Skill

pagekit-new-run

Scaffold a new fully-logged PageKit run folder by name. Wraps scripts/new-run.sh. Use when starting any PageKit run; prefer this over creating run folders by hand so structure stays consistent with the run-logging framework.

Install

npx claudepluginhub hnshah/pagekit --plugin pagekit

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Wraps `scripts/new-run.sh`. Creates `runs/<run-name>/` with the full fully-logged layout: goal, models, working-log, sources/README, prompts/01-07-*.md (copied from the canonical per-step prompts), outputs/NN-*-output.md placeholders, per-step artifact placeholders, evaluation and evaluator-pass templates.

SKILL.md

Similar Skills

ui-ux-pro-max

Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.

ui-ux-pro-max

57.6k

context7-mcp

Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.

context7-plugin

51.8k

startup-financial-modeling

Builds 3-5 year financial models for startups with cohort revenue projections, cost structures, cash flow, headcount plans, burn rate, runway, and scenario analysis.

startup-business-analyst

32.9k

Stats

Stars5

Forks2

Last CommitApr 16, 2026

Actions

View Source View Plugin View on GitHub View README

PageKit — Scaffold a New Run

Wraps scripts/new-run.sh. Creates runs/<run-name>/ with the full fully-logged layout: goal, models, working-log, sources/README, prompts/01-07-.md (copied from the canonical per-step prompts), outputs/NN--output.md placeholders, per-step artifact placeholders, evaluation and evaluator-pass templates.

Read first

../pagekit/references/run-logging.md — the fully-logged tier definition

../pagekit/references/method.md — the method at a glance

Procedure

Confirm the run name with the user. Use a slug (lowercase, hyphenated).

Run: bash scripts/new-run.sh <run-name>.

Tell the user where the scaffold landed and what to fill next (goal.md and sources/).

Why use this skill instead of the script directly

The conversation logs the choice and the name, which helps later when the run is reviewed.

It is the on-ramp to pagekit (the orchestrator skill) for a complete run.

Failure modes

runs/<run-name> already exists → suggest a different name.

Repo not at the root → cd to the repo root and retry.

Hand off to the pagekit orchestrator, or invoke pagekit-signal-doc directly if the user wants to drive step by step.