Bradliebs

Systematic debugging for the Ollama Agent Harness — reproduce, localize, reduce, fix, guard

Git workflow for the Ollama Agent Harness — atomic commits, small changes, safe history

Security hardening for the Ollama Agent Harness — input validation, command injection, secrets, deny-first review

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…

Project conventions for the Ollama Agent Harness — architectural patterns borrowed from the Claude Code paper

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…

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…

Evidence-first research — gathers sources on a topic, synthesises findings, and cites every claim. Marks what could not be verified instead of guessing.

Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element…

Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a…

Restrict file edits to a specific directory for the session. Blocks Edit and Write outside the allowed path. Use when debugging to prevent accidentally "fixing" unrelated code, or when you want to scope changes to one module. Use when asked to "freeze",…

Upgrade gstack to the latest version. Detects global vs vendored install, runs the upgrade, and shows what's new. Use when asked to "upgrade gstack", "update gstack", or "get latest version". Voice triggers (speech-to-text aliases): "upgrade the tools",…

Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix…

Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open…

Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open…

Generate Trading 212 API code with correct ticker mapping, rate limiting, GBX conversion, and stop order flow. Use when: T212 API, Trading 212, stop order, T212 ticker, GBX pence conversion, T212 rate limit, position sync, T212 import.

Full-depth precision reasoning skill — Bayesian scenario analysis, counterfactual stress testing, and structured analytical output for complex or ambiguous decisions

Guided wizard that scaffolds Copilot skills, agents, memory, and cookbook recipes into any repo from a plain-English project description

Pre-scaffold gate that reads memory, detects build-path signals, checks for contradictions, and flags prerequisite risks — silently passing through when everything is consistent

Routing oracle and per-path reference for all 10 Power Platform build paths — maps Q1/PP diagnostic answers to a BUILD_PATH letter and provides a self-contained guide for each path

Pre-scaffold gate that reads memory, detects build-path signals, checks for contradictions, and flags prerequisite risks — silently passing through when everything is consistent

Team initialization flow (Phase 1 proposal + Phase 2 creation)

Use when applying the .ai CORE_SKILL.md operating system, choosing Copilot CLI or VS Code playbooks, doing inspect-first coding, minimal patches, debugging, repo edits, docs, beginner handoffs, verification, or reusable AI coding workflows.