Pharn Ship — Testing skill for Claude Code
Run the PRODUCT pipeline in order so a PHARN user need not re-type or memorize it: /pharn-spec → [human approves the SPEC] → /pharn-plan → /pharn-grill → /pharn-build → /pharn-regress → /pharn-verify.
How to install Pharn Ship
Installs to ~/.claude/commands/pharn-dev-pharn-oss-pharn-ship.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/pharn-dev/pharn-oss/HEAD/.claude/commands/pharn-ship.md -o ~/.claude/commands/pharn-dev-pharn-oss-pharn-ship.md Restart Claude Code, or start a new session, for it to be picked up.
What Pharn Ship does
description: "Run the PRODUCT pipeline in order so a PHARN user need not re-type or memorize it: /pharn-spec → [human approves the SPEC] → /pharn-plan → /pharn-grill → /pharn-build → /pharn-regress → /pharn-verify → [human decides merge/fix/abandon]. The seventh, terminal pipeline stage (pharn/ARCHITECTURE.md §6), realized as a GATED meta-orchestrator over stages 1–6 — the agent INVOKES each stage (advisory); WHETHER to proceed past a stage is read from that stage's STRUCTURAL floor verdict
Alternatives in Testing
- Flow Spec — NLSpec authoring — use when you need a structured specification from multi-AI research and consensus 2.8k ★
- Agent Skills Spec — A skill is a folder of instructions, scripts, and resources that agents can discover and load dynamically to p 1.9k ★
- Grill — Sharpen a fuzzy idea into §G/§C before spec 1.1k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Pharn Spec
Turn a user's prose intent into a structured, human-approved features/ /SPEC.md — the head of the product pipe
Pharn Loop
Run the PRODUCT pipeline as a BOUNDED, FLOOR-GATED auto-iteration: the same gated chain as /pharn-ship (/pharn
Sdflow Skills
Spec-driven development workflow for Claude Code / Codex: clarify → grill → generate the four artifacts, multi
Parallel Ship
Dynamic parallel pre-merge check with platform-routed Phase 1 gates (type/build + lint + test with coverage),
QA Phase
Run QAPhase — the autonomous acceptance-and-ship QA gauntlet. Proves a finished story end-to-end (spec-gap/gri
Ruver Feature Delivery
Ruver graph — grill → spec → tickets → TDD. MCP first, error if unavailable, no invent, then implement/ship
Related Agents
Plan Judge Agent
Judges a whole set of step plans as a set — does it actually reach a finished product? Checks coverage against
Mx Shipkit Builder
Use this agent to integrate the Ship Kit (analytics, SEO, Stripe payment, feedback widget, contact footer) int
Feature Build
Use when building a new feature from scratch. Chains search → plan → code → review → verify → learn in sequenc