GoogleDevRelExplorations
25 verified skills
cercano-classify
Classify or triage text using local AI via Cercano. Returns a category, confidence level, and brief reasoning. Use this for quick local triage of errors, logs, code quality issues, bug reports, or any content that needs categorization without sending it to the cloud.
development
cercano-extract
Extract specific information from text using local AI via Cercano. Returns only the relevant sections matching your query. Use this to pull function signatures, error messages, config values, API endpoints, or other targeted information from large text without sending everything to the cloud.
development
cercano-stats
View Cercano usage statistics and cloud token savings. Shows total requests, tokens processed locally, cloud tokens reported by the host, percentage kept local, and breakdowns by tool, model, and day.
tools
cercano-document
Generate doc comments for exported Go symbols using local AI and write them directly to the file. The host never sees the file contents — Cercano handles the entire read-think-write cycle locally.
development
cercano-local
Run prompts against local AI models via Cercano and Ollama. Use this for local inference — faster, private, and zero cost. Handles chat-style queries and agentic code generation with automatic validation. Offload summarization, explanation, code writing, and general LLM tasks to a local model instead of sending them to the cloud.
development
cercano-research
Research a question using DuckDuckGo search and local AI analysis. Crafts search queries, fetches top results, and synthesizes a sourced answer — all locally.
development
cercano-summarize
Summarize text or files using local AI via Cercano without sending content to the cloud. Supports brief, medium, and detailed summary lengths.
devops
cercano-explain
Explain code or text using local AI via Cercano. Returns a clear explanation of what the code does, its key interfaces, and data flow. Use this to understand unfamiliar code, complex algorithms, or dense documentation locally before deciding what context to send to the cloud.
development
cercano-models
List AI models available on the Ollama instance connected to Cercano. Returns model names, sizes, and modification dates. Use this to discover what local models are available before choosing one for inference or switching the active model.
data-ai
cercano-classify
Classify or triage text using local AI via Cercano. Returns a category, confidence level, and brief reasoning. Use this for quick local triage of errors, logs, code quality issues, bug reports, or any content that needs categorization without sending it to the cloud.
development
cercano-config
Query or update Cercano's runtime configuration without restarting the server. Use action 'get' to list available local models from Ollama. Use action 'set' to switch the active local model, change the Ollama endpoint URL, or change the cloud provider and model.
devops
cercano-config
Query or update Cercano's runtime configuration without restarting the server. Use this to switch the active local model, change the Ollama endpoint URL, or change the cloud provider and model. Useful when you need a different model for a specific task or want to point at a different Ollama instance.
testing
cercano-explain
Explain code or text using local AI via Cercano. Returns a clear explanation of what the code does, its key interfaces, and data flow. Use this to understand unfamiliar code, complex algorithms, or dense documentation locally before deciding what context to send to the cloud.
development
cercano-extract
Extract specific information from text using local AI via Cercano. Returns only the relevant sections matching your query. Use this to pull function signatures, error messages, config values, API endpoints, or other targeted information from large text without sending everything to the cloud.
development
cercano-fetch
Fetch a URL and extract readable text content locally. Returns full extracted text (not a summary) — HTML is stripped to clean plain text.
development
cercano-init
Initialize Cercano for a project by scanning the repo and building a context file. Makes all Cercano tools project-aware with domain-specific knowledge. Run this once per project for dramatically better local AI responses.
tools
cercano-init
Initialize Cercano for a project by scanning the repo and building a context file. Makes all Cercano tools project-aware with domain-specific knowledge. Run this once per project for dramatically better local AI responses.
tools
cercano-local
Run prompts against local AI models via Cercano and Ollama. Use this for local inference — faster, private, and zero cost. Handles chat-style queries and agentic code generation with automatic validation. Offload summarization, explanation, code writing, and general LLM tasks to a local model instead of sending them to the cloud.
development
cercano-models
List AI models available on the Ollama instance connected to Cercano. Returns model names, sizes, and modification dates. Use this to discover what local models are available before choosing one for inference or switching the active model.
data-ai
cercano-research
Research a question using DuckDuckGo search and local AI analysis. Crafts search queries, fetches top results, and synthesizes a sourced answer — all locally.
development
cercano-stats
View Cercano usage statistics and cloud token savings. Shows total requests, tokens processed locally, cloud tokens reported by the host, percentage kept local, and breakdowns by tool, model, and day.
tools
cercano-submit-usage
Submit cloud token usage data to Cercano (opt-in). This sends data, not a report — use cercano_stats to view usage. Helps track cloud tokens alongside local inference for accurate local-vs-cloud comparison.
devops
cercano-submit-usage
Submit cloud token usage data to Cercano (opt-in). This sends data, not a report — use cercano_stats to view usage. Helps track cloud tokens alongside local inference for accurate local-vs-cloud comparison.
devops
cercano-summarize
Summarize text or files using local AI via Cercano without sending content to the cloud. Supports brief, medium, and detailed summary lengths.
devops
cercano-fetch
Fetch a URL and extract readable text content locally. Returns full extracted text (not a summary) — HTML is stripped to clean plain text.
development