Launches the real build on its target runtime and proves six gates — launch, render, input, core loop, a designed outcome, and restart — recording everything in qa/verification.json.
Turns an existing game design doc into a production-level ART_DIRECTION covering visual style, camera, functional colour/light/material, HUD, motion and audio.
A business-analysis skill that pinpoints who actually pays and the lawful monetization move closest to real revenue for your product, service, audience, or open-source tool.
Scaffolds a React + Tailwind + shadcn/ui project and bundles it into a single self-contained HTML artifact for claude.ai.
Turns raw git commit history into polished, customer-friendly changelogs and release notes.
A decision-tree-driven skill for labeling cell types in scRNA-seq data via manual markers, automated classifiers, or reference label transfer.
Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery that extracts constraints, classifies project scale, and hands off to spec generation.
Writes and validates Python protocols for Opentrons OT-2/Flex robots — pipetting, serial dilutions, PCR, and hardware module control.
A repo-local scaffolder that generates a schema-valid SKILL.md, registers it in registry.yaml, and runs validation for the SciAgent-Skills repository.
A codeArbiter skill that scans an existing codebase with six parallel read-only scouts and back-fills the full set of project-state documents without guessing.
A strict commit-discipline skill that lets nothing reach version control until nine blocking gates — from explicit authorization to a clean post-commit tree — are cleared.
Builds a complete LaTeX/PDF literature survey on a research topic with 60+ verified citations, 6–10 topic-specific figures, and a classified literature table.
Audits a paper (PDF/DOI/arXiv) across image, numerical, and logical evidence tracks and produces a Level 1–4 graded, reviewable evidence report.
Turns a research question into a complete experiment package: design doc, runnable code, results.json with provenance, publication-grade figures, and a structured report.
Gives Claude Code grounded, cited recall over the memory, rules and decisions that every coding agent on the machine has written, all stored locally.
Makes Claude compute Bazi / Four Pillars charts with OpenFate's deterministic MCP tools instead of guessing pillars, Da Yun, or True Solar Time.
An output-style skill that reshapes Claude's replies into a rundown brief: TL;DR, status checklist, and numbered next moves.
Compresses a document, thread, transcript, or pasted text into a scannable TL;DR briefing.
Scores content against an 80-item CORE-EEAT benchmark before publishing, flags critical trust failures, and returns a prioritized fix plan.
Turns a keyword, topic, or URL into a publish-ready blog post, landing page, or full rewrite with metadata, JSON-LD, and an internal linking plan.