Claude Skills by Paretofilm

Adapt an existing project to the Superpowers + GStack workflow. Analyzes the project, identifies gaps, updates CLAUDE.md routing without losing existing content, and sets up required structure.

Write a structured handoff file (YAML frontmatter + prose) to docs/superpowers/handoff.md before /clear or /compact. Different from /context-save (gstack) — survives across machines and restores without gstack installed.

Generate beautiful, pedagogical HTML companions for superpowers-gstack MD artifacts (design docs, handoffs, plans). Auto-opens via --open flag. Generates per-directory dashboards. Triggered manually or via PostToolUse hook on Write/Edit of artifact-pattern MD files.

Use after a PRD, spec, or implementation plan for an iOS app or feature — before implementation begins. Validates the artifact against Apple Human Interface Guidelines (iOS) via WebFetch citations: vocabulary, controls/touch targets, navigation paradigm, modal presentation, gestures, system surfaces, keyboard handling, haptics, semantic colors, animation timing, privileged operations, accessibility, app lifecycle. Complementary to pitfall-verification ("will this work?") and quality-review ("...

One-shot XCUITest scaffolding for macOS SwiftUI apps. Audits the project, generates ranked TIER-1/2/3 test stubs, suggests accessibility identifiers with batch confirmation, and emits a Claude-readable xcresult runner script. Manual invocation only — modifies project files.

Use after a PRD, spec, or implementation plan for a macOS app or feature — before implementation begins. Validates the artifact against Apple Human Interface Guidelines via WebFetch citations: vocabulary, control choices, keyboard shortcuts, semantic colors, sheets/popovers/alerts, animations, privileged operations, accessibility, menu bar, app lifecycle, dock behavior, App menu. Complementary to pitfall-verification ("will this work?") and quality-review ("will this feel good?") — this asks ...

Track-aware wrapper around gstack's /office-hours skill. Runs the upstream office-hours session (six forcing questions / builder mode), detects native vs web intent from the resulting design doc, asks the platform question (iOS / macOS / both) if native, writes .gstack/track, renders DESIGN.html via htmlify and OPENS it in Safari BEFORE the approval gate, then asks "Approve / Revise / Restart" — fixing the upstream "approve-then-read" UX bug. On approval for native projects, suggests /superpo...

Use after completing any PRD, spec, plan, or code implementation — verifies that artifact-specific pitfalls (security, idempotency, integration contracts, edge cases, LLM output) do not apply before declaring work done. Two rounds max.

Use after completing any PRD, spec, or implementation plan — before implementation begins. Hunts perceived-quality pitfalls (silent failures, missing loading states, empty states, error recovery, state drift, animations, AI output, sudo flows) that make a product feel cheap or broken even when it technically works. Complementary to pitfall-verification.

Generate a tailored CLAUDE.md with routing rules for the Superpowers + GStack workflow. Asks about project type, evaluates relevant skills from both frameworks, and produces a project-specific routing plan.

Apple-canon design system consultation for SwiftUI projects. Produces DESIGN.md (human source of truth) + a Swift Package starter (DesignSystem.swift + Package.swift + Tests) wired with semantic colors, SF Pro typography, Liquid Glass material discipline, named motion presets, and accessibility baseline. Orchestrates the swiftui-rag MCP surface for canonical patterns and HIG citations, uses /htmlify for Phase 3 proposal preview, chains into macos-native-review for HIG conformance gating. Use ...

> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking. **Goal:** Ship plugin v2.13.0 of `superpowers-gstack`, adding a new `/superpowers-gstack:autoimplement` skill that orchestrates phase-by-phase autonomous execution of a plan file with cross-model adversarial review and a hard kill-switch. **Architecture:** A thin orchestrat...

Auto-advance through a multi-phase implementation plan by dispatching a subagent per phase, then chaining /review, /pitfall-verification, and /codex review at the phase boundary. Skips the y/n prompts a user would always answer "yes" to when reviews pass; stops by default when /review or any review flags actionable issues; severe findings (security/data-loss/correctness) always stop regardless of policy; pitfall/codex findings can be treated as advisory via the policy question. Composes exist...