By WenyuChiou
Delegate large-context reading, bilingual Chinese/English drafting, and second-opinion review to Google Gemini CLI safely.
gemini-delegate is a Claude-oriented skill for using Google Gemini as a specialist for large-context synthesis, long-form drafting, English or bilingual / CJK writing, and second-opinion review.
📚 Part of the agentic AI learning roadmap — a 7-stage curated path for building agentic AI, multilingual (zh-TW · zh-CN · English). This skill is referenced in §13 (Multi-LLM Delegation).
Claude has a finite working context, and certain tasks are a bad fit even when Claude could technically do them. Two failure modes are common:
Routing those tasks to Gemini lets Claude stay in its strengths (judgment, terminology review, factual checking) and lets Gemini do what it's actually best at (large-context synthesis and CJK drafting).
This skill pays off when:
It does not pay off when:
codex-delegate instead)This skill is not the Gemini version of codex-delegate. Its job is different:
It is not intended for bulk code generation or architecture work.
Gemini may produce useful drafts. Claude still decides whether the result is publishable.
gemini-delegate-skill/
├── README.md
├── README_zh-TW.md
├── scripts/
│ ├── run_gemini.sh
│ └── run_gemini.ps1
├── skills/
│ └── gemini-delegate/
│ ├── SKILL.md
│ └── references/
│ ├── wrapper.md
│ ├── delegation-targets.md
│ ├── output-contract.md
│ ├── review-checklist.md
│ ├── task-template.md
│ └── examples.md
└── tests/
└── test_wrappers.py
python -m pytest -q
Current wrapper tests cover:
result.json generation1. Install the skill via the ai-research-skills Claude Code marketplace:
claude plugin marketplace add WenyuChiou/ai-research-skills
claude plugin install gemini-delegate@ai-research-skills
Default scope is user (this OS account, all projects). Add --scope project to install only for the current project.
2. Make sure Gemini CLI is on $PATH:
npm install -g @google/gemini-cli
gemini --version
MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub wenyuchiou/ai-research-skills --plugin gemini-delegateHand token-heavy mechanical work (batch edits, scaffolding, refactors, test generation, plotting scripts) from Claude to Codex CLI.
11 research-hub skills: literature triage matrix, context compression, project orientation, design dialog, multi-AI routing, NotebookLM brief verification, paper-memory builder, paper summarizer, Zotero curator, the gap-to-topic decision dossier, and the research-hub orchestrator. Auto-discovered from skills/<name>/SKILL.md.
Full Zotero CRUD: search, add, update, delete items with notes, tags, collections, and PDF attachments. Dual local/Web API routing.
Manuscript revision, claim-evidence audit, banned-word / humanize pass, figure-text consistency, journal-format check, reviewer response.
6 skills for context-safe multi-agent collaboration: task-splitter, context-budget, output-reconciler, debate, shared-memory, and acceptance-gate. Composes with codex-delegate + gemini-delegate via bounded .ai task packets, .coord context policy, and result.json contracts.
Use Gemini CLI from Claude Code to review code or delegate tasks.
Enables Claude Code to manage Gemini CLI as an intern. Claude acts as manager/architect while Gemini does all coding work.
Integrate Gemini CLI for long-context code exploration from Claude Code and Codex
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.