Menu
SkillsMP a collecté 47 skills depuis bryancostanich/Cercano. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 40 skills collectés sur 47.
Deep multi-source research tool that identifies authoritative sources, systematically searches, analyzes and ranks findings, chases cited references, and compiles a structured report with executive summary, contradiction detection, gap analysis, and follow-up…
Langue du texte source : anglais
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.
Langue du texte source : anglais
Compute the expected result before running any simulation or sweep.
Langue du texte source : anglais
Stop and weigh real options before coding a structural decision.
Langue du texte source : anglais
Reduce, observe, reason, predict, probe, then fix — no guessing.
Langue du texte source : anglais
Match the test tier to the size of the change.
Langue du texte source : anglais
Isolate every feature branch in its own worktree; never share the root workspace.
Langue du texte source : anglais
Query or update Cercano's runtime configuration without restarting the server. Use action 'get' to list available local models. Use action 'set' to switch the active local runtime or model, change the Ollama endpoint URL, or change the cloud provider and…
Langue du texte source : anglais
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.
Langue du texte source : anglais
Deep multi-source research tool that identifies authoritative sources, systematically searches, analyzes and ranks findings, chases cited references, and compiles a structured report with executive summary, contradiction detection, gap analysis, and follow-up…
Langue du texte source : anglais
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.
Langue du texte source : anglais
Query or update Cercano's runtime configuration without restarting the server. Use action 'get' to list available local models. Use action 'set' to switch the active local runtime or model, change the Ollama endpoint URL, or change the cloud provider and…
Langue du texte source : anglais
Use when the user wants to check or change Cercano's runtime configuration — switch the local runtime or model, change the Ollama endpoint URL, or change the cloud provider and model. No server restart needed.
Langue du texte source : anglais
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…
Langue du texte source : anglais
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…
Langue du texte source : anglais
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…
Langue du texte source : anglais
Fetch a URL and extract readable text content locally. Returns full extracted text (not a summary) — HTML is stripped to clean plain text.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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…
Langue du texte source : anglais
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.
Langue du texte source : anglais
Research a question using DuckDuckGo search and local AI analysis. Crafts search queries, fetches top results, and synthesizes a sourced answer — all locally.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Summarize text or files using local AI via Cercano without sending content to the cloud. Supports brief, medium, and detailed summary lengths.
Langue du texte source : anglais
Use when the user needs to categorize, triage, or classify text — error severity, code quality, bug reports, log entries. Quick local classification without cloud round-trip.
Langue du texte source : anglais
Use when the user needs thorough, multi-source research with ranked findings, citations, and synthesis. Use this for literature reviews, competitive analysis, technical deep-dives, or any research that needs more than a quick answer. Prefer this over…
Langue du texte source : anglais
Use when the user wants to generate or update doc comments for Go code. Handles the entire read-think-write cycle locally — the host never sees the file contents. Supports dry_run mode to preview.
Langue du texte source : anglais
Use when the user asks to explain unfamiliar code, complex algorithms, or dense documentation. Processes the explanation locally before deciding what context to send to the cloud. Prefer this for initial code understanding.
Langue du texte source : anglais
Use when the user needs to pull specific information from large text — function signatures, error messages, config values, API endpoints. Extracts locally instead of reading entire files into cloud context.
Langue du texte source : anglais
Use when the user asks to fetch, read, or open a specific URL. Use this INSTEAD of WebFetch to read web pages locally without sending content to the cloud. DO NOT TRIGGER when: user asks a research question without a specific URL (use cercano-research…
Langue du texte source : anglais
Use when setting up Cercano for a new project. Scans the repo to build a project context file that makes all Cercano tools project-aware. Run this once per project for better local AI responses.
Langue du texte source : anglais
Use when the user wants to run a prompt against a local AI model via Ollama. Handles both chat-style queries and agentic code generation with validation. Use this to offload work to local inference — faster, private, zero cost.
Langue du texte source : anglais
Use when the user wants to see what AI models are available on their Ollama instance. Returns model names, sizes, and modification dates.
Langue du texte source : anglais
Use when the user asks to research, look up, investigate, find information, or learn about any topic. Use this INSTEAD of WebSearch or WebFetch for general research questions. ALWAYS prefer this tool for web research. DO NOT TRIGGER when: user provides a…
Langue du texte source : anglais
Use when the user asks about Cercano usage, token savings, or local vs cloud inference stats. Shows total requests, tokens processed locally, and breakdowns by tool, model, and day.
Langue du texte source : anglais
Use when the user wants to submit cloud token usage data to Cercano for tracking. This sends data, not a report — use cercano_stats to view usage. Opt-in telemetry for local-vs-cloud comparison.
Langue du texte source : anglais
Use when the user needs to summarize large text, files, logs, or diffs. ALWAYS prefer this over reading large files directly into cloud context. Processes content locally and returns a concise summary.
Langue du texte source : anglais
Fetch a URL and extract readable text content locally. Returns full extracted text (not a summary) — HTML is stripped to clean plain text.
Langue du texte source : anglais
Research a question using DuckDuckGo search and local AI analysis. Crafts search queries, fetches top results, and synthesizes a sourced answer — all locally.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Summarize text or files using local AI via Cercano without sending content to the cloud. Supports brief, medium, and detailed summary lengths.
Langue du texte source : anglais