Ollama Library

Local models via CLI and Modelfile. Run prompts and custom Modelfiles on your machine. No cloud spend for inference.

10 implementations · Verified 3 · Untested 7 — status from registry.

PromptAnalyticsUntested

Data Analysis — Ollama

Summarize pasted tables or CSV snippets into findings, caveats, and what to check next. Analysis only. (Ollama Modelfile + chat prompt for offline runs.)

Open

PromptContentVerified

Writing Draft — Ollama

Draft a clear first pass from notes — then stop for human edit. No fake claims or invented metrics. (Ollama Modelfile + chat prompt for offline runs.)

Open

PromptDocumentationUntested

Doc Review — Ollama

Review docs for clarity, broken promises, and missing prerequisites before publish. (Ollama Modelfile + chat prompt for offline runs.)

Open

PromptEngineeringUntested

Coding Review — Ollama

Review a diff or file for bugs, risky paths, and missing tests — without auto-committing or running destructive commands. (Ollama Modelfile + chat prompt for offline runs.)

Open

PromptMarketingVerified

SEO Brief — Ollama

Produce a one-page SEO brief (intent, title options, outline, risks) from a keyword and URL context. (Ollama Modelfile + chat prompt for offline runs.)

Open

PromptOpsUntested

Monitoring Check — Ollama

Turn a status paste or log snippet into a short health note: what changed, severity, and a reversible next step. (Ollama Modelfile + chat prompt for offline runs.)

Open

PromptProductivityUntested

Personal Assistant — Ollama

Daily capture → prioritized plan with stop rules. Local-first; does not spend money or send mail alone. (Ollama Modelfile + chat prompt for offline runs.)

Open

PromptResearchVerified

Deep Research — Ollama

Turn a fuzzy question into a sourced research brief with open questions and next checks — not a final verdict. (Ollama Modelfile + chat prompt for offline runs.)

Open

PromptSalesUntested

Lead Research — Ollama

Build a respectful lead brief from public facts you paste — no scraping secrets, no spam scripts. (Ollama Modelfile + chat prompt for offline runs.)

Open

PromptSupportUntested

Support Triage — Ollama

Classify an inbound message, propose a first reply hold, and flag escalation — human sends. (Ollama Modelfile + chat prompt for offline runs.)

Open

All Library Teams List your team