SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-17 UTC

No new commits yet today

Open the update feed

gemini-skillWJZ-P/gemini-skill

Packages the Gemini web UI into a toolset callable by agents, so automated pipelines can start chats,…

No ratings yet Rate this skill
Stars832
Forks121
Watchers832
Open Issues9

InstallOne-line install

Installable · 15 skills

This repository follows the Agent Skills spec, so one command installs it into your AI client — works across Claude Code, Codex, Cursor, Copilot, Windsurf, and 18+ other clients.

npx skills@latest add WJZ-P/gemini-skill

15 more are not listed — run npx skills@latest add WJZ-P/gemini-skill --list to see them all.

Add -g install globally (available in every project) · add --agent claude-code to target a client · add --yes to skip the prompts. Restart your AI client afterward and it will pick it up.

OverviewOverview

Key Features

Packages the Gemini web UI into a toolset callable by agents, so automated pipelines can start chats, upload images and retrieve generated results directly. Key capabilities include: 1. MCP tool first: prefer the MCP tools exposed by this skill to run operations, covering most chat and image-generation scenarios and keeping the agent from hand-assembling browser scripts; 2. Script fallback: when MCP tools cannot satisfy the need, run the bundled skill scripts to perform the same operations so the pipeline does not break; 3. Managed browser connection: when neither of the above works, connect to a browser instance managed by the skill and continue with the existing logged-in session; 4. Session and model control: create new chats and switch Gemini models so different tasks run on the right model and in a clean context; 5. Image upload and retrieval: batch-upload reference images, send messages and capture images generated on the page, closing the loop from input to output; 6. Status probing: check whether the Gemini page is reachable and the login state is valid, surfacing environment problems before a task fails midway.

Use Cases

Tasks where an agent must operate the Gemini web UI automatically for multi-turn chats, reference-image generation and result collection; batch processing that switches models or opens new sessions to isolate context per task; automation orchestration that probes availability before running unattended steps.

Target Roles

AI / Algorithm Engineer, Full-stack / Indie Developer, Test / QA Engineer, Content Creator / Social Media Operator.

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID1118
Data sourceGitHub
RepositoryWJZ-P/gemini-skill
CategoryAI & Agent Skills / Browser Automation & Multimodal Generation
Primary languageJavaScript
LicenseMIT License
Default branchmain
GitHub repository ID1180015183
Node IDR_kgDORlWaTw
Rank#880 (position within the source ranking)
Site-wide popularity rank#994 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

02505007501k2026-09-292026-10-112026-09-29 · 8342026-10-11 · 832
  • Now832
  • Previous point · 09-29 834
  • vs previous point -2
  • 2 data points 12 days
0501001502026-09-292026-10-112026-09-29 · 1212026-10-11 · 121
  • Now121
  • Previous point · 09-29 121
  • vs previous point ±0
  • 2 data points 12 days

TimelineTimeline

Repository created2026-03-12 16:01:198 months ago
Data last updated2026-10-26 12:05:2822 days ago
Last commit2026-09-18 13:41:012 months ago

CommitLatest commit

Committed by WJZ-P. Update Category: Documentation Updates. Commit details: docs: add AtomGit star badge to README. This update refines the documentation for easier onboarding.

333e818 WJZ-P 2026-09-18

Next stepsNext steps