gemini
Use Gemini AI for research, analysis, summarization, web search, and complex reasoning. Use when you need AI-powered research, code analysis, content summarization, or web search with synthesis.
What this skill does
# Gemini AI Assistant Leverage Google's Gemini Pro model with its 1M context window for research, analysis, and reasoning tasks. ## Prerequisites Install the Gemini CLI: ```bash pip install google-generativeai ``` Set your API key: ```bash export GEMINI_API_KEY=your_api_key ``` Get an API key at: https://makersuite.google.com/app/apikey ## CLI Reference ### Basic Usage ```bash # Simple question gemini -m pro "Your question here" # With text output (no markdown) gemini -m pro -o text "Your question" # Disable extensions for programmatic use gemini -m pro -o text -e "" "Your question" # Pipe content as stdin echo "content to analyze" | gemini -m pro -o text -e "" "Summarize this" cat file.txt | gemini -m pro -o text -e "" "Analyze this code" ``` ## Common Operations ### Research Deep research with critical analysis: ```bash gemini -m pro -o text -e "" "You are an expert research analyst. Research: [topic]. Provide specific facts, distinguish opinions from facts, note uncertainties, and give actionable insights." ``` ### Summarization ```bash cat document.txt | gemini -m pro -o text -e "" "Summarize this content, focusing on: [focus area]" ``` ### Code Analysis ```bash cat code.ts | gemini -m pro -o text -e "" "Analyze this code and answer: [question]" ``` ### Web Search with Synthesis ```bash gemini -m pro -o text -e "" "Search and synthesize: [query]. Include specific facts, dates, and distinguish confirmed from speculative information." ``` ### Fact-Checking ```bash gemini -m pro -o text -e "" "Fact-check this claim: [claim]. State true/false/partial, cite sources, note context." ``` ### Step-by-Step Reasoning ```bash gemini -m pro -o text -e "" "Think through this problem step by step: [problem]. Constraints: [constraints]. Provide reasoning and conclusion." ``` ### Data Extraction ```bash cat content.txt | gemini -m pro -o text -e "" "Extract [what to extract] from this content. Format as [json/list/table]." ``` ### News Lookup ```bash gemini -m pro -o text -e "" "Latest news about: [topic] from [timeframe]. Summarize important developments." ``` ## Prompt Templates ### Research Prompt ``` You are an expert research analyst. Your goal is to provide genuinely useful, accurate research. RESEARCH OBJECTIVE: [topic] QUALITY STANDARDS: - Be specific and concrete, not vague - Distinguish between facts, expert opinions, and speculation - Note when information is uncertain, contested, or evolving - Identify what's NOT known or what gaps exist - Provide actionable insights, not just information ``` ### Analysis Prompt ``` Analyze the following and provide: 1. Key findings 2. Implications 3. Recommendations 4. Uncertainties or gaps Content: [content] ``` ## Best Practices 1. **Use `-o text -e ""`** for programmatic usage to get clean output 2. **Pipe large content** via stdin rather than command line args 3. **Be specific** in prompts - vague questions get vague answers 4. **Ask for structure** - request lists, tables, or JSON for parseable output 5. **Request citations** when accuracy matters 6. **Set timeouts** for long operations (gemini can take 30-120s) ## Error Handling | Error | Solution | |-------|----------| | "command not found" | Install: `pip install google-generativeai` | | "API key" / "unauthorized" | Set `GEMINI_API_KEY` environment variable | | "rate limit" / "quota" | Wait and retry, or check quota at Google Cloud Console | | Timeout | Break into smaller queries or increase timeout |
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.