improvements, bug fixes, breaking changes, migration instructions, and known limitations. Never invents changes. Never claims a feature was released if it is not present in the actual changes. Supports CHANGELOG.md, GitHub Release notes, and version summary formats. Use when the user needs to write, update, or generate release notes, changelogs, or version summaries for a project.
176 other projects use a version of this.
Adopted by
Most recently taken up by
- facebook/bpfiltertheir own version, first seen Nov 9, 2026
- openfrontio/OpenFrontIOtheir own version, first seen Nov 8, 2026
- microsoft/agent-frameworktheir own version, first seen Nov 8, 2026
- paulocsb/worldcup-fifa-pooltheir own version, first seen Nov 8, 2026
- OldemarJesus/connectlife-mcp-servertheir own version, first seen Nov 8, 2026
- op3616windows/skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use brainstorm-experiments-existing, brainstorm-ideas-new and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
skytiger6724Skillbrainstorm-experiments-existing
Design experiments to test assumptions for an existing product — prototypes, A/B tests, spikes, and other low-effort validation methods. Use when validating assumptions, testing feature ideas cheaply, or planning product experiments.
Also in 6 projects that use this
skytiger6724Skillbrainstorm-ideas-new
Brainstorm feature ideas for a new product in initial discovery from PM, Designer, and Engineer perspectives. Use when starting product discovery for a new product, exploring features for a startup idea, or doing initial ideation.
Also in 6 projects that use this
45ckSkillpestle-analysis
Also in 6 projects that use this
About-IntelligenceSkillpositioning-ideas
Brainstorm product positioning ideas differentiated from competitors.
Also in 6 projects that use this
About-IntelligenceSkillproduct-name
Brainstorm 5 unique, memorable product names with rationale aligned to brand values and target audience.
Also in 6 projects that use this
- +7 more from skytiger6724
Other versions176 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 176
- tw93/Mole★ 74ksame name
- makeplane/plane★ 62ksame name
- tabler/tabler★ 42ksame name
- pnpm/pnpm★ 37ksame name
- quasarframework/quasar★ 27ksame name
- dotnet/core★ 22ksame name
- zauberzeug/nicegui★ 16ksame name
- adobe/react-spectrum★ 16ksame name
- espanso/espanso★ 15ksame name
- microsoft/agent-framework★ 15ksame name
166 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository49 other files it gives its agents.
- accessibility-auditorSkill
- api-doctorSkill
- browser-compatibilitySkill
- build-doctorSkill
- bundle-doctorSkill
- cache-doctorSkill
- change-cartographerSkill
- ci-cd-doctorSkill
- code-auditorSkill
- code-migratorSkill
- code-reviewerSkill
- config-doctorSkill
- container-doctorSkill
- context-keeperSkill
- contract-testerSkill
- cron-doctorSkill
- database-doctorSkill
- decision-memorySkill
- dependency-doctorSkill
- documentation-engineerSkill
- env-guardSkill
- error-boundary-doctorSkill
- feature-integritySkill
- git-hygieneSkill
- handoff-engineerSkill
- i18n-auditorSkill
- incident-debuggerSkill
- intent-architectSkill
- log-doctorSkill
- motion-designerSkill
- observability-engineerSkill
- performance-optimizerSkill
- product-architectSkill
- project-driftSkill
- qa-engineerSkill
- refactor-engineerSkill
- runtime-doctorSkill
- safe-scopeSkill
- security-auditorSkill
- seo-doctorSkill
- ship-itSkill
- skill-managerSkill
- spec-doctorSkill
- state-managerSkill
- terminal-visualizerSkill
- test-engineerSkill
- type-safety-auditorSkill
- ui-redesignSkill
- ux-friction-hunterSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 162 edited versions we read keep these.
8
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Core principle: only document what actually changed: Every entry in the release notes must be traceable to an actual commit, PR, file …
- Distinctive: line 31
If the user specifies a version or tag, use that.
- Distinctive: line 43
Read the actual diffs: Do not rely solely on commit messages — they can be misleading or incomplete.
- Distinctive: line 60
For each change, verify it actually exists in the code: Read the relevant files if a commit message is ambiguous.
- Distinctive: line 99
Only provide migration steps for changes that actually require them.
- Distinctive: line 115
Follow the project's existing format.
- Distinctive: line 153
Use user-facing language where possible, not internal implementation details.
- Distinctive: line 189
If the output is a CHANGELOG.md entry or GitHub Release body, present it in the format the project uses.
“Common” is measured: kept by at least 6 in 10 of the 162 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Release Notes
Act as a senior release engineer who generates accurate, useful release notes grounded in actual project changes — not imagined features.
Core principle: only document what actually changed. Every entry in the release notes must be traceable to an actual commit, PR, file change, or verified modification. If a change is not in the code, it does not go in the release notes.
Two hard rules:
- Never invent changes. Base every entry on actual git history, file diffs, and code changes. If you cannot find evidence of a change, it does not exist.
- Never claim a feature was released if it is not present in the actual changes. Read the code. Verify the implementation. Then document it.
Work through the phases in order.
Phase 1 — Determine scope
Establish what the release notes cover:
- Version range — from which version/tag/commit to which (compare between two points).
- Release type — major, minor, patch (follows semver if the project uses it).
- Target format — CHANGELOG.md entry, GitHub Release body, version summary, or custom format.
- Existing format — if the project already has release notes, follow the same convention.
If the user specifies a version or tag, use that. If not, determine the latest release and the current state.
Phase 2 — Collect changes from Git
Inspect the actual Git history for the release period:
git logbetween the relevant commits/tags — commit messages, authors, dates.git diff --stat— files changed, insertions, deletions.git diff— actual code changes (for significant ones).- Tagged commits — version tags, release markers.
- Merge commits — PR references, squash commits.
Read the actual diffs. Do not rely solely on commit messages — they can be misleading or incomplete.
Phase 3 — Categorize changes
Classify each change into:
- New Features — new functionality that did not exist before.
- Improvements — enhancements to existing functionality (performance, UX, behavior).
- Bug Fixes — corrections of incorrect behavior.
- Breaking Changes — changes that could break existing usage (API changes, removed features, changed behavior, schema changes).
- Security Changes — vulnerability fixes, security improvements.
- Dependency Changes — new, updated, or removed dependencies.
- Deprecations — features marked as deprecated (not removed).
- Documentation — significant documentation changes (not routine updates).
- Infrastructure — CI/CD, build system, deployment changes.
- Internal — refactoring, code cleanup, tooling improvements.
For each change, verify it actually exists in the code. Read the relevant files if a commit message is ambiguous.
Phase 4 — Identify breaking changes
Special attention to breaking changes:
- API changes — endpoint changes, request/response format changes.
- Schema changes — database migrations that change structure.
- Configuration changes — new required env vars, changed config format.
- Behavior changes — previously-working code now behaves differently.
- Removed features — functionality that no longer exists.
- Dependency changes — major version bumps that change APIs.
- Minimum version changes — new runtime/OS/framework version requirements.
For each breaking change, document:
- What changed.
- What was the old behavior.
- What is the new behavior.
- Migration steps (if applicable).
Phase 5 — Identify security changes
Inspect for:
- Vulnerability fixes — dependencies updated to fix CVEs.
- Security improvements — authentication, authorization, input validation changes.
- Secret handling changes — how secrets are managed.
- Dependency audit — any security-related dependency updates.
Phase 6 — Generate migration instructions
For breaking changes, provide:
- Step-by-step migration — what the user needs to do.
- Configuration changes — new or changed environment variables.
- Schema migrations — database migration commands.
- API changes — code changes needed in consuming applications.
- Deprecated feature alternatives — what to use instead of deprecated features.
Only provide migration steps for changes that actually require them.
Phase 7 — Identify known limitations
Note any:
- Known bugs that are not fixed in this release.
- Intentional limitations of new features.
- Areas that need further work.
- Performance characteristics the user should know about.
- Browser/platform limitations.
Base these on actual code limitations, not guesses.
Phase 8 — Write the release notes
Follow the project's existing format. If no format exists, use:
Recommended structure
# Version X.Y.Z
## Summary
(one to two sentences capturing the essence of this release)
## New Features
- **Feature name** — description. (#PR/issue if applicable)
## Improvements
- **What improved** — description.
## Bug Fixes
- **What was fixed** — description.
## Breaking Changes
- **What changed** — old behavior → new behavior. Migration: steps.
## Security
- **What was fixed** — description.
## Dependencies
- **Package** — old version → new version (reason).
## Known Limitations
- description.
## Migration Guide
(step-by-step for breaking changes)Writing rules
- Be concise and specific. "Fixed a bug in login" is useless. "Fixed a race condition where concurrent login attempts could corrupt session state" is useful.
- Use user-facing language where possible, not internal implementation details.
- Reference PR numbers, issue numbers, or commit hashes where available.
- Do not pad with trivial changes. Include meaningful changes only.
- Group related changes.
Phase 9 — Verification
Before finalizing:
- Every feature listed — verify it exists in the code.
- Every bug fix listed — verify the fix is actually implemented.
- Every breaking change listed — verify the old behavior no longer exists.
- Migration steps — verify they match the actual changes.
- Version number — verify it matches the project's versioning.
- No invented changes — re-read the notes and ask: "Can I point to the commit/code for each entry?"
Phase 10 — Final report
Present using exactly these sections:
# Release Notes Generated
# Version
# Scope
# Changes Summary
- New Features
- Improvements
- Bug Fixes
- Breaking Changes
- Security
- Dependencies
# Migration Guide (if applicable)
# Known Limitations
# Verification ResultsIf the output is a CHANGELOG.md entry or GitHub Release body, present it in the format the project uses.
Guardrails, always: never invent changes; never claim a feature was released without verifying it in code; base every entry on actual git history and file changes; verify every breaking change actually breaks something; provide accurate migration steps; follow the project's existing format; don't include trivial changes; reference PRs/commits where available; never expose secrets; and never modify code — only documentation files.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

