Pete McWilliams
Community@petemcw · Minneapolis, MN
Pete McWilliams publishes Claude Code skills for autonomous TDD development, architecture decision records, issue triage, and evidence-backed codebase explanation.
Agent Skills by Pete McWilliams
Showing 14 vetted skills indexed across 1 GitHub repositories.
petemcwdomain-modeling
Build and refine a project domain model through glossary and ADR documentation.
petemcwarchitecture-decision-records
Capture architectural decisions as structured ADR documents with context, alternatives, and rationale.
petemcwfarseer
Plan large work efforts as decision-ticket maps on an issue tracker.
petemcwbut-why
Investigates design rationale behind code by querying git history, tickets, docs, chat, and observability sources in parallel.
petemcwplanner
Transforms feature requests into structured implementation plans with task breakdowns and TDD requirements.
petemcwunderstand
Explains how code works and why it was built that way in plain language.
petemcwbut-how
Explains how code subsystems work by synthesizing parallel codebase explorations into architectural walkthroughs.
petemcwtriage
Move issues through a state machine of roles and write agent-ready briefs.
petemcwgit-guardrails
Configure Claude Code hooks to block dangerous Git commands before execution.
petemcwdeslop
Rewrites text to remove AI writing patterns and restore natural human voice.
petemcwteach
Creates interactive HTML lessons and learning records in a persistent teaching workspace.
petemcworchestrate
Execute implementation plans with parallel TDD workers and hook-based quality gates.
petemcwrepo-setup
Configures a repository for autonomous TDD development through interactive setup.
petemcwinterviewer
Interviews users in structured question rounds to surface hidden assumptions and settle design decisions.
Frequently Asked Questions About Pete McWilliams
FAQPage SchemaWhat tasks can I accomplish with Pete McWilliams' skills?▼
You can plan features as structured TDD implementation plans, execute them with parallel workers, record architecture decision records, triage issues into agent-ready briefs, explain subsystems and design rationale with cited evidence, block destructive Git commands, and remove AI tells from writing.
Who are these skills designed for?▼
Software engineers and technical leads practicing autonomous, test-driven development in Claude Code. They suit developers who want documented architecture decisions, evidence-backed explanations of legacy code, structured issue triage, and guardrails against destructive Git operations.
How do I set up a repository for autonomous development with these skills?▼
Run the repo-setup skill once to configure a repository for TDD-based autonomous development with Farseer. Then use planner to create implementation plans from feature descriptions and orchestrate to execute them with parallel TDD workers.
What prerequisites or dependencies do these skills require?▼
Skills run inside Claude Code; orchestrate requires a plan previously created by the planner skill. The but-why skill discovers available MCPs to query evidence sources like source control, issue trackers, chat, observability, and analytics. Git-guardrails installs Claude Code hooks.
How do the explanation skills differ from each other?▼
Use but-how for runtime behavior, code walkthroughs, and layering or ownership questions; use but-why for design rationale, regressions, and postmortems backed by cited evidence. The understand skill combines both into one plain explanation of a change or subsystem.