Official agent skill

Changelog Cleanup

by snowflakedb in snowflakedb/snowflake-connector-nodejs

Analyze and clean up the Upcoming Release section in CHANGELOG.md.

OfficialApache-2.0Auto-check passedDevelopment

Install Changelog Cleanup

skills CLI
$ npx skills add snowflakedb/snowflake-connector-nodejs --skill changelog-cleanup -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install snowflakedb/snowflake-connector-nodejs changelog-cleanup --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/snowflakedb/snowflake-connector-nodejs.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.cursor/skills/changelog-cleanup .claude/skills/changelog-cleanup && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
changelog-cleanup
GitHub stars
143
Token cost
~1.7k tokens
SKILL.md length
747 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
Apache-2.0

At a glance

Analyze and clean up the Upcoming Release section in CHANGELOG.md.

  • Works in 2 steps: Grammar and Logic Review → Sort Entries into Sections
  • The user mentions changelog cleanup
  • SKILL.md covers Changelog structure, Phase 1: Grammar and Logic…, Phase 2: Sort Entries into… and Output format
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Changelog Cleanup is an agent skill from snowflakedb/snowflake-connector-nodejs, published by the product's own GitHub organization. Analyze and clean up the Upcoming Release section in CHANGELOG.md. Reviews each entry for grammar and logic issues, then sorts entries into named sections (New features, Changes, Bugfixes, Dependencies, Internal for non-customer-facing work, and Other as needed). Use when the user mentions changelog cleanup, changelog sorting, release notes review, or preparing a release.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Changelog and release notes. The licence is Apache-2.0.

When your agent uses it

  • The user mentions changelog cleanup
  • Changelog sorting
  • Release notes review
  • Preparing a release

Example prompts

  • “/changelog-cleanup”

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. Grammar and Logic Review
  2. Sort Entries into Sections

What it can do on your machine

Read from SKILL.md and the folder at commit dc60af1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Changelog Cleanup loads about 1.7k tokens when it runs. Until then it costs about 98 tokens; SKILL.md has 747 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~98
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from snowflakedb/snowflake-connector-nodejs at commit dc60af1, republished under its Apache-2.0 licence (© snowflakedb). 747 words, ~1,712 tokens.

Download SKILL.mdSave it as .claude/skills/changelog-cleanup/SKILL.md (or your agent's skills folder).
name
changelog-cleanup
description
Analyze and clean up the Upcoming Release section in CHANGELOG.md. Reviews each entry for grammar and logic issues, then sorts entries into named sections (New features, Changes, Bugfixes, Dependencies, Internal for non-customer-facing work, and Other as needed). Use when the user mentions changelog cleanup, changelog sorting, release notes review, or preparing a release.

Changelog Cleanup

Cleans up the ## Upcoming Release section of CHANGELOG.md in two phases: grammar/logic review, then sorting into named sections.

Changelog structure

Each release is a ## heading (e.g., ## Upcoming Release, ## 2.3.6). Within a release, entries are organized under named sections — plain-text labels followed by a colon, each followed by a blank line and then bullet entries. For ## Upcoming Release, use the section order defined in Phase 2 below. Older releases may use different section names (e.g., Deprecations:, Breaking changes:, Performance:) or the legacy flat list.

Example structure:

markdown
## 2.3.6

New features:

- Entry one

Changes:

- Entry two

Bugfixes:

- Entry three
- Entry four

Dependencies:

- Entry five

Internal:

- Entry visible only in Snowflake-internal or non-customer contexts (see below)

Older releases (before 2.3.6) use a legacy flat list of bullets with no named sections. That format is no longer valid for new releases.

Phase 1: Grammar and Logic Review

  1. Read CHANGELOG.md and extract all content under ## Upcoming Release (stop at the next ## heading).
  2. For each entry, check for:
    • Spelling and grammar mistakes
    • Unclear or ambiguous phrasing
    • Logical issues (e.g., an entry starting with "Fixed" that actually describes a new feature, or contradictory statements)
    • Entries placed under the wrong section (e.g., a bug fix listed under "New features:", or a customer-visible change under Internal:)
  3. When an issue is found, use the AskQuestion tool to present the proposed fix to the user. Provide two options: "Accept" and "Reject". Batch related fixes into a single AskQuestion call when possible to reduce round-trips, but keep each fix clearly labeled.
  4. Apply only accepted fixes. Do not modify entries the user rejects.

Phase 2: Sort Entries into Sections

After grammar/logic fixes are applied, sort entries into named sections. The five sections below are the defaults, but you may rename, split, or combine them when it makes the release easier for an end-user to scan — for example, Bugfixes and Performance: instead of a single Bugfixes: bucket. When proposing custom section names, use the AskQuestion tool to confirm them with the user.

Default sections, in this order:

Section 1 — New features:

Entries that semantically describe something new (e.g. Added), regardless of the leading verb.

Section 2 — Changes:

Entries that describe enhancing, changing, updating, removing, refactoring, or modifying existing behavior (e.g. Improved, Changed, Updated, Removed, Replaced), regardless of the leading verb. Dependency bumps belong in Dependencies: (see Section 4), not here.

Section 3 — Bugfixes:

Entries that semantically describe fixing incorrect behavior (e.g. Fixed), regardless of the leading verb.

Section 4 — Dependencies:

Customer-visible dependency changes: bumps (e.g. Bumped axios to ...), removals, replacements, or pins of third-party packages that ship to customers. Include CVE-driven bumps here. Omit this section if the release has no dependency changes.

Internal-only dependency or tooling changes (e.g. dev-dependency bumps, CI tooling) belong in Internal: instead.

Show full SKILL.md (316 more words)Show less
Section 5 — Internal:

Entries that do not affect end customers in any meaningful way: no change to public API, connection options, query behavior, error handling, packaging, or documented runtime for typical self-hosted or customer Snowflake workloads.

Use Internal: for Snowflake-internal execution contexts (e.g. driver behavior only when running inside SPCS or similar), internal-only request fields or telemetry that customers do not configure or observe, CI/release automation, or repo hygiene with zero customer-visible impact.

Do not put here: dependency bumps that address CVEs or change shipped binaries for customers, fixes to connection/auth/query bugs, or any feature a customer could rely on outside Snowflake-managed environments.

Example (from this repo’s changelog):

markdown
Internal:

- Included `spcs_token` when driver runs inside SPCS (org/repo#1372)
Section 6 — Other (custom name)

If there are entries that don't fit the five default sections above, or if the release would be clearer with different groupings (e.g., merging Bugfixes: and a perf cluster into Bugfixes and Performance:), use the AskQuestion tool to propose custom section names to the user.

Sorting rules
  • Use the first word after - as a signal, but override when the meaning clearly fits a different section.
  • Multi-line entries (parent + indented sub-bullets) stay as one unit.
  • Preserve original relative order within each section.
  • Omit sections that have no entries (don't output an empty section heading).
  • Each section heading is followed by a blank line, then its bullet entries.
  • Separate sections from each other with a blank line after the last bullet.
  • Entries must not end with a trailing period. Remove any trailing . from bullet entries for consistency (a trailing (...#1234) reference already has no period after it, so nothing to remove in that case).

Output format

The final output under ## Upcoming Release must use named sections with bullet entries. You may use the default section names or custom ones — whichever makes the release easiest for an end-user to understand at a glance.

Example with default sections:

markdown
## Upcoming Release

New features:

- Added support for OAuth tokens
- Added new `timeout` option

Changes:

- Improved error details when OAuth fails
- Changed default `jsonColumnVariantParser` to `JSON.parse`

Bugfixes:

- Fixed a crash when loading config
- Fixed typo in error message

Dependencies:

- Bumped axios to 1.15.1 to address CVE-2025-62718
- Dropped `uuid` dependency in favor of Node built-in `crypto.randomUUID()`

Internal:

- Included `spcs_token` when driver runs inside SPCS (org/repo#1372)

Example with custom sections (e.g., for a patch release):

markdown
## Upcoming Release

Bugfixes and Performance:

- Reduced peak memory usage when streaming large result sets
- Fixed a crash when loading config

Dependencies:

- Bumped axios to 1.15.1 to address CVE-2025-62718

Internal:

- Extended login-request telemetry to detect cloud VMs

© snowflakedb, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .cursor/skills/changelog-cleanup of snowflakedb/snowflake-connector-nodejs.

Open the folder on GitHubat commit dc60af1

Compare with similar skills

Changelog Cleanup next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Changelog Cleanup compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Changelog Cleanup this skillsnowflakedb/snowflake-connector-nodejs143—~1.7kAutomated safety check: PassApache-2.0
Simple Englishmoeru-ai/airi50k2 repos~4.6kAutomated safety check: PassMIT
StarRocks Release NotesStarRocks/starrocks12k—~1.9kAutomated safety check: NotesApache-2.0
Cutting A ReleaseTriliumNext/Trilium38k—~3.2kAutomated safety check: PassAGPL-3.0
Rea Changelog Updatemorluto/rea80k—~1.9kAutomated safety check: PassMIT
Mole CLI Release Flowtw93/Mole70k—~2.6kAutomated safety check: PassGPL-3.0

Similar skills

  • Simple English

    moeru-ai/airi

    Write or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop.

    50k GitHub starsUsed in 2 repos~4.6k tokens
    DevelopmentAuto-check passed
  • StarRocks Release Notes

    StarRocks/starrocks

    Drafts English release notes for a StarRocks patch release from the PRs merged into its release branch, then opens a documentation PR and hands translation to /translate.

    12k GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check: notes
  • Cutting A Release

    TriliumNext/Trilium

    A skill your agent uses when cutting, preparing, or debugging a Trilium release — bumping the monorepo version, tagging, or diagnosing a failed "Release" workflow run.

    38k GitHub stars~3.2k tokensUpdated today
    DevelopmentAuto-check passed
  • Prepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.

    80k GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Runbook for assessing and executing a Mole CLI release: distribution channels, pre-flight checks, capital-V tags, build artifacts and the handoff to curated release notes.

    70k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed
  • React Router Release Notes Prep

    remix-run/react-router

    Polishes pending React Router change files before the versioning scripts run, and decides whether a long-form What's Changed section is warranted.

    57k GitHub stars~1.1k tokensUpdated yesterday
    DevelopmentAuto-check passed

Categories

Questions about Changelog Cleanup

What does Changelog Cleanup do?

Analyze and clean up the Upcoming Release section in CHANGELOG.md. Changelog Cleanup is an agent skill from snowflakedb/snowflake-connector-nodejs, published by the product's own GitHub organization.md.

When should I use Changelog Cleanup?

Changelog Cleanup fits situations like: the user mentions changelog cleanup; changelog sorting; release notes review; preparing a release.

How do I install Changelog Cleanup in Claude Code?

Run `npx skills add snowflakedb/snowflake-connector-nodejs --skill changelog-cleanup -a claude-code`. Or copy the skill folder (.cursor/skills/changelog-cleanup in snowflakedb/snowflake-connector-nodejs) into .claude/skills/changelog-cleanup in your project. Claude Code loads it when a task matches its description.

How do I install Changelog Cleanup in Codex?

Run `npx skills add snowflakedb/snowflake-connector-nodejs --skill changelog-cleanup -a codex`. Or copy the skill folder (.cursor/skills/changelog-cleanup in snowflakedb/snowflake-connector-nodejs) into .agents/skills/changelog-cleanup in your project. Codex loads it when a task matches its description.

Can I use Changelog Cleanup in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add snowflakedb/snowflake-connector-nodejs --skill changelog-cleanup -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/changelog-cleanup, .gemini/skills/changelog-cleanup, .github/skills/changelog-cleanup and .opencode/skills/changelog-cleanup in your project.

What does Changelog Cleanup need to run?

SKILL.md names no scripts, command-line tools or credentials: Changelog Cleanup is instructions for the agent only.

Does Changelog Cleanup access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Changelog Cleanup safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Changelog Cleanup use?

Changelog Cleanup is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Changelog Cleanup use?

About 1.7k tokens (SKILL.md is roughly 6.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Changelog Cleanup?

Skills that share tags, products or a category with Changelog Cleanup: Simple English (moeru-ai/airi, 50k stars), StarRocks Release Notes (StarRocks/starrocks, 12k stars), Cutting A Release (TriliumNext/Trilium, 38k stars) and Rea Changelog Update (morluto/rea, 80k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Changelog Cleanup?

snowflakedb (a GitHub organization, an official publisher) maintains it in snowflakedb/snowflake-connector-nodejs, which has 143 GitHub stars. The repository was last updated on October 7, 2026.

Source: snowflakedb/snowflake-connector-nodejs on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.