Agent skill

Release Changelog

by pipeshub-ai in pipeshub-ai/pipeshub-ai

Generate an enterprise-style changelog for a PipesHub GitHub release.

Apache-2.0Auto-check passedDevelopment

Install Release Changelog

skills CLI
$ npx skills add pipeshub-ai/pipeshub-ai --skill release-changelog -a claude-code

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

GitHub CLI
$ gh skill install pipeshub-ai/pipeshub-ai release-changelog --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/pipeshub-ai/pipeshub-ai.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/release-changelog .claude/skills/release-changelog && 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
release-changelog
GitHub stars
3.8k
Token cost
~2.7k tokens
SKILL.md length
965 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
Apache-2.0

At a glance

Generate an enterprise-style changelog for a PipesHub GitHub release.

  • Works in 6 steps: Resolve the release → Understand the material → Write the detailed changelog file → …
  • Tasks that involve Changelog and release notes
  • SKILL.md covers Step 1 — Resolve the release, Step 2 — Understand the material, Step 3 — Write the detailed… and Step 4 — Maintain the folder…, plus 2 more sections
  • Calls gh

What it does

Release Changelog is an agent skill from pipeshub-ai/pipeshub-ai. Generate an enterprise-style changelog for a PipesHub GitHub release. Takes a release URL or tag (e.g. https://github.com/pipeshub-ai/pipeshub-ai/releases/tag/v0.5.0 or v0.5.0), writes the detailed per-release changelog to changelog/<version.md, and registers it in the repo-root CHANGELOG.md (condensed entry + link) and the changelog/README.md index.

Its SKILL.md is about 2.7k 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. It works with GitHub, Model Context Protocol, Python and Redis. The repository describes itself as: The open-source context layer for AI agents. PipesHub turns your company's knowledge (Slack, Drive, Jira, GitHub, Microsoft 365 and 40+ connectors) into a permission-aware… The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Changelog and release notes

Example prompts

  • “/release-changelog”

Requirements

  • Python 3
  • Node.js
  • Docker

Workflow steps

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

  1. Resolve the release
  2. Understand the material
  3. Write the detailed changelog file
  4. Maintain the folder index
  5. Register the release in the root CHANGELOG.md
  6. Report

What it can do on your machine

Read from SKILL.md and the folder at commit 75eb65c. 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

    Shell commands in SKILL.md call:

    • gh

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

  • Network

    No URLs in SKILL.md. Its commands use gh, which can reach the network depending on how they are called.

    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

Release Changelog loads about 2.7k tokens when it runs. Until then it costs about 93 tokens; SKILL.md has 965 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~93
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k

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 pipeshub-ai/pipeshub-ai at commit 75eb65c, republished under its Apache-2.0 licence (© pipeshub-ai). 965 words, ~2,725 tokens.

Download SKILL.mdSave it as .claude/skills/release-changelog/SKILL.md (or your agent's skills folder).
name
release-changelog
description
Generate an enterprise-style changelog for a PipesHub GitHub release. Takes a release URL or tag (e.g. https://github.com/pipeshub-ai/pipeshub-ai/releases/tag/v0.5.0 or v0.5.0), writes the detailed per-release changelog to changelog/<version>.md, and registers it in the repo-root CHANGELOG.md (condensed entry + link) and the changelog/README.md index.
argument-hint
<release-url-or-tag>

Release Changelog Generator

Turn a raw GitHub release (auto-generated "What's Changed" PR list) into a curated, enterprise-grade changelog. The style is a hybrid of Linear (strong narrative headline + explained highlights) and Keep a Changelog (categorized, scannable sections), tuned for developers and operators who self-host PipesHub.

Two artifacts, one source of truth each way:

  • changelog/<version>.md — the detailed per-release changelog (every PR represented, authors credited).
  • CHANGELOG.md at the repo root — the registry: one condensed entry per release, newest first, each linking to its detailed file. (changelog/README.md keeps a one-row-per-release index table for folder browsing.)

Step 1 — Resolve the release

The argument is a GitHub release URL or a bare tag.

  • From a URL like https://github.com/pipeshub-ai/pipeshub-ai/releases/tag/v0.5.0, the tag is the last path segment.
  • Tags are inconsistent: some have a v prefix (v0.5.0), some don't (0.1.0-beta). If gh release view fails with the given form, retry with the prefix toggled.

Fetch the release:

bash
gh release view <tag> --repo pipeshub-ai/pipeshub-ai --json tagName,name,publishedAt,isPrerelease,body

If the body is large, save it to a scratch file first and read it from there — never summarize from a truncated body. Read the ENTIRE body before writing anything.

Step 2 — Understand the material

The body is mostly * <PR title> by @author in <PR url> lines, possibly with a "New Contributors" section and a "Full Changelog: ...compare..." link. PR titles are terse; interpret them using this architecture context:

PipesHub is a workplace AI platform (enterprise search + agent workflows). Polyglot system: Python FastAPI microservices (Connectors :8088, Indexing :8091, Query/RAG :8000, Docling parsing :8081, Embedding :8002, Parsing :8092, Extraction :8093), 1 Node.js Express API (auth/users/knowledge-base/storage), a React/Next.js frontend, and an Electron desktop app. Stateful backends are pluggable: graph (Neo4j/ArangoDB), vector (Qdrant/OpenSearch/Redis), MongoDB, KV (Redis/etcd), broker (Kafka/Redis Streams). 30+ enterprise connectors (Google Workspace, Microsoft 365, Slack, Jira, Confluence, GitLab, Notion, Salesforce, Zoom, OneDrive, Outlook, SharePoint, S3, local filesystem…). AI layer: RAG pipeline, agent loop and toolsets, MCP server, LiteLLM orchestration, knowledge graphs.

For the 4–7 PRs that anchor the Highlights section, you may enrich with:

bash
gh pr view <num> --repo pipeshub-ai/pipeshub-ai --json title,body

Limit to ~8 such lookups per release; spend them on the biggest features.

Step 3 — Write the detailed changelog file

Output path: changelog/<version>.md at the repo root, where <version> is the tag without any v prefix (0.5.0.md, 0.4.0-beta.2.md). Create the directory if needed.

File format (follow exactly)
markdown
# <version> — <Punchy headline conveying the main gist of the release>

**Released:** <Month D, YYYY> · **Channel:** <Stable | Beta | Alpha | Pre-release> · **Tag:** [`<tag>`](https://github.com/pipeshub-ai/pipeshub-ai/releases/tag/<tag>)

<1–2 paragraph narrative summary: the themes of the release and what an
operator/developer gets by upgrading. Concrete, plain language, no hype.
Mention scale honestly (e.g. "120+ merged PRs").>

## Highlights

### <Major feature/theme 1>

<2–5 sentences: what it is, the problem it solves, operational implications.
Cite PRs inline: ([#2223](https://github.com/pipeshub-ai/pipeshub-ai/pull/2223) — @jatingaur18).>

### <Major feature/theme 2>
…
(3–7 highlights for large releases; 1–3 for small patch releases)

## Breaking changes & upgrade notes

<ONLY if PR titles clearly imply breaking/behavioral changes, port/config changes,
removals, or migrations. Otherwise omit the section entirely.>

## Connectors

- **<Connector name>** — <merged description of all its PRs this release> ([#N](link), [#M](link))

## Agents & AI

- <RAG, agents, tools, LLM, embedding, indexing, citations, prompts…> ([#N](link))

## Fixes

- <bug fixes not already covered above; merge duplicate/follow-up-fix PRs into one bullet> ([#N](link), [#M](link))

## Performance & reliability

- <perf, memory leaks, DB indexes, deadlocks, race conditions, rate limits> ([#N](link))

## Security & authentication

- <auth, SAML, JWT, OAuth, encryption, input validation> ([#N](link))

## Developer experience & infrastructure

- <CI, tests, docker, builds, SDK/OpenAPI spec, logging, docs> ([#N](link))

## New contributors

- @handle made their first contribution in [#N](link)
(only if the raw notes have a "New Contributors" section)

---

*Full commit-level detail: [GitHub release](<release url>) · [Compare view](<compare url from raw notes, if present>)*
Rules
  1. Every PR in the raw notes must be represented — in Highlights or a category bullet. Merging related PRs into one bullet is encouraged (cite all their numbers). Never silently drop a PR. Trivial CI churn may collapse into one bullet citing many numbers. Exception: for a founding release whose body enumerates the project's entire initial history (body > 50 KB), a thematic treatment with representative PR citations is allowed — but keep the full New Contributors list.
  2. Do not fabricate. Derive descriptions from PR titles and the architecture context. If a title is cryptic, describe it conservatively rather than guessing at specifics.
  3. Credit authors with @handle on highlights and notable bullets; keep credits wherever the raw notes name one clear author.
  4. The H1 headline must convey the release's single biggest story — e.g. "0.5.0 — Salesforce and GitLab connectors mature, agents get file tools". Never generic ("Bug fixes and improvements") unless the release truly is only that.
  5. Omit empty sections. Bullets are 1–2 sentences, sentence case.
  6. PR links always as [#1234](https://github.com/pipeshub-ai/pipeshub-ai/pull/1234).
  7. For a pre-release later finalized by a stable release, add one line under the metadata line: *This beta was finalized as [0.4.0](0.4.0.md).* (link the sibling file if it exists).
  8. Humanize the date from publishedAt (ISO 8601 UTC).
  9. Channel: Stable for plain semver tags; Beta/Alpha per the tag suffix; trust the isPrerelease field for GitHub's own marking.
Show full SKILL.md (363 more words)Show less

Step 4 — Maintain the folder index

If changelog/README.md exists, insert/update this release's row (newest first): | [<version>](<version>.md) | <date> | <channel> | <H1 headline text> | under the columns Version | Date | Channel | Summary. If it doesn't exist, create it with a short intro ("Curated changelogs for PipesHub releases, newest first.") and that table.

Step 5 — Register the release in the root CHANGELOG.md

CHANGELOG.md at the repo root is the registry of all releases, newest first — condensed entries only; the changelog/<version>.md file stays the detailed record. Make two insertions:

  1. A new row in the index table, in release-date order (at the top, just under the header row, when this is the newest release): | [<version>](#<anchor>) | <Mon D, YYYY> | <Channel> | <short theme, ≤8 words> |
  2. The new release entry, ending with its own ---, in release-date order: directly below the ## Unreleased section (after its --- separator) when this is the newest release, so the previous newest slides down; otherwise just below the next-newer release's entry.
  3. Refresh the ## Unreleased compare link to start from the newest published release's tag (the new tag, unless you are writing an older release): [<tag>...HEAD](https://github.com/pipeshub-ai/pipeshub-ai/compare/<tag>...HEAD).

If the file doesn't exist, create it with this skeleton before inserting:

markdown
# PipesHub Changelog

All notable changes to [PipesHub](https://github.com/pipeshub-ai/pipeshub-ai) — the workplace AI platform for enterprise search and agent workflows — documented in one place, newest first.

This file is the release registry: each entry is a condensed summary linking to the detailed per-release changelog in [`changelog/`](changelog/) (full PR-level accounting and author credits) and to the raw GitHub release. Versioning follows semver; **Stable** releases are recommended for production, **Beta/Alpha** channels preview the next stable.

| Version | Date | Channel | Theme |
|---|---|---|---|

---

## Unreleased

Changes merged to `main` since the last release: [`<tag>...HEAD`](https://github.com/pipeshub-ai/pipeshub-ai/compare/<tag>...HEAD).

---

*Maintained with the `release-changelog` skill (`.claude/skills/release-changelog/SKILL.md`). Detailed per-release changelogs live in [`changelog/`](changelog/).*
Entry format (follow exactly)
markdown
## <version> — <YYYY-MM-DD>

**<H1 headline from the detailed file>** · <Channel> · [`<tag>`](https://github.com/pipeshub-ai/pipeshub-ai/releases/tag/<tag>) · [Full changelog](changelog/<version>.md)

<One- or two-sentence narrative: scale ("~195 PRs since 0.5.0") and theme.>

### Added
- <condensed bullet, citing only the 1–3 anchor PRs> ([#N](link))

### Changed
### Fixed
### Security
### Breaking changes & upgrade notes

Use only the sections that apply; 3–10 bullets total, distilled from the detailed file's Highlights and Breaking sections — do not re-enumerate every PR. Always keep the Breaking section when the detailed file has one.

  • Pre-releases: append · *Finalized as [<stable>](#<anchor>)* to the metadata line once the stable ships; when writing the stable entry for a cycle that had a pre-release, add that pointer to the existing pre-release entry and open the stable narrative with "Finalizes <pre> …".
  • Anchors: GitHub's slug of the H2 — lowercase, dots and the em dash removed, spaces become hyphens (## 0.4.0-beta.2 — 2026-05-02 → #040-beta2--2026-05-02). Verify the new index row's link matches the heading you actually wrote.
  • Never rewrite existing registry entries except the pre-release pointer above, and this release's own row and entry when it is regenerated (update them in place).

Step 6 — Report

Reply with the detailed file path, the H1 headline chosen, a one-line theme summary, and confirmation that changelog/README.md and the root CHANGELOG.md were updated. Do not paste the whole file into chat.

© pipeshub-ai, 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 .claude/skills/release-changelog of pipeshub-ai/pipeshub-ai.

Open the folder on GitHubat commit 75eb65c

Compare with similar skills

Release Changelog 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.

Release Changelog compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Release Changelog this skillpipeshub-ai/pipeshub-ai3.8k—~2.7kAutomated safety check: PassApache-2.0
Pre ReleaseZhuoZhuoCrayon/throttled-py651—~1.1kAutomated safety check: PassMIT
Os ReleaseCronusL-1141/AI-company371—~2.3kAutomated safety check: PassMIT
Rea Changelog Updatemorluto/rea80k—~1.9kAutomated safety check: PassMIT
Go-Redis Release Preparationredis/go-redis22k—~1.1kAutomated safety check: PassBSD-2-Clause
pybind11 Release Publicationpybind/pybind1118k—~2.5kAutomated safety check: PassCustom licence

Similar skills

  • Pre Release

    ZhuoZhuoCrayon/throttled-py

    Automates release preparation for throttled-py. An agent skill from ZhuoZhuoCrayon/throttled-py.

    651 GitHub stars~1.1k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Os Release

    CronusL-1141/AI-company

    发布 AI Team OS 新版本的完整清单——预检、版本七处锁步、中英双语 CHANGELOG、双份 dist 构建、私有术语扫描、commit/tag、双仓推送、建 GitHub Release 条目并核对 latest 徽章、事后核对。当准备发版、补建漏掉的 Release 条目、或核对已发版本的线上状态时使用。

    371 GitHub stars~2.3k tokensUpdated yesterday
    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
  • Official

    Prepares a go-redis release locally: picks the next semver, gathers merged PRs, writes the RELEASE-NOTES entry and bumps versions, without publishing.

    22k GitHub stars~1.1k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Walks a maintainer through publishing a pybind11 release after the preparation PR merges, with preflight checks, confirmations before each push and a GitHub release.

    18k GitHub stars~2.5k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Builds categorized release notes for a Plane release pull request from its commits and writes them into the PR description, for both the plane-cloud and plane-ee repos.

    61k GitHub stars~2.5k tokensUpdated 2 days ago
    DevelopmentAuto-check passed

More from pipeshub-ai/pipeshub-ai

All 9 skills in this repo
  • PipesHub Excel Spreadsheet Builder

    pipeshub-ai/pipeshub-ai

    Creates and edits .xlsx workbooks with real Excel formulas rather than hardcoded computed values, defaulting to exceljs in TypeScript with a static formula-safety check.

    3.8k GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Office Open XML Utilities

    pipeshub-ai/pipeshub-ai

    Unpacks a .docx or .pptx into pretty-printed XML, lets you make small targeted edits, and repacks it into a file Office will open.

    3.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Picks the right library for generating a new PDF, filling an existing PDF form, or extracting text and tables, defaulting to Node where possible.

    3.8k GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • PowerPoint Deck Builder

    pipeshub-ai/pipeshub-ai

    Creates new PowerPoint decks with pptxgenjs in TypeScript, reads existing decks with python-pptx, and applies a design-quality checklist so every slide has real visual hierarchy.

    3.8k GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • Verified Data Analysis with pandas

    pipeshub-ai/pipeshub-ai

    Loads, cleans, aggregates and joins tabular data with pandas under a verification rule: every number reported must be one that the code actually printed.

    3.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Chart Type Selection Guide

    pipeshub-ai/pipeshub-ai

    Picks the right chart type for a data question and applies readability rules like axis labels, colorblind palettes and legend restraint.

    3.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

Categories

Questions about Release Changelog

What does Release Changelog do?

Generate an enterprise-style changelog for a PipesHub GitHub release. Release Changelog is an agent skill from pipeshub-ai/pipeshub-ai. Generate an enterprise-style changelog for a PipesHub GitHub release.

When should I use Release Changelog?

Release Changelog fits situations like: tasks that involve Changelog and release notes.

How do I install Release Changelog in Claude Code?

Run `npx skills add pipeshub-ai/pipeshub-ai --skill release-changelog -a claude-code`. Or copy the skill folder (.claude/skills/release-changelog in pipeshub-ai/pipeshub-ai) into .claude/skills/release-changelog in your project. Claude Code loads it when a task matches its description.

How do I install Release Changelog in Codex?

Run `npx skills add pipeshub-ai/pipeshub-ai --skill release-changelog -a codex`. Or copy the skill folder (.claude/skills/release-changelog in pipeshub-ai/pipeshub-ai) into .agents/skills/release-changelog in your project. Codex loads it when a task matches its description.

Can I use Release Changelog 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 pipeshub-ai/pipeshub-ai --skill release-changelog -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/release-changelog, .gemini/skills/release-changelog, .github/skills/release-changelog and .opencode/skills/release-changelog in your project.

What does Release Changelog need to run?

Going by SKILL.md and its folder, Release Changelog needs the command-line tools its instructions call (gh). Our summary lists: Python 3; Node.js; Docker.

Does Release Changelog access the network?

SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Release Changelog 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 Release Changelog use?

Release Changelog 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 Release Changelog use?

About 2.7k tokens (SKILL.md is roughly 11k 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 Release Changelog?

Skills that share tags, products or a category with Release Changelog: Pre Release (ZhuoZhuoCrayon/throttled-py, 651 stars), Os Release (CronusL-1141/AI-company, 371 stars), Rea Changelog Update (morluto/rea, 80k stars) and Go-Redis Release Preparation (redis/go-redis, 22k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Release Changelog?

pipeshub-ai (a GitHub organization) maintains it in pipeshub-ai/pipeshub-ai, which has 3,827 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 11, 2026.

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