Boardgame-design skills for Claude Code: rules versioning, balance reports, checklist enforcement, evidence-first verification, data pipelines, bot evaluation, and review tooling. Complements obra/superpowers.
Use after a batch of playtest or simulation runs. Scans game logs for crash signatures, negative resources, stuck rounds, lopsided scores, zero-action games — surfaces these before declaring the run successful.
Use BEFORE presenting any analysis, balance report, win-rate claim, strategy comparison, or training run summary. Blocks the report until n, confidence intervals, lobby composition, rules version, and baseline comparison are stated.
Use when running balance or strategy bot evaluation. Enforces smart-only lobbies (no mixed difficulties for balance claims), n≥1000 for balance, per-player-count and per-founder-ability sweeps, and proper baseline naming.
Use when any project checklist is being walked — REPORT_CHECKLIST.md, design review checklist, deploy preflight, monkey-test verification. Forces explicit pass/fail with evidence for every item, no "looks fine" skips.
Use when building or modifying an xlsx → JSON → engine data pipeline. Templates the pipeline (xlsx reader → schema-validated JSON → typed TS/Python import) and adds a diff job that runs on xlsx change.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Requires
obra/superpowers. bg-superpowers is a domain-specific complement, not a replacement.
Boardgame-design skills for Claude Code, Codex (CLI + App), and Cursor. Promotes recurring rules from CLAUDE.md files — xlsx-as-golden-reference, smart-only balance lobbies, report quality gates, evidence-first verification, versioned design docs — into invokable skills that auto-trigger at the right moments.
| Skill | When it fires |
|---|---|
using-bg-superpowers | Auto-loads on SessionStart. Index + invocation gate for the rest. |
rules-version-auditor | Editing xlsx, rules.md, or code constants that hold game numbers. |
balance-report-critic | About to present any analysis or win-rate claim. |
checklist-enforcer | A project checklist (REPORT_CHECKLIST, preflight) is being walked. |
evidence-first-verifier | About to claim "fixed", "passing", "deployed", "above baseline". |
versioned-design-doc-keeper | Writing to a vXpYY-named directory or file. |
data-pipeline-builder | Building or modifying an xlsx → JSON → engine pipeline. |
interactive-review-tool | Need a browser-based click-edit tool for design artifacts. |
bot-battle-referee | Running balance or strategy bot evaluation. |
anomaly-scanner | After a batch of playtest or simulation runs. |
seasoned-war-gamer | Veteran-player critique of a mechanic, rule, or counter design. |
Since v0.2.0, the repo is a multi-plugin marketplace. The plugin itself lives under plugins/bg-superpowers/; the repo root holds marketplace manifests (one for Claude Code, one for Codex) and shared tooling.
bg-superpowers/ # repo root = marketplace
├── .claude-plugin/marketplace.json # Claude Code marketplace
├── .agents/plugins/marketplace.json # Codex marketplace
├── README.md LICENSE scripts/
└── plugins/bg-superpowers/ # the actual plugin
├── .claude-plugin/plugin.json
├── .codex-plugin/plugin.json
├── .cursor-plugin/plugin.json
├── skills/<name>/SKILL.md × 11
├── hooks/{hooks.json, hooks-cursor.json, session-start, run-hook.cmd}
└── CLAUDE.md
claude plugin marketplace add taojiastanford/bg-superpowers
claude plugin install bg-superpowers@bg-superpowers-marketplace
User-scope install — available in every new Claude Code session, every directory. Verify with claude plugin list.
Update later:
claude plugin update bg-superpowers
# restart the session for the update to take effect
First install Codex CLI itself if you haven't:
sudo npm i -g @openai/codex # requires Node >= 16; sudo if your npm prefix is root-owned
# or (when Homebrew's Codex cask is healthy): brew install --cask codex
Sign in once (opens a browser):
codex # then exit after the sign-in flow completes
Register the bg-superpowers marketplace:
codex plugin marketplace add taojiastanford/bg-superpowers
That writes a [marketplaces.bg-superpowers-marketplace] entry into ~/.codex/config.toml and clones the repo into ~/.codex/.tmp/marketplaces/bg-superpowers-marketplace/.
Then enable the plugin. Codex's CLI has no plugin install subcommand — pick one:
Interactive (recommended): run codex, type /plugins, find bg-superpowers in the picker, toggle it on. Exit.
Manual: add this block to ~/.codex/config.toml:
[plugins."bg-superpowers@bg-superpowers-marketplace"]
enabled = true
Confirm with codex plugin marketplace add --help (sanity check the CLI is current) or simply cat ~/.codex/config.toml | grep bg-superpowers.
Codex App and Codex CLI share ~/.codex/config.toml. Once you've done the CLI steps above, the App automatically lists bg-superpowers in its Plugins panel with the same enable state. No separate install.
If your Codex App build exposes a "Custom marketplace" or "Developer mode" UI, you can add
taojiastanford/bg-superpowersthere directly without using the CLI.
In Cursor Agent chat:
/add-plugin https://github.com/taojiastanford/bg-superpowers
Or use the plugin marketplace UI and paste the GitHub URL.
v0.2 ships the Cursor manifest but Cursor parity has not been heavily tested.
Not supported in v0.2 — see CLAUDE.md TODO list.
For Claude Code, point the marketplace at the local repo:
claude plugin marketplace add /Users/taojia/.../boardgames/bg_superpowers
claude plugin install bg-superpowers
npx claudepluginhub taojiastanford/bg-superpowers --plugin bg-superpowersComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
Complete collection of 30 Claude Code skills for document processing, development, business productivity, and creative tasks