release-notes-drafting
Skill0 starsChanged 17 days agoMITView on GitHub
Turn engineering tickets, changelogs, PR titles or sprint summaries into customer-facing release notes. Use whenever someone asks for release notes, a changelog entry, a "what's new" post, a product update email, or a monthly product drop summary, even if they only paste raw ticket titles.
In this repository33 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- beta-program-managerSkill
- cross-team-dependency-mapSkill
- customer-advisory-board-prepSkill
- data-request-routerSkill
- decision-logSkill
- deprecation-planSkill
- duplicate-request-mergingSkill
- experiment-logSkill
- feature-flag-trackingSkill
- feedback-taggingSkill
- information-debt-auditSkill
- internal-enablement-briefSkill
- kpi-health-checkSkill
- launch-readiness-checklistSkill
- meeting-to-action-converterSkill
- new-pm-onboarding-packSkill
- pricing-packaging-change-logSkill
- process-documentationSkill
- product-metrics-definitionsSkill
- product-ops-contextSkill
- quarterly-planning-prepSkill
- raci-builderSkill
- request-intake-triageSkill
- retro-facilitationSkill
- ritual-calendarSkill
- roadmap-hygieneSkill
- sprint-review-summarySkill
- support-escalation-patternsSkill
- tool-stack-auditSkill
- vendor-evaluation-scorecardSkill
- voice-of-customer-digestSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
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 29
Never invent a benefit, a metric, or a date that isn't in the source.
- Distinctive: line 42
No internal jargon, ticket IDs, team names, or codenames.
- Distinctive: line 43
Write "you," not "users."
- Distinctive: line 44
Avoid "we're excited to announce," "seamless," "powerful," "robust," "leverage."
- Distinctive: line 68
Before handing it over:
- Distinctive: line 69
Every item traces back to something in the source.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Release notes drafting
Release notes exist so a customer can answer one question in under ten seconds: "Does this change anything for me?" Everything below serves that.
Before you start
If .agents/product-ops-context.md exists (or .claude/product-ops-context.md), read it first. Use the team, owners, tools, meetings, and metric definitions it already has, and only ask for what's missing or specific to this task. If it doesn't exist, go ahead with what you're given, and suggest running product-ops-context once so the next skill doesn't have to ask.
Inputs to gather
Work from whatever the person provides: ticket titles, PR descriptions, a changelog, a sprint review, or notes from a product manager. Before drafting, sort every item into one of these buckets:
| Bucket | Goes in the notes? |
| New feature or capability | Yes, lead with these |
| Improvement to something that already exists | Yes |
| Bug fix a customer could have noticed | Yes, briefly |
| Internal refactor, tests, tooling, dependency bumps | No |
| Behind a flag or limited beta | Only if the person says so, and label it |
| Unclear | Ask, or list under "Needs confirmation" at the end |
Never invent a benefit, a metric, or a date that isn't in the source. If an item's customer impact is unclear, say so rather than guessing.
Writing each item
For every item that goes in:
- Name what changed in plain words. "You can now export reports as CSV," not "CSV export functionality."
- Say who it's for or where to find it, if the source says.
- Say why it matters in one sentence, only if the source supports it.
Rules:
- Lead with the verb or the outcome, not the feature name.
- One to two sentences per item. No item longer than three.
- No internal jargon, ticket IDs, team names, or codenames.
- Write "you," not "users."
- Avoid "we're excited to announce," "seamless," "powerful," "robust," "leverage."
Output format
## [Product name] updates — [Month Year or version]
### New
- **[Short outcome headline].** [One or two sentences.]
### Improved
- **[Short outcome headline].** [One sentence.]
### Fixed
- [One line per fix, written as what now works.]
### Needs confirmation (internal only — remove before publishing)
- [Item] — [what's unclear]Drop any section that has no items. If the person asks for a different channel (email, in-app banner, social post), keep the same sorting but shorten to the top one to three items.
Final check
Before handing it over:
- Every item traces back to something in the source.
- Nothing internal-only slipped in.
- A customer who reads only the bold headlines still gets the gist.
Related skills
- sprint-review-summary — the internal version of what shipped
- internal-enablement-brief — brief the field before the notes go out
- feature-flag-tracking — check what customers can actually see
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.

