Golden Path — Testing skill for Claude Code
The golden path.
How to install Golden Path
Installs to ~/.claude/commands/pierry-harness-kit-golden-path.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/Pierry/harness-kit/HEAD/.claude/commands/golden-path.md -o ~/.claude/commands/pierry-harness-kit-golden-path.md Restart Claude Code, or start a new session, for it to be picked up.
What Golden Path does
description: The golden path. One command, idea to merged PR. Runs the full pipeline, prd → prp → plan → dev → test → pr, with sensor + eval gates at every stage.
Golden path. Idea → merged PR. Paved, opinionated, supported. The recommended way; not the only way (step off any time, see Detours).
Full reference: `docs/GOLDEN-PATH.md`.
Flags
Passed through to the SSE half (`/sse:run`):
--local: stop after/sse:test, no PR. Dev + test locally.--sdd: spec-driven loop varia
Alternatives in Testing
- Obsidian Graduate — Promote an idea fragment into a full project spec with tasks, board entries, and structure 277 ★
- Project PRD — Jesteś doświadczonym menedżerem produktu, którego zadaniem jest stworzenie kompleksowego dokumentu wymagań pro 265 ★
- Claude Dev Skill — A Claude Code custom skill that turns Claude into a Tech Lead — coordinating parallel Worker Agents through a 112 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Wb Dev Live Testing
Load directions via mcpwork-buddywb_run("agent_docs", {"path": "dev/live-testing-directions", "depth": "full"}
Crewbook Build
You bring the idea. Your AI team ships the software. Crewbook: Build sets up a Claude Code agent team (PO, Lea
Prp PRD
Interactive PRD generator - problem-first, hypothesis-driven product spec with back-and-forth questioning
PM Working Backwards Agent
Multi-agent CrewAI pipeline that turns a product problem statement into a research brief, PRFAQ, BRD, and buil
Spec Feature
Run the full feature specification pipeline (prd → techspec → tasks) end to end.
Analyze Spec
Full requirements analysis pipeline. Takes a raw TZ either from a file path OR from text pasted in the current
Related Agents
Reliability Engineer
Python delivery agent for quality gates and test infrastructure. Owns test suite (>=80% coverage enforced), go
Idea Scorer
Gates candidate ideas on Stage One, then scores survivors against the real rubric. Runs in a fresh context dur
Full Auto
Fully autonomous pipeline from idea to implementation. Writes the spec, clarifies it, fixes gaps, then plans,