Runs Gemini CLI headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Gemini CLI or compare its result with another coding agent.
Scanned 9/2/2026
Install to Claude Code
Skills Directorynpx -y skills add CherryHQ/cherry-studio --skill code-mate-gemini --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Code Mate Gemini?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/cherryhq-code-mate-gemini)More formats (shields.io, HTML) on the badges page.
---
name: code-mate-gemini
description: Runs Gemini CLI headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Gemini CLI or compare its result with another coding agent.
---
# Gemini CLI
## Run
1. Set the Bash working directory to the exact project the user named and set a finite timeout, normally 10 minutes.
2. Check availability with `command -v gemini`. If it is missing, stop and ask the user to install Gemini CLI in Code Mate.
3. Run one task and exit:
```bash
gemini -p "<prompt>" --output-format json
```
Pass the prompt as one quoted argument. Parse the JSON result and treat a JSON error or nonzero exit as failure. Never start interactive Gemini or an authentication flow.
## Authentication And Permissions
If Gemini reports missing authentication, project, or provider configuration, stop and ask the user to finish Gemini setup in Code Mate. Never request, read, print, or copy credentials.
Keep headless approval policy at its read-only default. Only when the user explicitly requests workspace changes may the command use the narrowest policy and tool permissions needed; do not enable unrestricted approval.
Example: ask Gemini to review a module without editing, run the command above from the repository, and summarize the parsed response and any reported error.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
