gemini-cli
Ask Gemini via the local `gemini` CLI (no MCP). Use when the user says "ask gemini" / "use gemini", wants a second opinion, needs large-context `@path` analysis, sandbox runs, or structured change-mode edits.
What this skill does
# Gemini CLI Skill Use Google’s `gemini` CLI as an external “second brain” when you need a very large context window, a second opinion, or safe sandbox execution. This skill does **not** use MCP; it runs the local CLI directly. ## When To Use Use this skill when the user asks to: - “Ask Gemini” / “Use Gemini” - Analyze or summarize large files or directories (especially with `@path` references) - Brainstorm options with a specific framework (SCAMPER, design thinking, etc.) - Generate structured edit suggestions (“change mode”) that can be applied deterministically ## Prerequisites - `gemini` CLI is installed and configured (e.g. `gemini --version` works) - You are allowed to run local shell commands in this environment - For sandbox execution, Gemini CLI supports `-s/--sandbox` (see `gemini --help`) ## Core Commands ### One-shot query (plain) ```bash gemini "Explain what this code does: @src/main.ts" ``` ### Choose a model ```bash gemini -m gemini-3-pro-preview "..." gemini -m gemini-3-flash-preview "..." ``` ### Sandbox mode ```bash gemini -s "Safely test @scripts/example.py and explain the results." ``` ## Helper Script (Recommended) This skill ships with a dependency-free wrapper that mirrors the core behavior of `gemini-mcp-tool` without MCP: `skills/gemini-cli/scripts/gemini-tool.mjs` Important: Gemini CLI can only read files under its current “project directory” (typically the process working directory). Run the wrapper from the repo you want Gemini to read, or pass `--cwd`. ```bash node skills/gemini-cli/scripts/gemini-tool.mjs help ``` ### Ask Gemini (wrapper) ```bash node skills/gemini-cli/scripts/gemini-tool.mjs ask --prompt "Summarize @. in 5 bullets." node skills/gemini-cli/scripts/gemini-tool.mjs ask --cwd /path/to/project --prompt "Summarize @. in 5 bullets." node skills/gemini-cli/scripts/gemini-tool.mjs ask --prompt "..." --model gemini-3-pro-preview node skills/gemini-cli/scripts/gemini-tool.mjs ask --prompt "..." --sandbox ``` ### Brainstorm (wrapper) ```bash node skills/gemini-cli/scripts/gemini-tool.mjs brainstorm --prompt "How should we design onboarding?" --methodology scamper --ideaCount 12 ``` ### Change Mode (structured edits + chunk caching) Use change mode when you want Gemini to output **deterministic** OLD/NEW blocks that can be applied by exact string matching. ```bash node skills/gemini-cli/scripts/gemini-tool.mjs ask --changeMode --prompt "In @src/foo.ts, rename Foo to Bar and update call sites." ``` If the response is chunked, the output includes a `cacheKey`. Fetch the next chunk: ```bash node skills/gemini-cli/scripts/gemini-tool.mjs fetch-chunk --cacheKey <key> --chunkIndex 2 ``` ## Safety Rules - Never execute destructive commands from Gemini output without explicit user approval. - In change mode, the `OLD` block must match the file content **exactly**; otherwise, do not apply the edit. - Prefer read-only analysis unless the user explicitly requests changes.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.