By Smirnov-Labs
Codebase health check via git history — surfaces high-churn files, bus factor, bug hotspots, velocity trends, and firefighting patterns before you read a line of code
Get a second opinion on your current implementation plan by sending it to Codex for independent review. Use after brainstorming, after writing a plan, or when you want to iterate on a plan before execution. Triggers on 'get a second opinion', 'review plan with codex', 'codex review', or 'iterate on plan'.
Use when reviewing an implementation plan document (docs/superpowers/plans/*.md or similar) for LLM-style overengineering before implementation. Runs a rubric-driven Claude pass plus a Codex adversarial pass, merges findings, and proposes specific edits to slim the plan. Triggers on 'check this plan for bloat', 'is this overengineered', 'detect overengineering', or invoked as /detect-overengineering.
Use when the user wants a git-history health check of an unfamiliar or inherited repository — triggers on "git recon", "codebase health check", "analyze this repo's history", "where are the landmines", or onboarding/due-diligence framing. Do NOT use for architecture review, bug-fixing, or feature work; this skill reads history, not code.
Use when the user needs to create a presentation, pitch deck, slide deck, or visual summary about a project, codebase, website, or topic. Triggers on requests like 'build a deck', 'create a presentation', 'make slides about', or 'pitch deck for'.
Use when reading or reporting what automated PR reviewers left before merging — Codex (`chatgpt-codex-connector`) and an Architecture-Review / SAR GitHub Action (`github-actions[bot]`). Triggers on "what did the bots say", before declaring a PR done or merging, or when a Codex finding or clean verdict seems missing because `gh pr view --json comments` came back empty. Read-only (does not commit or push); for auto-fixing PR feedback use `/pr-fix` instead.
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.
A Claude Code skills marketplace and starter template that bundles reusable AI workflows, a Memory Bank system for persistent project context, custom slash commands, and an automated architecture reviewer -- everything you need to supercharge Claude Code on any project.
# 1. Register this marketplace (one-time)
/plugin marketplace add smirnov-labs/claude-skills
# 2. Install any plugin (pick the ones you want)
/plugin install presentation-tools@smirnovlabs-claude-skills
/plugin install plan-utilities@smirnovlabs-claude-skills
/plugin install git-recon@smirnovlabs-claude-skills
/plugin install pr-utilities@smirnovlabs-claude-skills
Or from the CLI outside a session:
claude plugin marketplace add smirnov-labs/claude-skills
claude plugin install presentation-tools@smirnovlabs-claude-skills
Once installed, skills activate automatically based on what you ask. Say "build a pitch deck for this project", "get a second opinion on this plan", or "run a git recon on this repo" — or invoke directly with /presentation-blueprint, /codex-plan-review, or /git-recon.
| Skill | Plugin | What it does | Trigger phrases |
|---|---|---|---|
| presentation-blueprint | presentation-tools | End-to-end presentation consultant: analyzes codebases/websites/projects, crafts strategic blueprints, and renders polished decks via document-skills:pptx | "build a deck", "create a presentation", "pitch deck for" |
| codex-plan-review | plan-utilities | Sends your current plan to Codex 5.4 (high-effort, read-only) for an independent architectural second opinion before you execute | "review plan with codex", "get a second opinion", "iterate on plan" |
| detect-overengineering | plan-utilities | Audits an implementation-plan doc for LLM-style overengineering: a rubric-driven Claude pass plus a Codex adversarial pass, merged into specific edits that slim the plan | "check this plan for bloat", "is this overengineered", "detect overengineering" |
| git-recon | git-recon | 12-month git-history health check: surfaces high-churn files, bus factor, bug hotspots, velocity trends, and firefighting patterns before you read any code | "git recon", "codebase health check", "where are the landmines" |
| reading-bot-pr-reviews | pr-utilities | Read-only: fetches every automated PR review (Codex across its 3 endpoints + the Architecture/SAR review), filters on exact bot logins, and reports a severity-classified merge verdict so no finding — or clean pass — is missed | "what did the bots say", "read the PR reviews", "did Codex/the SAR pass" |
The presentation-blueprint skill requires document-skills:pptx for rendering:
/plugin install document-skills@anthropic-agent-skills
The codex-plan-review skill requires the Codex CLI on your PATH with a gpt-5.4-codex model available.
The git-recon skill needs only git — runs locally against the repo you're standing in.
The reading-bot-pr-reviews skill requires the GitHub CLI (gh) authenticated against the repo, and a repo whose PRs are reviewed by Codex and/or an Architecture-Review GitHub Action.
| Component | Location | Description |
|---|---|---|
| Skills Marketplace | .claude-plugin/marketplace.json + skills/ | Installable skills that other Claude Code instances can pull from github:smirnov-labs/claude-skills |
| Memory Bank | .claude/memory-bank/ | Structured documentation templates that give Claude full project context across sessions |
| Custom Slash Commands | .claude/commands/ | /plan, /pr, /memory, /loop-review -- ready-to-use workflows |
| Architect-Gate | .github/claude/ | Automated architecture review that runs on every PR via CI |
Want the full Memory Bank + Architect-Gate + commands for a new project? Clone the repo:
git clone https://github.com/smirnov-labs/claude-skills.git my-project
cd my-project
rm -rf .git # Remove template git history
git init # Start fresh
npx claudepluginhub smirnov-labs/claude-skills --plugin presentation-toolsThe /ship orchestrator: conducts the Shipwright Method loop (tier classification, phase-by-phase execution via superpowers + claude-skills, evidence recording) and enforces its gates with five fail-open lifecycle hooks
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
Comprehensive 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.
This skill should be used when users need to generate ideas, explore creative solutions, or systematically brainstorm approaches to problems. Use when users request help with ideation, content planning, product features, marketing campaigns, strategic planning, creative writing, or any task requiring structured idea generation. The skill provides 30+ research-validated prompt patterns across 14 categories with exact templates, success metrics, and domain-specific applications.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
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.