agentleFS
45ck45ck/deployment-release-skills/.claude/skills/release-notes-writer/SKILL.md

release-notes-writer

Skill1 starsChanged 8 months agoMITView on GitHub

12 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 7

    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
  1. Distinctive:

    Write release notes that clearly communicate included changes, impacts, known issues, actions for users, and support expectations.

    line 12
  2. Distinctive:

    Prefer executable artifacts over broad process prose.

    line 53
  3. Distinctive:

    Keep the result usable in real runbooks, tickets, release docs, and repo workflows.

    line 55
  4. Distinctive:

    Do not confuse “mostly tested” with release safety.

    line 58
  5. Distinctive:

    Do not assume rollback works because it was written down once.

    line 59
  6. Distinctive:

    Do not hide configuration drift or approval gaps.

    line 60
  7. Distinctive:

    Do not optimize for release speed at the expense of operational recovery.

    line 61

“Common” is measured: kept by at least 6 in 10 of the 12 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

release-notes-writer

Purpose

Write release notes that clearly communicate included changes, impacts, known issues, actions for users, and support expectations.

Trigger this skill when

  • A release, deployment, rollout, cutover, or environment promotion needs explicit operational review.
  • You need deployment outputs that can feed engineering, operations, governance, or assessment work.
  • The delivery plan risks confusion between readiness signals and actual release safety.

Expected inputs

  • release scope
  • user-facing changes
  • technical changes
  • known issues
  • support/contact info

Deliverables

  • release notes
  • impact summary
  • upgrade actions
  • known limitations
  • support guidance

Operating procedure

  1. Clarify the release context, deployment path, change window, and operational constraints.
  2. Separate what is proven, tested, approved, or rehearsed from what is merely assumed.
  3. Produce the skill-specific artifact or review output.
  4. Surface risks, dependencies, timing gaps, ownership gaps, and rollback concerns explicitly.
  5. Recommend the next best handoff instead of trying to solve the entire release lifecycle at once.

Quality gates

  • The output is specific to the current release context.
  • Uncertainty, dependencies, and decision blockers are visible.
  • The result is usable by an engineering lead, release manager, SRE/ops owner, or assessment team.
  • Operational safety, not only delivery speed, is reflected in the recommendation.

Handoff targets

  • runbook-writer
  • post-release-monitoring-plan
  • go-live-readiness-reviewer

Output style

  • Be explicit about operational risk, timing, ownership, and reversibility.
  • Prefer executable artifacts over broad process prose.
  • Surface evidence gaps instead of inventing readiness.
  • Keep the result usable in real runbooks, tickets, release docs, and repo workflows.

Failure modes to avoid

  • Do not confuse “mostly tested” with release safety.
  • Do not assume rollback works because it was written down once.
  • Do not hide configuration drift or approval gaps.
  • Do not optimize for release speed at the expense of operational recovery.

Minimum output skeleton

## Summary
## Findings
## Structured outputs
## Risks / blockers
## Open questions
## Recommended next skill

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.