Version Release
NG-ZORRO/ng-zorro-antd
NG-ZORRO/ng-zorro-antd repository release workflow. An agent skill from NG-ZORRO/ng-zorro-antd.
Skill for compiling and writing release notes for langchain-azure packages.
Install Release Notes
$ npx skills add langchain-ai/langchain-azure --skill release-notes -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install langchain-ai/langchain-azure release-notes --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/langchain-ai/langchain-azure.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/release-notes .claude/skills/release-notes && rm -rf skills-srcUse ~/.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/
Install the "release-notes" agent skill from https://github.com/langchain-ai/langchain-azure/tree/main/.github/skills/release-notes into .claude/skills/release-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "release-notes", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/langchain-ai/langchain-azure/tree/main/.github/skills/release-notesType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add langchain-ai/langchain-azure --skill release-notes -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install langchain-ai/langchain-azure release-notes --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/langchain-ai/langchain-azure.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.github/skills/release-notes .agents/skills/release-notes && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "release-notes" agent skill from https://github.com/langchain-ai/langchain-azure/tree/main/.github/skills/release-notes into .agents/skills/release-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "release-notes", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add langchain-ai/langchain-azure --skill release-notes -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install langchain-ai/langchain-azure release-notes --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/langchain-ai/langchain-azure.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.github/skills/release-notes .cursor/skills/release-notes && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "release-notes" agent skill from https://github.com/langchain-ai/langchain-azure/tree/main/.github/skills/release-notes into .cursor/skills/release-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "release-notes", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/langchain-ai/langchain-azure.git --path .github/skills/release-notes--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add langchain-ai/langchain-azure --skill release-notes -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install langchain-ai/langchain-azure release-notes --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/langchain-ai/langchain-azure.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.github/skills/release-notes .gemini/skills/release-notes && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "release-notes" agent skill from https://github.com/langchain-ai/langchain-azure/tree/main/.github/skills/release-notes into .gemini/skills/release-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "release-notes", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install langchain-ai/langchain-azure release-notesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add langchain-ai/langchain-azure --skill release-notes -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/langchain-ai/langchain-azure.git skills-src && mkdir -p .github/skills && cp -r skills-src/.github/skills/release-notes .github/skills/release-notes && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "release-notes" agent skill from https://github.com/langchain-ai/langchain-azure/tree/main/.github/skills/release-notes into .github/skills/release-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "release-notes", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add langchain-ai/langchain-azure --skill release-notes -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install langchain-ai/langchain-azure release-notes --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/langchain-ai/langchain-azure.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.github/skills/release-notes .opencode/skills/release-notes && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "release-notes" agent skill from https://github.com/langchain-ai/langchain-azure/tree/main/.github/skills/release-notes into .opencode/skills/release-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "release-notes", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
release-notes- GitHub stars
- 147
- Token cost
- ~1.2k tokens
- SKILL.md length
- 459 words
- Files
- 1
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- MIT
At a glance
Skill for compiling and writing release notes for langchain-azure packages.
- Works in 4 steps: Identify the two release tags you are… → List the PRs merged between the two tags… → Write the release notes. For each… → …
- A new version of a package is being released and the README.md changelog section needs to be updated with a summary of merged PRs
- SKILL.md covers Required policy, How to compile release notes and What counts as a breaking change
- Calls gh and git
What it does
Release Notes is an agent skill from langchain-ai/langchain-azure, published by the product's own GitHub organization. Skill for compiling and writing release notes for langchain-azure packages. Use when a new version of a package is being released and the README.md changelog section needs to be updated with a summary of merged PRs.
Its SKILL.md is about 1.2k 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 and Building AI agents. It works with LangChain and Microsoft Azure. The repository describes itself as: Build secure LangChain applications on Azure. The licence is MIT.
When your agent uses it
- A new version of a package is being released and the README.md changelog section needs to be updated with a summary of merged PRs
- Tasks that involve Changelog and release notes
- Tasks that involve Building AI agents
Example prompts
- “/release-notes”
Requirements
- Python 3
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Identify the two release tags you are comparing. Tags follow the pattern ==, for example langchain-azure-ai==1.2.1. List available tags with
- List the PRs merged between the two tags using the GitHub CLI
- Write the release notes. For each meaningful PR (skip internal/CI-only changes), add a bullet using friendly, user-facing language. Follow…
- Update the package README.md. Add the new version entry at the top of the ## Changelog section
What it can do on your machine
Read from SKILL.md and the folder at commit 5784474. 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:
ghgit
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use gh and git, 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 Notes loads about 1.2k tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 459 words of instructions outside code blocks.
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 langchain-ai/langchain-azure at commit 5784474, republished under its MIT licence (© langchain-ai). 459 words, ~1,220 tokens.
Download SKILL.mdSave it as
.claude/skills/release-notes/SKILL.md (or your agent's skills folder).- name
- release-notes
- description
- Skill for compiling and writing release notes for langchain-azure packages. Use when a new version of a package is being released and the README.md changelog section needs to be updated with a summary of merged PRs.
- user-invocable
- true
Compiling Release Notes for langchain-azure Packages
Each package maintains a ## Changelog section in its README.md. When a new version is released, update that section with a concise, user-friendly summary of what changed.
Required policy
- ALWAYS append release notes as a new version entry at the top of the changelog.
- NEVER modify the content of previously published version entries.
How to compile release notes
Identify the two release tags you are comparing. Tags follow the pattern
<package>==<version>, for examplelangchain-azure-ai==1.2.1. List available tags with:bash gh release list --repo langchain-ai/langchain-azure # or git tag --list | grep langchain-azure-aiList the PRs merged between the two tags using the GitHub CLI:
bash # Get the commits between the two tags and look for merge commits git log <old-tag>..<new-tag> --oneline --merges # Or use the GitHub compare API to get a full list of commits gh api repos/langchain-ai/langchain-azure/compare/<old-tag>...<new-tag> \ --jq '.commits[].commit.message'You can also browse the merged PRs on GitHub directly by filtering by merge date range:
https://github.com/langchain-ai/langchain-azure/pulls?q=is%3Apr+is%3Amerged+merged%3A<start-date>..<end-date>+label%3A<package-label>Write the release notes. For each meaningful PR (skip internal/CI-only changes), add a bullet using friendly, user-facing language. Follow these conventions:
- Start sentences with "We" to keep a consistent, team-friendly voice (e.g., "We fixed a problem when loading class X").
- Use past tense ("We introduced", "We fixed", "We improved").
- Mark breaking changes with
**[Breaking change]:**. See what counts as a breaking change before applying this marker. - Mark new features with
**[NEW]**when the addition is significant. - Reference the PR number with a link, e.g.,
[#123](https://github.com/langchain-ai/langchain-azure/pull/123).
Update the package
README.md. Add the new version entry at the top of the## Changelogsection:markdown ## Changelog - **<new-version>**: - We fixed an issue with X. [#123](https://github.com/langchain-ai/langchain-azure/pull/123) - We introduced support for Y. [#124](https://github.com/langchain-ai/langchain-azure/pull/124) - **<previous-version>**: ...Do not edit existing entries for previously released versions; only append a new section for the release being prepared.
Each package's
README.mdis the source of truth for its changelog. The files to update are:Package README location langchain-azure-ailibs/azure-ai/README.mdlangchain-azure-computelibs/azure-compute/README.mdlangchain-azure-dynamic-sessionslibs/azure-dynamic-sessions/README.mdlangchain-sqlserverlibs/sqlserver/README.mdlangchain-azure-storagelibs/azure-storage/README.mdlangchain-azure-postgresqllibs/azure-postgresql/README.mdlangchain-azure-cosmosdblibs/azure-cosmosdb/README.md
Show full SKILL.md (191 more words)Show less
What counts as a breaking change
Apply **[Breaking change]:** only when a user's working code, on a runtime
that remains supported, stops working or changes behavior:
- Removing or renaming public API, or changing a signature, default, or return type.
- Changing runtime behavior so existing supported code produces a different result.
- Adding a newly required dependency or configuration that installed users must now supply.
Do not apply the marker to these:
- Raising the minimum supported Python version. This follows the
repository's Python support policy and changes no API or behavior on any
supported interpreter. The
requires-pythonmetadata makes older runtimes resolve to the previous release rather than install an incompatible one, so nothing breaks silently. State the impact in plain language instead, for example: "Users running Python 3.10 must upgrade their runtime to install this release." - Dropping a Python version that upstream has already end-of-lifed.
- Internal refactors, CI-only changes, or typing-only changes with no runtime effect.
A release whose only user-visible change is a support-policy update is a patch release. Labeling a patch bump as breaking contradicts the version being shipped, so match the marker to the version you are actually publishing.
© langchain-ai, MIT. 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 .github/skills/release-notes of langchain-ai/langchain-azure.
Open the folder on GitHubat commit 5784474
Compare with similar skills
Release Notes 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Release Notes this skilllangchain-ai/langchain-azure | 147 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Version ReleaseNG-ZORRO/ng-zorro-antd | 9.2k | — | ~3.1k | Automated safety check: Pass | MIT | |
| Code ReviewAzure/Azurite | 2.3k | — | ~734 | Automated safety check: Pass | MIT | |
| Add ModelPipelex/pipelex | 939 | — | ~2.7k | Automated safety check: Pass | Custom licence | |
| Azure App Configuration Release NotesAzure/AppConfiguration | 263 | — | ~3.1k | Automated safety check: Pass | MIT | |
| A2ui Release Pythona2ui-project/a2ui | 17k | — | ~4.2k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Code Review
Azure/Azurite
Review Azurite pull requests with service-aware checks for Blob, Queue, and Table behavior, API compatibility, tests, and release notes.
Add Model
Pipelex/pipelex
Add a new AI model to Pipelex's own inference configuration: the backend TOMLs in .pipelex/inference/backends/ (OpenAI, Azure, Anthropic, Bedrock, Google, Vertex, Mistral and the rest), the kit…
- Official
Azure App Configuration Release Notes
Azure/AppConfiguration
Writes customer-facing release notes for Azure App Configuration libraries and providers in a fixed file layout, version heading and category structure.
A2ui Release Python
a2ui-project/a2ui
Releases the Python SDKs (a2ui-core, a2ui-agent-sdk) to PyPI by running preflight checks, dispatching the release workflow as a dry run, confirming with the maintainer, publishing, and following the…
Commit
Magic-Resume/Magic-Resume
Write a Magic Resume commit message that passes the gitmoji + conventional-type lint.
More from langchain-ai/langchain-azure
- Official
Code Review
langchain-ai/langchain-azure
Reviews changes in the langchain-azure monorepo using package-specific knowledge of langchain-azure-ai, langchain-azure-compute, langchain-azure-cosmosdb, langchain-azure-postgresql…
Related
Works with
Categories
Questions about Release Notes
What does Release Notes do?
Skill for compiling and writing release notes for langchain-azure packages. Release Notes is an agent skill from langchain-ai/langchain-azure, published by the product's own GitHub organization. Skill for compiling and writing release notes for langchain-azure packages.
When should I use Release Notes?
Release Notes fits situations like: A new version of a package is being released and the README.md changelog section needs to be updated with a summary of merged PRs; tasks that involve Changelog and release notes; tasks that involve Building AI agents.
How do I install Release Notes in Claude Code?
Run `npx skills add langchain-ai/langchain-azure --skill release-notes -a claude-code`. Or copy the skill folder (.github/skills/release-notes in langchain-ai/langchain-azure) into .claude/skills/release-notes in your project. Claude Code loads it when a task matches its description.
How do I install Release Notes in Codex?
Run `npx skills add langchain-ai/langchain-azure --skill release-notes -a codex`. Or copy the skill folder (.github/skills/release-notes in langchain-ai/langchain-azure) into .agents/skills/release-notes in your project. Codex loads it when a task matches its description.
Can I use Release Notes 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 langchain-ai/langchain-azure --skill release-notes -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-notes, .gemini/skills/release-notes, .github/skills/release-notes and .opencode/skills/release-notes in your project.
What does Release Notes need to run?
Going by SKILL.md and its folder, Release Notes needs the command-line tools its instructions call (gh and git). Our summary lists: Python 3.
Does Release Notes access the network?
SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Release Notes 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 Notes use?
Release Notes is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Release Notes use?
About 1.2k tokens (SKILL.md is roughly 4.9k 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 Notes?
Skills that share tags, products or a category with Release Notes: Version Release (NG-ZORRO/ng-zorro-antd, 9.2k stars), Code Review (Azure/Azurite, 2.3k stars), Add Model (Pipelex/pipelex, 939 stars) and Azure App Configuration Release Notes (Azure/AppConfiguration, 263 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Release Notes?
langchain-ai (a GitHub organization, an official publisher) maintains it in langchain-ai/langchain-azure, which has 147 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 6, 2026.
Source: langchain-ai/langchain-azure on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.