changelog-scribe
Generate and maintain a Keep a Changelog style CHANGELOG.md from Conventional Commits, grouped by type with correct semver headings.
Skill by anton-abyzov
Chalk Labs
Need help deploying changelog-scribe?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/anton-abyzov-changelog-scribe
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/changelog-scribe
What's inside
- Skill name
changelog-scribe- Description
- Generate and maintain a Keep a Changelog style CHANGELOG.md from Conventional Commits, grouped by type with correct semver headings.
- License
- MIT
- Instructions
- 80 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# changelog-scribe Produce a human-readable `CHANGELOG.md` that follows the [Keep a Changelog](https://keepachangelog.com) convention, derived from commit history and grouped for release notes. ## Structure Newest release on top. Keep an `## [Unreleased]` section for work not yet shipped. ```markdown # Changelog All notable changes to this project are documented here. The format is based on Keep a Changelog, and this project adheres to Semantic Versioning. ## [Unreleased] ## [1.5.0] - 2026-06-10 ### Added - Refresh-token rotation for the auth service (#482). ### Fixed - Pagination off-by-one on the search endpoint (#491). ### Security - Reject expired refresh tokens issued before this release. [Unreleased]: https://example.com/repo/compare/v1.5.0...HEAD [1.5.0]: https://example.com/repo/compare/v1.4.0...v1.5.0 ``` ## Section categories | Heading | Source commit types | Notes | |--------------|------------------------------------|-----------------------------| | `Added` | `feat` | new capabilities | | `Changed` | `refactor`, `perf`, behavior shifts| existing behavior changed | | `Deprecated` | commits noting deprecation | still works, will be removed| | `Removed` | removals | gone this release | | `Fixed` | `fix` | bug fixes | | `Security` | `fix` with security impact, CVEs | call these out explicitly | `docs`, `test`, `build`, `ci`, and `chore` commits are normally omitted from user-facing notes unless they change behavior. ## Building an entry from commits 1. Collect commits since the last tag: `git log v1.4.0..HEAD --pretty='%s%n%b'`. 2. Parse each Conventional Commit header into `(type, scope, description)`. 3. Map the type to a section above. 4. Rewrite the description for a reader who did not see the diff: expand jargon, keep it one line, link the PR/issue. 5. Surface `BREAKING CHANGE:` footers prominently — a bold note under the version heading and a `### Changed` / `### Removed` entry. ## Choosing the next version - Any breaking change → bump **major**. - Otherwise any `feat` → bump **minor**. - Otherwise (only `fix`/`perf`) → bump **patch**. ## Style rules - Imperative, present tense: "Add", not "Added a thing" in the bullet body. - One bullet per user-visible change; group trivial commits. - Always include the date in `YYYY-MM-DD` and the comparison link footer. - Never invent entries. If a commit is unclear, ask or read the diff — do not guess what it shipped. ## Agent guidance - Move `## [Unreleased]` content into the new version block on release; leave a fresh empty `## [Unreleased]` behind. - Keep the bottom-of-file link references in sync with each new tag. - If commits are not Conventional, infer category from the diff but flag that the history should adopt Conventional Commits going forward.
From anton-abyzov/vskill-test-public-skills-826, MIT.
More from anton-abyzov/vskill-test-public-skills-826
- 0.551score
private-skill-sharing-review
anton-abyzov
Review a proposed sharing or publishing workflow for a private AI skill using supplied repository visibility and authorization details.
SkillAFreshness: AClaude Code +9 - 0.551score
skill-inventory-drift
anton-abyzov
Compare supplied AI skill inventories from two machines or agents by source identity, version, content hash and installation scope.
SkillAFreshness: AClaude Code +9 - 0.551score
release-evidence-review
anton-abyzov
Review supplied software release receipts and state exactly which source, test, deployment, installation and runtime claims they support.
SkillAFreshness: AClaude Code +9 - 0.471score
dockerfile-hardening-guide
anton-abyzov
Harden Dockerfiles for security and size — non-root users, pinned bases, multi-stage builds, minimal layers, and supply-chain hygiene.
SkillCFreshness: CClaude Code +9 - 0.471score
git-bisect-detective
anton-abyzov
Drive git bisect to find the exact commit that introduced a regression, including automated test scripts and merge-commit handling.
SkillCFreshness: CClaude Code +9 - 0.471score
http-api-mock-forge
anton-abyzov
Stand up deterministic HTTP API mocks for tests and local dev using MSW, Nock, or Prism — request matching, stateful handlers, and contract fidelity.
SkillCFreshness: CClaude Code +9 - 0.471score
scanner-tripwire-fixture
anton-abyzov
DELIBERATE security-scanner test fixture — contains intentionally dangerous patterns (curl-pipe-bash, env-var exfiltration).
SkillCFreshness: CClaude Code +9 - 0.471score
oss-dependency-triage
anton-abyzov
Triage third-party dependencies before adoption — maintenance health, security advisories, supply-chain risk, and a go/no-go scoring rubric.
SkillCFreshness: CClaude Code +9 - 0.471score
sql-query-review-lens
anton-abyzov
Review SQL queries for correctness, performance, and safety — index usage, N+1 patterns, injection risk, and EXPLAIN-driven tuning.
SkillCFreshness: CClaude Code +9 - 0.471score
oss-license-auditor
anton-abyzov
Audit a project's dependency licenses for compatibility and obligations — copyleft detection, license allowlists, and SPDX-based reporting.
SkillCFreshness: CClaude Code +9 - 0.471score
conventional-commits-gatekeeper
anton-abyzov
Enforce and author Conventional Commits messages, validate commit history, and map commit types to semantic-version bumps.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 10, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from anton-abyzov
- 0.783score
glossary
anton-abyzov
Build the shared language - interview the user term by term and write GLOSSARY.md with what each term means in the business, the data, the code and the UI.
SkillAFreshness: A★ 167Claude Code +9 - 0.783score
sw-grill-me
anton-abyzov
Interview the user relentlessly, in rounds, until every decision in a plan is settled; facts are your job, decisions are theirs.
SkillAFreshness: A★ 167Claude Code +9 - 0.783score
grill-me
anton-abyzov
Interview the user relentlessly, in rounds, until every decision in a plan is settled; facts are your job, decisions are theirs.
SkillAFreshness: A★ 167Claude Code +9 - 0.783score
sw-glossary
anton-abyzov
Build the shared language - interview the user term by term and write GLOSSARY.md with what each term means in the business, the data, the code and the UI.
SkillAFreshness: A★ 167Claude Code +9 - 0.781score
handoff
anton-abyzov
Hand work to another tool, account or machine and pick it up there, in two words.
SkillAFreshness: A★ 167Claude Code +9 - 0.781score
sw-handoff
anton-abyzov
Hand work to another tool, account or machine and pick it up there, in two words.
SkillAFreshness: A★ 167Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get changelog-scribe running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
changelog-scribe skill. Agent Mart. https://agentmart.dev/skills/anton-abyzov-changelog-scribe (last updated 2026-10-24)