agentleFS
aptitude-stackaptitude-stack/registery/.agents/skills/changelog-writer/SKILL.md

changelog-writer

Skill1 starsChanged 8 months agoMITView on GitHub

Write concise architecture-focused milestone changelogs for implementation work. Use when a user asks to document what was delivered, include Mermaid diagrams, present DB schema in tables with clear field roles, and add links to relevant files/endpoints/tests.

21 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use regex-builder, test-writer and 1 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.
  • jMertaSkill

    regex-builder

    Use when the user asks to create, debug, explain, validate, or optimize a regular expression or replacement for a specific engine. Verifies representative matches, non-matches, captures, escaping, portability limits, and backtracking risk in the target runtime.

    Also in 3 projects that use this

  • leonardomsoSkill

    test-writer

    Generate comprehensive Vitest tests for code examples in JavaScript concept documentation pages, following project conventions and referencing source lines

    Also in 5 projects that use this

  • glinckerSkill

    readme-generator

    Generates comprehensive README.md files for software projects by analyzing codebase structure

    Also in 6 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

15 rules. 0 are common, 12 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 19 edited versions we read keep these.

  • 12

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Write changelogs in the same style as project milestone changelogs under docs/changelog/.

    line 8
  2. Distinctive:

    Read the target plan/spec and implementation files before drafting.

    line 12
  3. Distinctive:

    Verify every major claim has at least one file link.

    line 15
  4. Distinctive:

    Keep writing concise and technical.

    line 19
  5. Distinctive:

    Use Markdown links to concrete repo-relative paths for routes, services, models, migrations, tests, and plans.

    line 20
  6. Distinctive:

    Prefer repo-relative links by default.

    line 21
  7. Very specific:

    Never use machine-specific absolute filesystem paths such as /path/to/repo/....

    line 22
  8. Distinctive:

    Add a schema section with Markdown tables.

    line 24
  9. Distinctive:

    Call out key tradeoffs and limits without repeating obvious code details.

    line 25
  10. Distinctive:

    Avoid invented behavior; only document what is implemented.

    line 26
  11. Distinctive:

    Prefer deep links to the most specific file that proves the point.

    line 39
  12. Distinctive:

    When useful, include multiple links per bullet (API + core + persistence + test).

    line 40
  13. Distinctive:

    Keep link lists short and relevant.

    line 41
  14. Distinctive:

    Keep every link portable across machines by using repo-relative paths or GitHub URLs only.

    line 42
  15. Very specific:

    Use references/changelog-template.md as the starting structure and adapt headings to the milestone.

    line 46

“Common” is measured: kept by at least 6 in 10 of the 19 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

Changelog Writer

Write changelogs in the same style as project milestone changelogs under docs/changelog/.

Workflow

  1. Read the target plan/spec and implementation files before drafting.
  2. Map each delivered behavior to concrete code links.
  3. Draft a concise changelog using the template in references/changelog-template.md.
  4. Verify every major claim has at least one file link.

Output Rules

  • Keep writing concise and technical; prefer bullets over long paragraphs.
  • Use Markdown links to concrete repo-relative paths for routes, services, models, migrations, tests, and plans.
  • Prefer repo-relative links by default; GitHub links are acceptable when a hosted deep link is more useful.
  • Never use machine-specific absolute filesystem paths such as /path/to/repo/....
  • Include at least one Mermaid diagram (flowchart or sequenceDiagram) that reflects the real implementation.
  • Add a schema section with Markdown tables. Each table row must explain field purpose, not only type.
  • Call out key tradeoffs and limits without repeating obvious code details.
  • Avoid invented behavior; only document what is implemented.

Minimum Sections

  1. Title + short intro linking the milestone plan/spec.
  2. Scope Delivered.
  3. Architecture / Flow (Mermaid).
  4. Design Notes (major decisions and rationale).
  5. Schema Reference (table format with clear explanations).
  6. Verification Notes (tests or checks).

Link Quality

  • Prefer deep links to the most specific file that proves the point.
  • When useful, include multiple links per bullet (API + core + persistence + test).
  • Keep link lists short and relevant.
  • Keep every link portable across machines by using repo-relative paths or GitHub URLs only.

Reusable Template

Use references/changelog-template.md as the starting structure and adapt headings to the milestone.

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.