>- Generates and formats changelog files for a new release based on provided version and raw changelog data.
npx skills add https://github.com/google-gemini/gemini-cli --skill docs-changelog
To standardize the process of updating changelog files (latest.md,
preview.md, index.md) based on automated release information.
v0.28.0,v0.29.0-preview.2).
2026-02-12T20:33:15Z).section and a "Full Changelog" link.
latest.md and preview.md Highlightschange (e.g., New Feature: A brief description...).
chores.
Stable Releases.
.gemini/skills/docs-changelog/references/highlights_examples.mdfor the correct style and tone.
versionstring.
version contains "nightly", STOP. No changes are made.version ends in .0, follow the Path A: New Minor Versionprocedure.
version does not end in .0, follow the Path B: Patch Versionprocedure.
TIME input into two formats for later use:yyyy-mm-dd and Month dd, yyyy.
BODY content to a temporary file for processing.request URLs to be markdown links with the PR number as the text (e.g.,
#12345).
temporary file will be used in subsequent steps.
*Use this path if the version number ends in .0.*
Important: Based on the version, you must choose to follow either section
A.1 for stable releases or A.2 for preview releases. Do not follow the
instructions for the other section.
v0.28.0)For a stable release, you will generate two distinct summaries from the
changelog: a concise announcement for the main changelog page, and a more
detailed highlights section for the release-specific page.
index.md:Each announcement entry must start with a bold-typed title that
summarizes the change.
use the existing announcements in docs/changelogs/index.md and the
example within
.gemini/skills/docs-changelog/references/index_template.md as your
guide. This format includes PR links and authors. Stick to 1 or 2 PR
links and authors.
docs/changelogs/index.md.latest.md:in the "Guidelines for latest.md and preview.md Highlights" section
above.
.gemini/skills/docs-changelog/references/latest_template.md.
version, release_date, generatedhighlights, and the processed content from the temporary file.
docs/changelogs/latest.md withthe populated template.
v0.29.0-preview.0)preview.md:guidelines.
.gemini/skills/docs-changelog/references/preview_template.md.
version, release_date, generatedhighlights, and the processed content from the temporary file.
docs/changelogs/preview.mdwith the populated template.
*Use this path if the version number does not end in .0.*
Important: Based on the version, you must choose to follow either section
B.1 for stable patches or B.2 for preview patches. Do not follow the
instructions for the other section.
v0.28.1)docs/changelogs/latest.md# Latest stable release: {{version}}
Released: {{release_date_month_dd_yyyy}}
If so, continue to step 4. Otherwise, skip to step 5.
to the existing "What's Changed" list in latest.md. Do not change or
replace the existing list, only add to the beginning of it.
last part of the URL that looks like ...{previous_version} and update
it to be ...{version}.
Example: assume the patch version is v0.29.1. Change
Full Changelog: https://github.com/google-gemini/gemini-cli/compare/v0.28.2…v0.29.0
to
Full Changelog: https://github.com/google-gemini/gemini-cli/compare/v0.28.2…v0.29.1
v0.29.0-preview.3)docs/changelogs/preview.md# Preview release: {{version}}
Released: {{release_date_month_dd_yyyy}}
If so, continue to step 4. Otherwise, skip to step 5.
to the existing "What's Changed" list in preview.md. Do not change or
replace the existing list, only add to the beginning of it.
last part of the URL that looks like ...{previous_version} and update
it to be ...{version}.
Example: assume the patch version is v0.29.0-preview.1. Change
Full Changelog: https://github.com/google-gemini/gemini-cli/compare/v0.28.2…v0.29.0-preview.0
to
Full Changelog: https://github.com/google-gemini/gemini-cli/compare/v0.28.2…v0.29.0-preview.1
npm run format fails, it may be necessary to runnpm install first to ensure all formatting dependencies are available.
Then, run npm run format to ensure consistency.
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take google-gemini/docs-changelog from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference npm.
Without those the skill loads but fails at the first command.