Agent skill

Collaborating With Gemini

by yunshenwuchuxun in yunshenwuchuxun/latex-paper-skills

Use the Gemini CLI as a breadth-exploration co-pilot for paper-from-zero.

MITAuto-check passedMarketing & SEO

Install Collaborating With Gemini

skills CLI
$ npx skills add yunshenwuchuxun/latex-paper-skills --skill collaborating-with-gemini -a claude-code

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

GitHub CLI
$ gh skill install yunshenwuchuxun/latex-paper-skills collaborating-with-gemini --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/yunshenwuchuxun/latex-paper-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/collaborating-with-gemini .claude/skills/collaborating-with-gemini && 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
collaborating-with-gemini
GitHub stars
267
Token cost
~1.1k tokens
SKILL.md length
389 words
Files
5 (incl. scripts, references, assets)
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Use the Gemini CLI as a breadth-exploration co-pilot for paper-from-zero.

  • Tasks that involve Keyword research
  • SKILL.md covers When to Use, When NOT to Use, Gemini-Specific Rules and Quick Start (shell-safe), plus 5 more sections
  • Runs Python scripts from its folder; calls python3; needs GEMINI_API_KEY and GOOGLE_API_KEY
  • Tasks that involve Proposals and quotes

What it does

Collaborating With Gemini is an agent skill from yunshenwuchuxun/latex-paper-skills. Use the Gemini CLI as a breadth-exploration co-pilot for paper-from-zero. Primary role: candidate direction expansion, adjacent work scanning, keyword cluster generation, and alternative framing proposals. Also supports generic code collaboration as fallback.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts, reference files and assets (for example `assets/prompt-template.md`, `references/shell-quoting.md` and `scripts/gemini_bridge.py`).

It sits in Marketing & SEO, covering Keyword research and Proposals and quotes. It works with Google Gemini. The repository describes itself as: A modular skill-based framework for writing, revising, and managing LaTeX academic papers with AI assistance. The licence is MIT.

When your agent uses it

  • Tasks that involve Keyword research
  • Tasks that involve Proposals and quotes

Example prompts

  • “/collaborating-with-gemini”

Requirements

  • Python 3
  • A credential in GEMINI_API_KEY
  • A credential in GOOGLE_API_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit d0f1061. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

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

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • GEMINI_API_KEY
    • GOOGLE_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Collaborating With Gemini loads about 1.1k tokens when it runs, and up to ~1.4k if it reads all its reference files. Until then it costs about 71 tokens; SKILL.md has 389 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.4k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from yunshenwuchuxun/latex-paper-skills at commit d0f1061, republished under its MIT licence (© yunshenwuchuxun). 389 words, ~1,137 tokens.

Download SKILL.mdSave it as .claude/skills/collaborating-with-gemini/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
collaborating-with-gemini
description
Use the Gemini CLI as a breadth-exploration co-pilot for paper-from-zero. Primary role: candidate direction expansion, adjacent work scanning, keyword cluster generation, and alternative framing proposals. Also supports generic code collaboration as fallback.
metadata.short-description
Breadth co-pilot (Gemini) for paper-from-zero

Collaborating with Gemini (Codex)

Use Gemini CLI as a breadth-exploration collaborator for paper-from-zero, or as a generic code collaborator in fallback mode.

This skill provides a lightweight bridge script that returns structured JSON and supports multi-turn sessions via SESSION_ID.

Shared rules: This skill inherits all shared rules from ../../_shared/collaboration-base.md (core rules, candidates-only constraint, fallback code-collaboration mode, safety guardrails, and collaboration state capsule format). Only Gemini-specific additions are listed below.

When to Use

  • paper-from-zero needs to expand the candidate literature pool.
  • topic-brief initial draft exists but adjacent research areas are uncovered.
  • contribution-map needs 3-5 alternative framing candidates.
  • evidence-matrix has coverage gaps that need broader search directions.
  • Fallback: generic code collaboration tasks (analysis, patch, review).

When NOT to Use

  • Claim-level logical analysis or reviewer objection stress tests (use Claude).
  • Final routing judgment between review/empirical (use Claude).
  • Generating ref.bib entries or verified citations.
  • Tasks requiring depth reasoning rather than breadth scanning.

Gemini-Specific Rules

  • Optional: pass --sandbox to run Gemini in sandbox mode.
  • Auth/home notes:
    • The bridge defaults GEMINI_CLI_HOME to a writable repo-local directory (<repo>/.gemini_cli_home/) to avoid Gemini CLI hanging in some runners.
    • If your local gemini is already logged in, reuse that login with --use-user-home.
    • If you have GEMINI_API_KEY set but want to use OAuth creds, add --prefer-oauth to unset API-key env vars for this run.

Quick Start (shell-safe)

If your prompt contains Markdown backticks, use a heredoc; see references/shell-quoting.md.

bash
PROMPT="$(cat <<'EOF'
Review src/auth.py around login() and propose fixes.
OUTPUT: Unified Diff Patch ONLY.
EOF
)"
python3 .codex/skills/collaborating-with-gemini/scripts/gemini_bridge.py --cd "." --PROMPT "$PROMPT"

Output: JSON with success, SESSION_ID, agent_messages, and optional error / all_messages.

Show full SKILL.md (152 more words)Show less

Multi-turn Sessions

bash
# Start a session
PROMPT="$(cat <<'EOF'
Analyze the bug in foo(). Keep it short.
EOF
)"
python3 .codex/skills/collaborating-with-gemini/scripts/gemini_bridge.py --cd "." --PROMPT "$PROMPT"

# Continue the same session
PROMPT="$(cat <<'EOF'
Now propose a minimal fix as Unified Diff Patch ONLY.
EOF
)"
python3 .codex/skills/collaborating-with-gemini/scripts/gemini_bridge.py --cd "." --SESSION_ID "<SESSION_ID>" --PROMPT "$PROMPT"

Prompting Patterns (Paper Mode)

Use assets/prompt-template.md as a starter when crafting --PROMPT. Paper-mode templates (top of the file):

  • literature-map — expand candidate papers and adjacent research areas
  • innovation-candidates — generate 3-5 candidate contribution framings
  • evidence-matrix-gap-check — audit evidence coverage gaps

Each template specifies its input sources, output artifact mappings, and constraints.

Advanced Flags

  • --sandbox: Run Gemini in sandbox mode.
  • --model <name>: Override the default Gemini model.
  • --return-all-messages: Include all raw messages (tool calls, traces) in output JSON.
  • --use-user-home: Reuse your normal home (and existing ~/.gemini login) for this run.
  • --prefer-oauth: Unset GEMINI_API_KEY/GOOGLE_API_KEY so OAuth creds can be used (if present in the selected home).
  • --seed-user-auth: Copy OAuth/settings files from your ~/.gemini into <repo>/.gemini_cli_home/.gemini/ (avoids --use-user-home hangs).
  • --fake-responses <path.jsonl>: Offline deterministic run using Gemini CLI fake responses (for smoke tests).

Verification

  • Cross-check both collaborators: use the check-collaborators skill
  • Smoke-test the bridge: python3 .codex/skills/collaborating-with-gemini/scripts/gemini_bridge.py --help

References

  • ../../_shared/collaboration-base.md (shared rules)
  • assets/prompt-template.md (prompt patterns)
  • references/shell-quoting.md (shell quoting/backticks)

© yunshenwuchuxun, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (scripts, references, assets) in .codex/skills/collaborating-with-gemini of yunshenwuchuxun/latex-paper-skills.

  • SKILL.md
  • assets/fake-responses-simple.jsonl
  • assets/prompt-template.md
  • references/shell-quoting.md
  • scripts/gemini_bridge.py

Open the folder on GitHubat commit d0f1061

Compare with similar skills

Collaborating With Gemini 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.

Collaborating With Gemini compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Collaborating With Gemini this skillyunshenwuchuxun/latex-paper-skills267—~1.1kAutomated safety check: PassMIT
Amazon Listing Competitor Analysisbrowser-act/skills6.1k1 repos~3.2kAutomated safety check: PassMIT
Tnr Content Auditstudie-tech/TheNinjaRPG104—~4.9kAutomated safety check: NotesNone
Ecommerce Keyword Researchnexscope-ai/eCommerce-Skills1.1k—~645Automated safety check: PassMIT
SEO Keyword ClusteringAgriciDaniel/claude-seo19k2 repos~3.3kAutomated safety check: PassMIT
Evaluate Skillevery-app/open-seo23k—~1.8kAutomated safety check: NotesMIT

Similar skills

  • Analyzes a competitor's Amazon listing by ASIN with BrowserAct data extraction, then reports what it does well, where the market has gaps and opportunity points for your own listing.

    6.1k GitHub starsUsed in 1 repo~3.2k tokens
    Marketing & SEOAuto-check passed
  • Tnr Content Audit

    studie-tech/TheNinjaRPG

    Audit TheNinja-RPG game content (jutsu, items, bloodlines, quests, badges, AI characters, assets) for grammar, balance, sound, animation, visual and consistency gaps, and write suggestions for the…

    104 GitHub stars~4.9k tokensUpdated today
    Marketing & SEOAuto-check: notes
  • Ecommerce Keyword Research

    nexscope-ai/eCommerce-Skills

    Cross-platform keyword research for e-commerce. An agent skill from nexscope-ai/eCommerce-Skills.

    1.1k GitHub stars~645 tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed
  • SEO Keyword Clustering

    AgriciDaniel/claude-seo

    Clusters keywords by how much their search results overlap and designs a hub-and-spoke content plan with an internal link matrix and an interactive cluster map.

    19k GitHub starsUsed in 2 repos~3.3k tokens
    Marketing & SEOAuto-check passed
  • Evaluate Skill

    every-app/open-seo

    Test a candidate OpenSEO skill end to end by running fresh, isolated Codex sessions against the local backend and scoring the reports they save.

    23k GitHub stars~1.8k tokensUpdated 2 days ago
    Marketing & SEOAuto-check: notes
  • SEO Content Brief Generator

    AgriciDaniel/claude-seo

    Builds research-backed SEO content briefs with competitor scoring, per-section word counts and page-type templates, for new pages or improving existing ones.

    19k GitHub starsUsed in 2 repos~2.6k tokens
    Marketing & SEOAuto-check passed

More from yunshenwuchuxun/latex-paper-skills

All 8 skills in this repo
  • Arxiv Paper Writer

    yunshenwuchuxun/latex-paper-skills

    Writes ML/AI review and survey papers for arXiv using the IEEEtran LaTeX template with verified BibTeX citations.

    267 GitHub stars~3.2k tokensUpdated 6 mo ago
    Auto-check passed
  • Collaborating With Claude

    yunshenwuchuxun/latex-paper-skills

    Use the Claude Code CLI as a depth-analysis co-pilot for paper-from-zero.

    267 GitHub stars~1.2k tokensUpdated 6 mo ago
    Auto-check passed
  • Paper From Zero

    yunshenwuchuxun/latex-paper-skills

    Route a fixed research topic into a rigorous paper-generation workflow.

    267 GitHub stars~1.5k tokensUpdated 6 mo ago
    Auto-check passed
  • Results Backfill

    yunshenwuchuxun/latex-paper-skills

    Back-fill verified experiment results into an existing empirical paper draft.

    267 GitHub stars~1.7k tokensUpdated 6 mo ago
    Auto-check passed
  • Empirical Paper Writer

    yunshenwuchuxun/latex-paper-skills

    Draft IEEE-style empirical ML/AI papers from a structured research contract.

    267 GitHub stars~5.3k tokensUpdated 6 mo ago
    Auto-check passed
  • Check Collaborators

    yunshenwuchuxun/latex-paper-skills

    Verify that Gemini CLI and Claude Code CLI are installed, authenticated, and API-reachable before starting collaboration workflows.

    267 GitHub stars~1.4k tokensUpdated 6 mo ago
    Auto-check passed

Works with

Questions about Collaborating With Gemini

What does Collaborating With Gemini do?

Use the Gemini CLI as a breadth-exploration co-pilot for paper-from-zero. Collaborating With Gemini is an agent skill from yunshenwuchuxun/latex-paper-skills. Use the Gemini CLI as a breadth-exploration co-pilot for paper-from-zero.

When should I use Collaborating With Gemini?

Collaborating With Gemini fits situations like: tasks that involve Keyword research; tasks that involve Proposals and quotes.

How do I install Collaborating With Gemini in Claude Code?

Run `npx skills add yunshenwuchuxun/latex-paper-skills --skill collaborating-with-gemini -a claude-code`. Or copy the skill folder (.codex/skills/collaborating-with-gemini in yunshenwuchuxun/latex-paper-skills) into .claude/skills/collaborating-with-gemini in your project. Claude Code loads it when a task matches its description.

How do I install Collaborating With Gemini in Codex?

Run `npx skills add yunshenwuchuxun/latex-paper-skills --skill collaborating-with-gemini -a codex`. Or copy the skill folder (.codex/skills/collaborating-with-gemini in yunshenwuchuxun/latex-paper-skills) into .agents/skills/collaborating-with-gemini in your project. Codex loads it when a task matches its description.

Can I use Collaborating With Gemini 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 yunshenwuchuxun/latex-paper-skills --skill collaborating-with-gemini -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/collaborating-with-gemini, .gemini/skills/collaborating-with-gemini, .github/skills/collaborating-with-gemini and .opencode/skills/collaborating-with-gemini in your project.

What does Collaborating With Gemini need to run?

Going by SKILL.md and its folder, Collaborating With Gemini needs Python for the scripts in its folder, the command-line tools its instructions call (python3) and credentials named GEMINI_API_KEY and GOOGLE_API_KEY. Our summary lists: Python 3; A credential in GEMINI_API_KEY; A credential in GOOGLE_API_KEY.

Does Collaborating With Gemini access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Collaborating With Gemini 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Collaborating With Gemini use?

Collaborating With Gemini 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 Collaborating With Gemini use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 308 tokens, read only when the agent opens those files.

What are the alternatives to Collaborating With Gemini?

Skills that share tags, products or a category with Collaborating With Gemini: Amazon Listing Competitor Analysis (browser-act/skills, 6.1k stars), Tnr Content Audit (studie-tech/TheNinjaRPG, 104 stars), Ecommerce Keyword Research (nexscope-ai/eCommerce-Skills, 1.1k stars) and SEO Keyword Clustering (AgriciDaniel/claude-seo, 19k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Collaborating With Gemini?

yunshenwuchuxun (a GitHub user) maintains it in yunshenwuchuxun/latex-paper-skills, which has 267 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on March 25, 2026.

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