Systematic debugging for the Ollama Agent Harness — reproduce, localize, reduce, fix, guard
Langue du texte source : anglais
Menu
SkillsMP a collecté 13 skills depuis Bradliebs/ollama-agent-harness. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 13 skills collectés sur 13.
Systematic debugging for the Ollama Agent Harness — reproduce, localize, reduce, fix, guard
Langue du texte source : anglais
Git workflow for the Ollama Agent Harness — atomic commits, small changes, safe history
Langue du texte source : anglais
Security hardening for the Ollama Agent Harness — input validation, command injection, secrets, deny-first review
Langue du texte source : anglais
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…
Langue du texte source : anglais
Project conventions for the Ollama Agent Harness — architectural patterns borrowed from the Claude Code paper
Langue du texte source : anglais
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…
Langue du texte source : anglais
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…
Langue du texte source : anglais
Evidence-first research — gathers sources on a topic, synthesises findings, and cites every claim. Marks what could not be verified instead of guessing.
Langue du texte source : anglais
Code review skill for the Ollama Agent Harness — enforces architectural conventions from the Claude Code paper
Langue du texte source : anglais
Autonomous plan execution — reads IMPLEMENTATION_PLAN.md, picks the next task, implements it, validates, commits, and repeats
Langue du texte source : anglais
Guided wizard that scaffolds Copilot skills, agents, memory, and cookbook recipes into any repo from a plain-English project description
Langue du texte source : anglais
Supervised shopping assistant — browses stores, compares prices, builds baskets, but ALWAYS requires human approval before checkout
Langue du texte source : anglais
Testing conventions for the Ollama Agent Harness using Jest
Langue du texte source : anglais