mrkeyoor.com_
Sat 12 Sept 15:47 UTC
LLM Toolsevaluationupdated 12 Sept 2026

gemini-skills review

Gemini Skills is a set of instruction files and helper scripts that teaches coding agents how to use current Gemini APIs and SDKs. It covers ordinary API work, live audio and video sessions, and Gemini Omni video generation so an agent is less likely to produce code from outdated model knowledge.

Verdict

Our lab could not execute commit 80dd31d because the Python repository had no supported entry point and no Dockerfile, so there is no install or test outcome to back the instructions. The skills are worth adding for developers who already chose Gemini and will pin, inspect, and refresh them. Treat Google's 117-prompt evaluation as vendor evidence, and keep official documentation plus application tests as the final authority.

We ran it

Screenshot of gemini-skills (ai.google.dev/gemini-api/docs)

Answers from our run

Did you run gemini-skills yourself?

No. Its code is Python, and it carries no manifest our lab installs from, and no Dockerfile, so there was nothing standard to install, build or test. This review is written from the repository's own documentation.

Who should not use gemini-skills?

Organizations that require an officially supported Google product: the README explicitly says this repository is not one and is ineligible for Google's open-source vulnerability rewards program.

What are the alternatives to gemini-skills?

Google Skills, Anthropic Skills, Context7. Our lab could not execute commit 80dd31d because the Python repository had no supported entry point and no Dockerfile, so there is no install or test outcome to back the instructions.

Setup3/56 install paths, but API credentials and toolchain needs remain
Docs5/53 focused skills give specific limits, examples, and source links
Community4/54,096 stars, 9 issues and PRs, and a push one day ago
Maturity3/5Version 2.1.0 is active, but there are no tagged releases

Who it’s for

Developers using Claude Code, Codex, Cursor, Antigravity, or another skill-aware agent to build against Gemini.
Teams migrating old Gemini SDK or model examples and willing to check the official docs before accepting generated code.
Voice and video developers who need concrete Live API formats, session limits, and event-handling rules in the agent's context.
Gemini Omni users who want maintained scripts for media upload, inspection, preparation, generation, editing, and extension.

Who it’s NOT for

Organizations that require an officially supported Google product: the README explicitly says this repository is not one and is ineligible for Google's open-source vulnerability rewards program.
Teams that need a repeatable local verification result before adoption: our lab found no supported execution path and no Dockerfile, so it produced no install, build, test, dependency, or audit result.
Vertex AI developers looking for the old skill here: the README says vertex-ai-api-dev moved to google/skills.
Browser voice apps that need asynchronous function calls, code execution, or URL context in Live sessions: the Live skill lists all three as unsupported.
Video editors in the EEA, Switzerland, the United Kingdom, or affected US states: the Omni skill says uploaded video editing and extension are unavailable in those regions.
Teams unwilling to refresh installed instructions manually: Google's own blog says the skill update story can leave old information in user workspaces.

Setup reality

We did not run commit 80dd31d. Our harness classified the Python repository as having no supported ecosystem entry point, and it found no Dockerfile, so there are no lab results for installation, build, tests, dependency count, disk use, or vulnerabilities.

The instruction files can be added through Vercel Skills, Context7, Antigravity, Claude Code, Cursor, or Codex. Actual Gemini calls need the relevant Google SDK and a GEMINI_API_KEY; the Omni scripts require Python 3.10 or newer, google-genai 2.19.0 or newer, plus ffmpeg and ffprobe for media preparation.

API behavior is the larger setup concern. The main skill says interactions are stored by default for 55 days on paid tiers and 1 day on the free tier. Disabling storage also disables previous-interaction chaining and background jobs. Installed skill copies need manual updates when model names or SDK advice changes.

Three skills give agents current Gemini guidance

The repository contains 3 skills: gemini-api-dev, gemini-live-api-dev, and gemini-omni-flash-api. The first covers standard generation, streaming, tool calls, structured output, embeddings, agents, and migration from older SDK patterns. The Live skill focuses on bidirectional audio, video, text, session management, and ephemeral browser credentials. Omni adds Python scripts for uploading, inspecting, preparing, generating, editing, and extending video. This is a reference pack, not an SDK or proxy service.

The basic skill names current models and SDKs, rejects deprecated families, and tells the coding agent to fetch the matching official page before writing code. A static skill can point an agent toward today's source of truth, while linked documentation carries detailed parameters and edge cases. This division only works if the agent has a documentation tool or web access and follows the lookup instruction.

Version 2.1.0 has six documented installation paths

The Codex manifest reports version 2.1.0, and the README documents 6 ways to add the skills: Vercel Skills, Context7, Antigravity, Claude Code, Cursor, and Codex. Manifests exist for several plugin formats, and users can install the collection or choose one skill. A text application can therefore omit the longer Live and Omni instructions.

A working Gemini application still needs a Google SDK, an API key, provider access, and its own tests. The Omni helper requires Python 3.10 or newer and google-genai 2.19.0 or newer. Its media paths also call ffmpeg and ffprobe. None of these runtime pieces arrive because a plugin manager copied the skill files.

What happened when we ran it

commit 80dd31d received no executed lab run. The harness identified Python as the repository language but found no supported ecosystem entry point and no Dockerfile, so it stopped before installation. There is no measured build status, test count, dependency total, installed size, timing, or vulnerability result. Reporting any of those as zero would be wrong because the corresponding steps never ran.

The repository is mostly Markdown with a small set of Python media utilities, which explains the mismatch with an application-oriented harness. The absence of a runnable project check still leaves buyers without an independent signal about the examples or scripts. Test the exact API calls inside the application that will ship, especially after a model, SDK, or skill update.

Google's evaluation used 117 code-generation prompts

Google's linked blog says its evaluation harness used 117 prompts that generated Python or TypeScript Gemini SDK code. The README reports correct best-practice API code on 87% of tasks with Gemini 3 Flash and 96% with Gemini 3.1 Pro. Those are Google's results under its grading setup. They do not describe our lab or predict correctness for a particular agent wrapper and feature mix.

The same blog says installed skills may retain old information because updates are manual. That risk matters here because the files prescribe model names, SDK minimums, deprecations, and event shapes. Pin the repository commit, record the skill version used by a project, and review refreshes. A changed global copy is harder to audit than an ordinary dependency update in version control.

Paid-tier interactions are stored for 55 days by default

The main skill says interactions are stored by default for 55 days on a paid tier and 1 day on the free tier. Turning storage off also disables previous-interaction chaining and background execution. Tools, system instructions, and generation configuration are scoped to each interaction and must be supplied again on later turns. Those rules affect privacy and correctness, so they belong in the application's design rather than only in agent context.

The Live skill documents 16 kHz mono PCM input, 24 kHz output, and a 15-minute audio-only limit without compression. Audio with video drops to 2 minutes, connections last about 10 minutes, and function calls are synchronous. Code execution and URL context are unavailable. Handlers must process every content part in an event and clear queued playback when an interruption arrives.

Omni editing accepts source clips up to 10 seconds

The Omni skill accepts generation durations from 3 to 10 seconds and describes extensions up to a 40-second total. Uploaded video for editing is limited to 10 seconds. Regional rules are decisive: uploaded editing and extension are unavailable in the EEA, Switzerland, the United Kingdom, and some US states. Check eligibility before building a workflow around the included scripts.

Those scripts use ffmpeg and ffprobe, upload inputs to Gemini, wait for activation, and save outputs locally. Video with an audio stream asks the model to preserve or adapt that audio, while stripping it requests a new track. This choice changes the deliverable, so an agent should ask before removing audio or extending a prior interaction.

A one-day-old push outweighs zero GitHub releases

GitHub showed 4,096 stars and 9 combined issues and pull requests on September 12, 2026. The last push was September 11, one day earlier, and that merge corrected the Codex installation command. Other September changes updated model guidance and raised the plugin version. The repository is active even though GitHub returned 0 published releases and 0 tags. Pin a commit because there is no release artifact to anchor an installation.

The README says the project is not an officially supported Google product and is outside Google's open-source vulnerability rewards program. That sets clear support expectations. Gemini Skills is useful current context for an agent, especially for Live API work, but its text sits between a changing service and generated application code. Official documentation and tests in the consuming project remain the authority.

Alternatives

ProjectWhat it isPick it when
Google Skills gh↗Google's broader agent-skill collection, including the Gemini API path for Vertex AI.pick this instead when Vertex AI or a wider set of Google Cloud development skills is the target.
Anthropic Skills gh↗A catalog of agent skills centered on document, presentation, spreadsheet, and PDF work.pick this instead when the workflows target Claude and office artifacts rather than Gemini API code.
Context7 gh↗A documentation service that retrieves current library references for coding agents through MCP.pick this instead when many libraries need fresh documentation and a Gemini-only instruction bundle is too narrow.

What people are saying

  1. [github-trending] google-gemini/gemini-skills

Sources

  1. Gemini Skills repository and README
  2. Gemini API development skill
  3. Gemini Live API development skill
  4. Gemini Omni Flash skill
  5. Closing the knowledge gap with agent skills
  6. Gemini coding agents documentation

More llm tools reviews

reversa · Claude-Red · knowledge-work-plugins · llamafile · OpenContext · hyperresearch · the whole board →