Systematic debugging for the Ollama Agent Harness — reproduce, localize, reduce, fix, guard
Idioma del texto original: inglés
Menú
SkillsMP ha recopilado 13 skills de Bradliebs/ollama-agent-harness. Abre una skill para revisar su origen y sus detalles.
Mostrando 13 de 13 skills recopiladas.
Systematic debugging for the Ollama Agent Harness — reproduce, localize, reduce, fix, guard
Idioma del texto original: inglés
Git workflow for the Ollama Agent Harness — atomic commits, small changes, safe history
Idioma del texto original: inglés
Security hardening for the Ollama Agent Harness — input validation, command injection, secrets, deny-first review
Idioma del texto original: inglés
Build a new MCP (Model Context Protocol) server from scratch — a stdio program that exposes tools to AI agents. Use when the user wants to wrap an API, CLI, or internal service as an MCP server the harness (or Claude Desktop, Cursor, etc.) can load. Adapted…
Idioma del texto original: inglés
Project conventions for the Ollama Agent Harness — architectural patterns borrowed from the Claude Code paper
Idioma del texto original: inglés
Passively get to know the user over time — distill durable facts about who they are, what they work on, and how they like to be helped from conversation history into USER.md and memory. The home-user analog of Microsoft Work IQ's implicit-memory layer. Use…
Idioma del texto original: inglés
Build and maintain a Karpathy-style LLM-maintained personal wiki (a "Second Brain") as plain markdown the user owns. Use when the user wants to set up a second brain, capture/ingest a source into their notes, ask their knowledge base a question, file…
Idioma del texto original: inglés
Evidence-first research — gathers sources on a topic, synthesises findings, and cites every claim. Marks what could not be verified instead of guessing.
Idioma del texto original: inglés
Code review skill for the Ollama Agent Harness — enforces architectural conventions from the Claude Code paper
Idioma del texto original: inglés
Autonomous plan execution — reads IMPLEMENTATION_PLAN.md, picks the next task, implements it, validates, commits, and repeats
Idioma del texto original: inglés
Guided wizard that scaffolds Copilot skills, agents, memory, and cookbook recipes into any repo from a plain-English project description
Idioma del texto original: inglés
Supervised shopping assistant — browses stores, compares prices, builds baskets, but ALWAYS requires human approval before checkout
Idioma del texto original: inglés
Testing conventions for the Ollama Agent Harness using Jest
Idioma del texto original: inglés