tjn-claude
The skills from the tjn.claude toolkit as installable plugins, for people who want them without replacing their own ~/.claude. Install everything (tjn-skills) or one domain bundle. Skills only: no hooks, settings, permission changes or background jobs.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/travisjneuman-claude)HTML
<a href="/listings/travisjneuman-claude"><img src="/api/listings/travisjneuman-claude/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
Use as GitHub Template (Recommended)
Click the green **"Use this template"** button at the top of this repo to create your own copy with a clean commit history. Then clone your new repo to `~/.claude/`.
Or clone directly
git clone https://github.com/travisjneuman/.claude.git ~/.claude
Already have a `~/.claude` that Claude Code created? Don't clone over it: download and run [`scripts/install-in-place.sh`](./scripts/install-in-place.sh), which turns it into a checkout and keeps your existing files.
Or: just the skills, as a plugin
If you already have a `~/.claude` you like, you can take only the skills. This adds no hooks, no settings, no permission changes, and no background jobs. Inside Claude Code:
/plugin marketplace add travisjneuman/.claude /plugin install tjn-skills@tjn-claude
That is all 183 skills. Claude Code lists plugin skills with their descriptions and trims the least-used ones when the listing outgrows its budget, so if you only work in one area, install a domain bundle instead (`tjn-frontend`, `tjn-mobile`, `tjn-backend`, `tjn-systems-infra`, `tjn-quality-security`, `tjn-data-ai`, `tjn-business`, `tjn-creative`, `tjn-research`, `tjn-workflow`); the full list with install lines is in [`skills/README.md`](./skills/README.md#install-as-a-plugin). `/skill-doctor` shows what each skill costs. The agents, commands, rules, hooks, and `CLAUDE.md` are not part of the plugin; for those, use the full install above. (Added November 2026; if it misbehaves on your Claude Code version, please open an issue.)
Optional: community marketplaces
About 80 third-party skill repos, cloned read-only into an ignored folder. The toolkit works without them.
bash ~/.claude/scripts/init-marketplaces.sh
Optional: your private layer
Your GitHub account, project folders, and private rules go in a gitignored `local/` folder; see [`local.example/README.md`](./local.example/README.md). Until you set `GITHUB_OWNERS` there, nothing is ever committed or pushed for you.
Start Claude Code
# Start Claude Code — the toolkit loads automatically claude
That's it. Claude Code loads the toolkit from `~/.claude/` in every session.
What runs on its own
Read this before the first session. Everything here is switched off with one line in `~/.claude/.env.local` (copy [`.env.example`](./.env.example)).
| What | When | Turn off with | |------|------|---------------| | Claude Code runs without permission prompts (`bypassPermissions`); the guard hook blocks only a short list of destructive commands in Bash and PowerShell | Every session | Change `permissions.defaultMode` in `settings.json` | | Fast-forward pull of `~/.claude` from its `origin`, and of the marketplace clones | Background, at most daily | `PULL_INTERVAL_HOURS=0` | | Install and update the plugins `settings.json` enables | After that pull | `PLUGIN_AUTOINSTALL=0` | | Install missing language servers for the LSP plugins (`npm install -g`, or `pacman` where passwordless sudo exists) | After that pull | `LSP_AUTOINSTALL=0` | | Tally which skills, agents, and commands were used (names and counts only, stays on your machine) | Daily | `DAILY_MAINTENANCE=0` | | Session transcripts are kept instead of deleted after 30 days (`cleanupPeriodDays` is 36500) | Always | Lower `cleanupPeriodDays` in `settings.json` | | Commit and push pending work in repos you own | Session end and daily, **only after you set `GITHUB_OWNERS`** | Leave `GITHUB_OWNERS` unset, or `SESSION_END_AUTOPUSH=0` |
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
.claude-plugin/marketplace.json · Manifest · 357 lines
- {
- "name": "tjn-claude",
- "owner": {
- "name": "travisjneuman",
- "url": "https://github.com/travisjneuman"
- },
- "description": "The skills from the tjn.claude toolkit as installable plugins, for people who want them without replacing their own ~/.claude. Install everything (tjn-skills) or one domain bundle. Skills only: no hooks, settings, permission changes or background jobs.",
- "plugins": [
- {
- "name": "tjn-skills",
- "source": "./skills",
- "skills": ".",
- "description": "All 183 skills, including the agent-<name> specialists that run as their own subagent. Don't combine it with the bundles below; they are subsets of it.",
- "category": "development",
- "author": {
- "name": "travisjneuman",
- "url": "https://github.com/travisjneuman"
- },
- "homepage": "https://claude.travisjneuman.com",
- "repository": "https://github.com/travisjneuman/.claude",
- "license": "MIT"
- },
- {
- "name": "tjn-frontend",
- "source": "./skills",
- "skills": [
- "./accessibility-a11y",
- "./agent-accessibility-expert",
- "./agent-browser-extension-developer",
- "./agent-i18n-specialist",
- "./agent-next-js-expert",
- "./agent-seo-specialist",
- "./agent-svelte-expert",
- "./agent-vue-nuxt-expert",
- "./frontend-enhancer",
- "./generic-design-system",
- "./generic-fullstack-design-system",
- "./generic-fullstack-ux-designer",
- "./generic-react-design-system",
- "./generic-react-feature-developer",
- "./generic-react-ux-designer",
- "./generic-static-design-system",
- "./generic-static-ux-designer",
- "./generic-ux-designer",
- "./i18n-localization",
- "./pwa-development",
- "./svelte-development",
- "./ui-animation",
- "./ui-research",
- "./vue-development"
- ],
- "description": "Web frontend: React, Vue, Svelte, design systems, UX, animation, accessibility. 24 skills.",
- "category": "development",
- "author": {
- "name": "travisjneuman",
- "url": "https://github.com/travisjneuman"
- },
- "homepage": "https://claude.travisjneuman.com",
- "repository": "https://github.com/travisjneuman/.claude",
- "license": "MIT"
- },
- {
- "name": "tjn-mobile",
- "source": "./skills",
- "skills": [
- "./agent-android-developer",
- "./agent-flutter-developer",
- "./agent-kotlin-expert",
- "./agent-mobile-architect",
- "./agent-mobile-release-manager",
- "./android-development",
- "./flutter-development",
- "./ios-development",
- "./kotlin-multiplatform",
- "./mobile-cicd",
- "./react-native"
- ],
- "description": "Mobile: iOS, Android, React Native, Flutter, Kotlin Multiplatform, mobile release. 11 skills.",
- "category": "development",
- "author": {
- "name": "travisjneuman",
- "url": "https://github.com/travisjneuman"
- },
- "homepage": "https://claude.travisjneuman.com",
- "repository": "https://github.com/travisjneuman/.claude",
- "license": "MIT"
- },
- {
- "name": "tjn-backend",
- "source": "./skills",
- "skills": [
- "./agent-api-designer",
- "./agent-api-integration-specialist",
- "./agent-auth-specialist",
- "./agent-database-expert",
- "./agent-django-fastapi-expert",
- "./agent-email-specialist",
- "./agent-event-driven-architect",
- "./agent-graphql-architect",
- "./agent-microservices-architect",
- "./agent-payment-billing-specialist",
- "./agent-pwa-specialist",
- "./agent-realtime-specialist",
- "./agent-serverless-specialist",
- "./api-design",
- "./authentication-patterns",
- "./database-expert",
- "./devex-sdk-design",
- "./edge-computing",
- "./email-systems",
- "./event-driven-architecture",
- "./generic-fullstack-feature-developer",
- "./graphql-expert",
- "./low-code-platforms",
- "./microservices-architecture",
- "./serverless-development",
- "./websockets-realtime"
- ],
- "description": "Backend: APIs, databases, GraphQL, auth, payments, realtime, serverless, microservices. 26 skills.",
- "category": "development",
- "author": {
- "name": "travisjneuman",
- "url": "https://github.com/travisjneuman"
- },
- "homepage": "https://claude.travisjneuman.com",
- "repository": "https://github.com/travisjneuman/.claude",
- "license": "MIT"
- },
- {
- "name": "tjn-systems-infra",
- "source": "./skills",
- "skills": [
- "./agent-blockchain-developer",
- "./agent-cli-developer",
- "./agent-cloud-architect",
- "./agent-cpp-expert",
- "./agent-desktop",
- "./agent-desktop-developer",
- "./agent-embedded-developer",
- "./agent-game-developer",
- "./agent-macos-developer",
- "./agent-observability-engineer",
- "./agent-python-expert",
- "./agent-rust-expert",
- "./agent-wasm-specialist",
- "./ar-vr-xr",
- "./blockchain-web3",
- "./devops-cloud",
- "./electron-desktop",
- "./embedded-iot",
- "./game-development",
- "./growth-engineering",
- "./macos-native",
- "./monitoring-observability",
- "./tauri-desktop"
- ],
- "description": "Systems and infrastructure: DevOps, cloud, observability, desktop, embedded, edge, languages. 23 skills.",
- "category": "development",
- "author": {
- "name": "travisjneuman",
- "url": "https://github.com/travisjneuman"
- },
- "homepage": "https://claude.travisjneuman.com",
- "repository": "https://github.com/travisjneuman/.claude",
- "license": "MIT"
- },
- {
- "name": "tjn-quality-security",
- "source": "./skills",
- "skills": [
- "./agent-code-explainer",
- "./agent-compliance-engineer",
- "./agent-devsecops-engineer",
- "./agent-documentation-writer",
- "./agent-e2e-test-specialist",
- "./agent-migration-specialist",
- "./agent-technical-writer",
- "./agent-test-generator",
- "./application-security",
- "./codebase-documenter",
- "./compliance-engineering",
- "./debug-systematic",
- "./generic-code-reviewer",
- "./generic-fullstack-code-reviewer",
- "./generic-react-code-reviewer",
- "./generic-static-code-reviewer",
- "./literature-review-planner",
- "./payment-integration",
- "./performance-engineering",
- "./security",
- "./statistics-verifier",
- "./tdd-workflow",
- "./tech-debt-analyzer",
- "./test-specialist"
- ],
- "description": "Code quality and security: review, debugging, refactoring, performance, application security, compliance. 24 skills.",
- "category": "development",
- "author": {
- "name": "travisjneuman",
- "url": "https://github.com/travisjneuman"
- },
- "homepage": "https://claude.travisjneuman.com",
- "repository": "https://github.com/travisjneuman/.claude",
- "license": "MIT"
- },
- {
- "name": "tjn-data-ai",
- "source": "./skills",
- "skills": [
- "./agent-data-engineer",
- "./agent-ml-engineer",
- "./agent-product-analytics-specialist",
- "./ai-ml-development",
- "./data-engineering",
- "./data-science",
- "./llm-app-development",
- "./product-analytics",
- "./seo-analytics-auditor"
- ],
- "description": "Data and AI: data engineering, data science, ML, LLM applications. 9 skills.",
- "category": "development",
- "author": {
- "name": "travisjneuman",
- "url": "https://github.com/travisjneuman"
- },
- "homepage": "https://claude.travisjneuman.com",
- "repository": "https://github.com/travisjneuman/.claude",
- "license": "MIT"
- },
- {
- "name": "tjn-business",
- "source": "./skills",
- "skills": [
- "./agent-monetization-expert",
- "./agent-startup-advisor",
- "./ai-policy-generator",
- "./battle-card-builder",
- "./business-strategy",
- "./contract-redliner",
- "./customer-persona-builder",
- "./customer-success",
- "./finance",
- "./financial-scenario-planner",
- "./fundraising-analyzer",
- "./grant-proposal-builder",
- "./hr-talent",
- "./innovation",
- "./investment-memo-generator",
- "./leadership",
- "./legal-compliance",
- "./marketing",
- "./monetization-strategy",
- "./operations",
- "./options-comparator",
- "./process-flowchart-designer",
- "./product-management",
- "./real-estate-analyzer",
- "./risk-management",
- "./sales",
- "./startup-launch",
- "./supply-chain-optimizer",
- "./sustainability-esg"
- ],
- "description": "Business: strategy, finance, marketing, sales, product, legal, operations, HR. 29 skills.",
- "category": "development",
- "author": {
- "name": "travisjneuman",
- "url": "https://github.com/travisjneuman"
- },
- "homepage": "https://claude.travisjneuman.com",
- "repository": "https://github.com/travisjneuman/.claude",
- "license": "MIT"
- },
- {
- "name": "tjn-creative",
- "source": "./skills",
- "skills": [
- "./agent-audio-engineer",
- "./agent-brand-strategist",
- "./agent-graphic-designer",
- "./agent-motion-designer",
- "./agent-video-producer",
- "./audio-production",
- "./brand-identity",
- "./content-repurposer",
- "./graphic-design",
- "./impact-report-writer",
- "./newsletter-creator",
- "./podcast-producer",
- "./video-production"
- ],
- "description": "Creative: brand, graphic design, video, audio, content. 13 skills.",
- "category": "development",
- "author": {
- "name": "travisjneuman",
- "url": "https://github.com/travisjneuman"
- },
- "homepage": "https://claude.travisjneuman.com",
- "repository": "https://github.com/travisjneuman/.claude",
- "license": "MIT"
- },
- {
- "name": "tjn-research",
- "source": "./skills",
- "skills": [
- "./agent-ux-researcher",
- "./career-path-planner",
- "./case-interview-practice",
- "./course-material-creator",
- "./debate-practice-coach",
- "./health-wellness",
- "./learning-gap-analyzer",
- "./onboarding-guide-creator",
- "./rd-management",
- "./recipe-card-creator",
- "./research-presenter",
- "./travel-planner",
- "./volunteer-coordinator"
- ],
- "description": "Research and planning: research presentation, analysis, education, personal planning. 13 skills.",
- "category": "development",
- "author": {
- "name": "travisjneuman",
- "url": "https://github.com/travisjneuman"
- },
- "homepage": "https://claude.travisjneuman.com",
- "repository": "https://github.com/travisjneuman/.claude",
- "license": "MIT"
- },
- {
- "name": "tjn-workflow",
- "source": "./skills",
- "skills": [
- "./agent-browser",
- "./agent-go-expert",
- "./agent-product-manager",
- "./agent-teams",
- "./core-workflow",
- "./event-planner",
- "./generic-feature-developer",
- "./generic-static-feature-developer",
- "./image-studio",
- "./status-report-generator",
- "./toolkit-router"
- ],
- "description": "Workflow: task routing, documentation, toolkit helpers. 11 skills.",
- "category": "development",
- "author": {
- "name": "travisjneuman",
- "url": "https://github.com/travisjneuman"
- },
- "homepage": "https://claude.travisjneuman.com",
- "repository": "https://github.com/travisjneuman/.claude",
- "license": "MIT"
- }
- ]
- }
README.md · README · 519 lines · 1 finding marked
- <div align="center">
- <picture>
- <source media="(prefers-color-scheme: dark)" srcset="https://capsule-render.vercel.app/api?type=waving&color=0:1a1a2e,50:6366f1,100:d946ef&height=220§ion=header&text=tjn.claude/&fontSize=72&fontColor=ffffff&fontAlignY=35&desc=The%20Ultimate%20Claude%20Code%20Toolkit&descSize=20&descColor=c4b5fd&descAlignY=55&animation=fadeIn" />
- <source media="(prefers-color-scheme: light)" srcset="https://capsule-render.vercel.app/api?type=waving&color=0:e0e7ff,50:6366f1,100:9333ea&height=220§ion=header&text=tjn.claude/&fontSize=72&fontColor=1e1b4b&fontAlignY=35&desc=The%20Ultimate%20Claude%20Code%20Toolkit&descSize=20&descColor=4338ca&descAlignY=55&animation=fadeIn" />
- <img alt="tjn.claude/ — The Ultimate Claude Code Toolkit" src="https://capsule-render.vercel.app/api?type=waving&color=0:1a1a2e,50:6366f1,100:d946ef&height=220§ion=header&text=tjn.claude/&fontSize=72&fontColor=ffffff&fontAlignY=35&desc=The%20Ultimate%20Claude%20Code%20Toolkit&descSize=20&descColor=c4b5fd&descAlignY=55&animation=fadeIn" width="100%" />
- </picture>
- <br/>
- [](./CHANGELOG.md)
- [](./docs/SETUP-GUIDE.md)
- [](https://claude.travisjneuman.com)
- [](./LICENSE)
- [](https://github.com/travisjneuman/.claude/generate)
- [](./skills/MASTER_INDEX.md)
- [](./agents/README.md)
- [](./docs/COMMANDS.md)
- [](./plugins/marketplaces/)
- [](./docs/MARKETPLACE-GUIDE.md)
- [](./hooks/README.md)
- [](./templates/README.md)
- </div>
- ---
- ## 🚀 What Is This?
- A drop-in configuration layer for [Claude Code](https://docs.anthropic.com/en/docs/claude-code) that transforms it from a capable AI assistant into an enterprise-grade development powerhouse.
- **One `git clone` gives you** 183 domain skills, 10 specialist agents, 86 community marketplaces with 11,300+ additional skills, 29 slash commands, 7 lifecycle hooks — all auto-activating based on what you're working on. No manual configuration required.
- **How it works:** Describe what you want in plain language. Everything is installed and available, but only a small core of skills keeps its full description in Claude's context. The rest is listed by name and found through a generated index ([`INDEX.md`](./INDEX.md), [`index/graph.json`](./index/graph.json)) and the `toolkit-router` skill, so a large toolkit costs almost nothing until something is needed. Language rules load only for matching files.
- **Runs in YOLO mode on purpose:** `bypassPermissions` plus a Full Access+++ contract in `CLAUDE.md` (your request authorizes in-scope work; explicit "do not"s are absolute), backed by a guard hook that blocks a short list of footguns. Personal and machine-specific rules live in a gitignored [`local/`](./local.example/README.md) layer.
- **Cross-machine Git safety:** a session-start banner flags repos that are behind, unpushed, dirty, or diverged. Session-end and daily maintenance hooks checkpoint all pending changes in configured owned repos, including unfinished work, then push through the configured runner when repository state permits. They stop for conflicts or possible secrets and report other push blockers. Marketplace clones are pulled at most daily and are never committed.
- **Who it's for:** Developers who use Claude Code and want deeper domain expertise, structured workflows, and quality guardrails without manual setup.
- ---
- ## Route Map
- For agents (and people) looking for one thing: open the smallest file that answers, then stop. Grep indexes; don't read them whole.
- Up: [github.com/travisjneuman](https://github.com/travisjneuman) · Not here: per-project instructions belong in each project's own `CLAUDE.md` or `AGENTS.md`; personal and machine-specific rules live in the gitignored `local/` layer.
- | Step | Open | Answers |
- |------|------|---------|
- | 1 | [`CLAUDE.md`](./CLAUDE.md) (always loaded) | How to work: autonomy, git, safety, browser access, model selection, review-based validation |
- | 2 | [`INDEX.md`](./INDEX.md): `rg -n -i "<keyword>" ~/.claude/INDEX.md`, or invoke the `toolkit-router` skill, which does this | Which skill, agent, command, rule, checklist, or marketplace repo fits |
- | 3 | `skills/<name>/SKILL.md`, `agents/<name>.md`, `rules/<lang>.md`, `docs/reference/<kind>/<name>.md` | The procedure itself |
- | Need / keywords | Open | Notes |
- |-----------------|------|-------|
- | skill, domain, specialist, "is there something for X" | [`INDEX.md`](./INDEX.md), [`skills/MASTER_INDEX.md`](./skills/MASTER_INDEX.md) | Generated by `scripts/generate-index.mjs`; never hand-edit. Relationships: `index/graph.json` |
- | agent, subagent, `agent-*` | [`agents/README.md`](./agents/README.md) | Core agents live in `agents/`; other specialists are `agent-<name>` skills |
- | slash command, `/name` | [`docs/COMMANDS.md`](./docs/COMMANDS.md) | Sources in `commands/` |
- | language or stack rules, stack guide, checklist, workflow reference, tooling | [`docs/reference/README.md`](./docs/reference/README.md) | Lists every `rules/` file (path-scoped) and every on-demand reference doc |
- | hook, guard, secret scan, status line, session start/end | [`hooks/README.md`](./hooks/README.md) | Git hooks for this repo: `scripts/hooks/` |
- | marketplace, community skills | `index/marketplace-catalog.json`, [`docs/MARKETPLACE-GUIDE.md`](./docs/MARKETPLACE-GUIDE.md) | Catalog exists once marketplaces are pulled |
- | setup, new machine, configuration, troubleshooting | [`docs/README.md`](./docs/README.md) | Docs front door |
- | private rules, host settings, `local/` | [`local.example/README.md`](./local.example/README.md) | `local/` is gitignored |
- | durable project knowledge, documentation ownership | [`CLAUDE.md` → Memory and documentation](./CLAUDE.md#memory-and-documentation) | Owning subject note first; local layer supplies private routing |
- | image, logo, icon, illustration, visual asset create/edit/find | [`image-studio`](./skills/image-studio/SKILL.md) | Automatic reuse-first workflow; private runtime descriptor required |
- | scripts, counts, regenerate index | [`scripts/README.md`](./scripts/README.md), [`docs/COUNT-PIPELINE.md`](./docs/COUNT-PIPELINE.md) | Counts and index refresh are explicit, never automatic |
- | project or task templates | [`templates/README.md`](./templates/README.md) | |
- | version history, release notes | [`CHANGELOG.md`](./CHANGELOG.md) | |
- | contributing, pull requests | [`CONTRIBUTING.md`](./CONTRIBUTING.md) | |
- | security, reporting a vulnerability, trust model | [`SECURITY.md`](./SECURITY.md) | What full access trusts and how to narrow it |
- | audit findings, open improvement items | [`advisor-plans/README.md`](./advisor-plans/README.md) | Status table; done and open |
- | showcase website, claude.travisjneuman.com | [`website/README.md`](./website/README.md) | Next.js static export |
- | VS Code settings | [`vscode/README.md`](./vscode/README.md) | |
- | archived README, GSD tutorial, 2026-03 audits | [`archive/`](./archive/) | Historical only; see Contents below |
- ## Map
- ```mermaid
- graph LR
- R[README] --> C[CLAUDE.md]
- R --> I[INDEX.md]
- R --> D[docs/README]
- D --> REF[docs/reference/README]
- REF --> RU[rules/]
- R --> SK[skills/README]
- I --> SK
- R --> AG[agents/README]
- R --> CM[docs/COMMANDS.md]
- R --> HK[hooks/README]
- R --> SC[scripts/README]
- R --> TP[templates/README]
- R --> LE[local.example/README]
- R --> WS[website/README]
- ```
- ## Contents
- **This page:** [What Is This?](#-what-is-this) · [Route Map](#route-map) · [Quick Start](#-quick-start) · [What's Included](#-whats-included) · [How It Works](#-how-it-works) · [Key Features](#-key-features) · [Configuration](#-configuration) · [Multi-Machine Setup](#-multi-machine-setup) · [Platform Support](#-platform-support) · [What's New](#-whats-new) · [Documentation](#-documentation) · [Philosophy](#-philosophy)
- **Front doors**
- - [CLAUDE.md](./CLAUDE.md) — always-loaded constitution: autonomy, git, safety, review-based validation
- - [INDEX.md](./INDEX.md) — generated index of skills, agents, commands, rules, docs, marketplaces
- - [docs/README.md](./docs/README.md) — every guide, routed by need
- - [docs/reference/README.md](./docs/reference/README.md) — rules, stack guides, checklists, workflow and tooling references
- - [docs/COMMANDS.md](./docs/COMMANDS.md) — all slash commands by category (`commands/` holds only commands)
- - [skills/README.md](./skills/README.md) — skill routes and category browse aid
- - [agents/README.md](./agents/README.md) — core agents and how specialist agent skills work
- - [hooks/README.md](./hooks/README.md) — lifecycle hooks, token cost, guard behavior
- - [scripts/README.md](./scripts/README.md) — setup, maintenance, count and index scripts
- - [templates/README.md](./templates/README.md) — component, project, and operational templates
- - [local.example/README.md](./local.example/README.md) — template for the private `local/` layer
- **Archive** (historical, not routed by the index)
- - [archive/README-original.md](./archive/README-original.md) — the pre-v2.8.0 README, replaced by this streamlined one
- - [archive/GSD-TUTORIAL.md](./archive/GSD-TUTORIAL.md) — GSD workflow guide; GSD was removed from the toolkit
- - `archive/audits/` — 2026-03 compliance audits: [agents](./archive/audits/audit-agents-report.md), [hooks](./archive/audits/audit-hooks-report.md), [plugins](./archive/audits/audit-plugins-report.md), [skills](./archive/audits/audit-skills-report.md)
- ---
- ## ⚡ Quick Start
- ### Use as GitHub Template (Recommended)
- Click the green **"Use this template"** button at the top of this repo to create your own copy with a clean commit history. Then clone your new repo to `~/.claude/`.
- ### Or clone directly
- ```bash
- git clone https://github.com/travisjneuman/.claude.git ~/.claude
- ```
- Already have a `~/.claude` that Claude Code created? Don't clone over it: download and run [`scripts/install-in-place.sh`](./scripts/install-in-place.sh), which turns it into a checkout and keeps your existing files.
- ### Or: just the skills, as a plugin
- If you already have a `~/.claude` you like, you can take only the skills. This adds no hooks, no settings, no permission changes, and no background jobs. Inside Claude Code:
- ```
- /plugin marketplace add travisjneuman/.claude
- /plugin install tjn-skills@tjn-claude
- ```
- That is all 183 skills. Claude Code lists plugin skills with their descriptions and trims the least-used ones when the listing outgrows its budget, so if you only work in one area, install a domain bundle instead (`tjn-frontend`, `tjn-mobile`, `tjn-backend`, `tjn-systems-infra`, `tjn-quality-security`, `tjn-data-ai`, `tjn-business`, `tjn-creative`, `tjn-research`, `tjn-workflow`); the full list with install lines is in [`skills/README.md`](./skills/README.md#install-as-a-plugin). `/skill-doctor` shows what each skill costs. The agents, commands, rules, hooks, and `CLAUDE.md` are not part of the plugin; for those, use the full install above. (Added November 2026; if it misbehaves on your Claude Code version, please open an issue.)
- ### Optional: community marketplaces
- About 80 third-party skill repos, cloned read-only into an ignored folder. The toolkit works without them.
- ```bash
- bash ~/.claude/scripts/init-marketplaces.sh
- ```
- ### Optional: your private layer
- Your GitHub account, project folders, and private rules go in a gitignored `local/` folder; see [`local.example/README.md`](./local.example/README.md). Until you set `GITHUB_OWNERS` there, nothing is ever committed or pushed for you.
- ### Start Claude Code
- ```bash
- # Start Claude Code — the toolkit loads automatically
- claude
- ```
- That's it. Claude Code loads the toolkit from `~/.claude/` in every session.
- ### What runs on its own
- Read this before the first session. Everything here is switched off with one line in `~/.claude/.env.local` (copy [`.env.example`](./.env.example)).
- | What | When | Turn off with |
- |------|------|---------------|
- | Claude Code runs without permission prompts (`bypassPermissions`); the guard hook blocks only a short list of destructive commands in Bash and PowerShell | Every session | Change `permissions.defaultMode` in `settings.json` |
- | Fast-forward pull of `~/.claude` from its `origin`, and of the marketplace clones | Background, at most daily | `PULL_INTERVAL_HOURS=0` |
- | Install and update the plugins `settings.json` enables | After that pull | `PLUGIN_AUTOINSTALL=0` |
- | Install missing language servers for the LSP plugins (`npm install -g`, or `pacman` where passwordless sudo exists) | After that pull | `LSP_AUTOINSTALL=0` |
- | Tally which skills, agents, and commands were used (names and counts only, stays on your machine) | Daily | `DAILY_MAINTENANCE=0` |
- | Session transcripts are kept instead of deleted after 30 days (`cleanupPeriodDays` is 36500) | Always | Lower `cleanupPeriodDays` in `settings.json` |
- | Commit and push pending work in repos you own | Session end and daily, **only after you set `GITHUB_OWNERS`** | Leave `GITHUB_OWNERS` unset, or `SESSION_END_AUTOPUSH=0` |
- **Trust model.** The daily pull brings in whatever the `origin` of your `~/.claude` publishes, including hook scripts that then run on your machine. If you cloned this repo directly, that origin is this repo. If you'd rather review changes first, use the template (your copy becomes the origin and you merge upstream when you choose) or set `PULL_INTERVAL_HOURS=0` and pull by hand. `settings.json` is the maintainer's working configuration: review its `enabledPlugins`, `env`, and `permissions` and make them yours. Marketplace clones are other people's repositories, pulled at their latest commit and unreviewed; Claude can read and follow a skill from one. That is intended for a full-access setup, and [SECURITY.md](./SECURITY.md) says how to narrow it.
- ---
- ## 📦 What's Included
- | Component | Count | Description |
- |-----------|-------|-------------|
- | **[Skills](./skills/MASTER_INDEX.md)** | 183 | Domain expertise modules (React, security, DevOps, finance, etc.) |
- | **[Agents](./agents/README.md)** | 10 | Specialist subagents for focused tasks (code review, debugging, etc.) |
- | **[Commands](./docs/COMMANDS.md)** | 29 | Slash commands for common workflows |
- | **[Marketplace Repos](./plugins/marketplaces/)** | 86 | Community skill repositories (11,300+ additional skills) |
- | **[Hooks](./hooks/README.md)** | 7 | Wired public hooks (session lifecycle, status line, safety guards; not git hooks or the dispatcher) |
- | **[Templates](./templates/README.md)** | 17 | Project scaffolding and task templates |
- | **[Rules](./rules/)** | 10 | Stack-specific coding guardrails (TypeScript, Python, Go, Rust, etc.) plus web legal-exposure defaults |
- <details>
- <summary><strong>📋 Skills by Category</strong></summary>
- | Category | Skills |
- |----------|--------|
- | **Web Development** | `react-native`, `vue-development`, `svelte-development`, `flutter-development`, `pwa-development`, `electron-desktop`, `tauri-desktop`, `frontend-enhancer` |
- | **Backend & API** | `api-design`, `graphql-expert`, `database-expert`, `microservices-architecture`, `event-driven-architecture`, `websockets-realtime`, `serverless-development` |
- | **DevOps & Cloud** | `devops-cloud`, `monitoring-observability`, `performance-engineering`, `mobile-cicd` |
- | **AI & Data** | `ai-ml-development`, `llm-app-development`, `data-science` |
- | **Security** | `application-security`, `authentication-patterns` |
- | **Mobile** | `android-development`, `ios-development`, `macos-native`, `kotlin-multiplatform`, `react-native`, `flutter-development` |
- | **Quality** | `generic-code-reviewer`, `generic-feature-developer`, `generic-design-system`, `generic-ux-designer`, `test-specialist`, `tdd-workflow`, `debug-systematic`, `tech-debt-analyzer` |
- | **Business** | `business-strategy`, `finance`, `marketing`, `sales`, `product-management`, `hr-talent`, `legal-compliance`, `risk-management`, `operations`, `innovation` |
- | **Creative** | `brand-identity`, `graphic-design`, `video-production`, `audio-production`, `ui-animation`, `ui-research` |
- | **Productivity** | `codebase-documenter`, `reports-pdfs-and-slide-automation`, `content-repurposer`, `status-report-generator`, `core-workflow`, [`agent-desktop`](./skills/agent-desktop/SKILL.md) (native desktop app control) |
- | **Specialized** | `game-development`, `i18n-localization`, `seo-analytics-auditor`, `email-systems`, `payment-integration`, `product-analytics`, `growth-engineering`, `monetization-strategy` |
- | **Blockchain & Web3** | `blockchain-web3` (Solidity, DeFi, NFTs, Hardhat/Foundry) |
- | **Data Engineering** | `data-engineering` (ETL, Airflow, dbt, Kafka, BigQuery/Snowflake) |
- | **Edge & IoT** | `edge-computing`, `embedded-iot` (Cloudflare Workers, ESP32, FreeRTOS) |
- | **XR & Spatial** | `ar-vr-xr` (Unity XR, WebXR, ARKit, Vision Pro) |
- | **Compliance** | `compliance-engineering` (SOC2, HIPAA, GDPR, PCI-DSS) |
- | **Developer Tools** | `devex-sdk-design`, `low-code-platforms` (SDK design, Retool, Supabase, n8n) |
- | **Non-Tech** | `travel-planner`, `event-planner`, `recipe-card-creator`, `health-wellness`, `career-path-planner`, `real-estate-analyzer` |
- See **[MASTER_INDEX.md](./skills/MASTER_INDEX.md)** for the full listing with descriptions.
- </details>
- ---
- ## ⚙️ How It Works
- ### Dynamic Routing
- Every session loads `CLAUDE.md`, the unscoped rules, and the skill listing. Only the core skills and agents carry full descriptions there; every other skill, command, checklist, and stack guide is listed by name only, so it costs almost nothing until it is used. For specialized work, the `toolkit-router` skill greps the generated `INDEX.md` for the domain and loads what fits, including the indexed marketplace skills:
- ```
- Your prompt
- │
- ▼
- ┌──────────────────────────────┐
- │ Core skills (described) │ ← matched from their descriptions
- │ + toolkit-router → INDEX.md │ ← grep by domain for everything else
- └──────────┬───────────────────┘
- │
- ┌────────┼────────┬────────────┐
- ▼ ▼ ▼ ▼
- ┌──────┐ ┌──────┐ ┌──────┐ ┌────────────┐
- │Skills│ │Rules │ │Agents│ │ Marketplace│
- │ │ │& Chk │ │ │ │ skills │
- └──────┘ └──────┘ └──────┘ └────────────┘
- ```
- Path-scoped rules load only when matching files are read.
- ### Hook Lifecycle
- Hooks run automatically; most cost zero tokens:
- ```
- Session Start
- ├── Daily background pull (~/.claude, marketplaces, optional project repos)
- ├── Repo health banner (only when something needs attention)
- └── Private local hook (optional, from local/)
- Before Bash / PowerShell / Write / Edit
- └── Guard: blocks root rm -rf, force push, reset --hard, secret-file writes, AI trailers
- After File Edits
- └── Secret scan (tells Claude if a credential-looking string was written)
- After Each Response
- └── Once a day per machine: usage tally + commit-everything sweep (background)
- Session End
- └── Commit all pending work in configured owned repos, then push when repository state permits; log conflicts, possible secrets, and push blockers
- Status bar
- └── model · effort · folder (branch) · context % · 5h/7d usage · cost
- ```
- See **[hooks/README.md](./hooks/README.md)** for the full hook reference.
- ---
- ## 🔑 Key Features
- <details>
- <summary><strong>🏪 Marketplace — 86 marketplace repos, 11,300+ skills</strong></summary>
- The toolkit aggregates 86 community skill repositories as ignored local clones in `plugins/marketplaces/`. All are read-only (fetch but never push). Skills span security (Trail of Bits), full-stack development, scientific computing, SAP/enterprise, Elixir, Terraform, creative writing, and more. Some marketplace repos are **installed as plugins**, making their agents, commands, and skills fully active in the routing system alongside built-in resources. Non-installed repos contribute discoverable skills via keyword search.
- ```bash
- # Search marketplace skills
- find ~/.claude/plugins/marketplaces -name "SKILL.md" | xargs grep -li "kubernetes"
- # Update all marketplace repos
- bash ~/.claude/_pull-all-repos.sh
- ```
- See **[docs/MARKETPLACE-GUIDE.md](./docs/MARKETPLACE-GUIDE.md)** for the full catalog.
- </details>
- <details>
- <summary><strong>🛡️ Safety Guards</strong></summary>
- The `guard.js` hook blocks dangerous commands before execution, in Bash and in PowerShell (where it also blocks a recursive force delete of a drive or home root and piping a download into `Invoke-Expression`). It is pattern matching, a seatbelt rather than a sandbox; see [SECURITY.md](./SECURITY.md).
- | Blocked Pattern | Risk |
- |----------------|------|
- | `rm -rf /` / `rm -rf ~` | Filesystem destruction |
- Dismissed after review: Runs `rm -rf` against a root or home-directory path
- Line 312 on GitHub
- | `git push --force` | Overwrite remote history |
- | `DROP TABLE` / `TRUNCATE TABLE` | Database destruction |
- | `git reset --hard origin` | Discard all local changes |
- | `git clean -fd` | Delete untracked files |
- | `curl ... \| sh` | Pipe-to-shell (RCE) |
- | `npm publish` | Accidental package publication |
- | `chmod -R 777` | Overly permissive permissions |
- | `docker system prune -a` | Destroy all Docker resources |
- Additional safety: `guard.js` also blocks writes to `.env`, credential, key, `.ssh`, `.gnupg`, `.git/`, and `node_modules` files, and commits carrying AI attribution trailers. `secret-scan.js` checks every file Claude writes for credential-looking strings and tells Claude if it finds one.
- </details>
- <details>
- <summary><strong>🖥️ Cross-Platform</strong></summary>
- All hooks use a Node.js-based runner (`hooks/run-hook.js`) that resolves paths via `os.homedir()`. This avoids WSL path issues on Windows where `~` resolves to `/root/` instead of the Windows user home.
- On Windows, the runner explicitly prefers Git Bash (`C:\Program Files\Git\usr\bin\bash.exe`) over WSL bash to prevent drive mount failures on network drives.
- | Platform | Shell | Notes |
- |----------|-------|-------|
- | macOS | `/bin/bash` | Standard bash via Git or Homebrew |
- | Linux | `/bin/bash` | Standard bash |
- | Windows | Git Bash (preferred) | Avoids WSL drive mount errors |
- </details>
- <details>
- <summary><strong>🤖 Agent Teams</strong></summary>
- For complex tasks, spawn multiple specialist agents to work in parallel:
- - **Code review from multiple angles** — security, performance, tests
- - **Cross-layer features** — frontend + backend + database agents
- - **Competing hypotheses** — debug with parallel investigation
- Agent types include architecture analysts, debugging specialists, performance optimizers, security auditors, and many more specialists that run as `agent-*` skills. See **[agents/README.md](./agents/README.md)**.
- </details>
- <details>
- <summary><strong>🔌 MCP Servers</strong></summary>
- No MCP servers are configured by default, which keeps every session's context lean. Add one with `claude mcp add` when a project needs it; **[docs/MCP-SERVERS.md](./docs/MCP-SERVERS.md)** covers common options (memory, databases, GitHub, Context7) and their token cost. Browser work needs no MCP server: it uses the active app's built-in browser, then [`agent-browser`](./skills/agent-browser/SKILL.md), then Computer Use; Playwright, Puppeteer, and Selenium/WebDriver are prohibited.
- </details>
- <details>
- <summary><strong>🔄 Session Continuity</strong></summary>
- The toolkit maintains context between sessions automatically:
- 1. **Resume** — `claude --continue` / `--resume` reopen a previous conversation (auto memory is disabled in `settings.json`; durable preferences live in `CLAUDE.md`/`AGENTS.md`); `/handoff` writes an explicit handoff note when you want one
- 2. **Repo health** — `session-start-repo-health.sh` flags repos that need a pull, push, or reconciliation before you edit them
- 3. **Repo sync** — `session-start-pull.sh` fast-forward pulls in the background, at most once a day
- </details>
- ---
- ## 🛠️ Configuration
- ### Key Files
- | File | Purpose |
- |------|---------|
- | `CLAUDE.md` | Core rules: autonomy, workflow, git, safety, code standards |
- | `settings.json` | Claude Code settings, hook registrations, permissions |
- | `counts.json` | Public counts, identity lists, source revisions/digests and snapshot date |
- | `plugin.json` | Plugin metadata |
- ### Explicit count publication
- Public toolkit resources and committed manifest marketplace skill bodies are distinct populations. Local and hosted website builds consume the same generated snapshots. Pulling sources or committing does not regenerate them; authorize one explicit source refresh, inspect its output/diff, and then publish. Pins and recorded dates label selected source snapshots, not latest-upstream guarantees. See **[Count pipeline](./docs/COUNT-PIPELINE.md)** for commands, definitions, profile/portfolio destinations and the separate DESK-only media contract.
- ### Common Customizations
- **Add your own project directories** to auto-pull:
- ```bash
- cp ~/.claude/.env.example ~/.claude/.env.local
- # Edit CUSTOM_PROJECT_DIRS="/path/to/your/projects"
- ```
- **Switch action mode** between proactive (default) and conservative — see `docs/reference/workflows/action-policy.md`.
- **Disable a hook** — edit `settings.json` and remove the hook entry.
- ---
- ## 🖥️ Multi-Machine Setup
- The toolkit uses a two-layer architecture:
- 1. **This repo** (`~/.claude/`) — Shared configuration, cloned on every machine
- 2. **Machine-specific** (`.env.local`, `known_marketplaces.json`) — Gitignored, per-device
- ### New Device Setup
- ```bash
- git clone https://github.com/travisjneuman/.claude.git ~/.claude
- cp ~/.claude/.env.example ~/.claude/.env.local
- # Edit .env.local with machine-specific paths
- bash ~/.claude/scripts/fix-marketplace-paths.sh
- ```
- See **[docs/NEW-DEVICE-SETUP.md](./docs/NEW-DEVICE-SETUP.md)** for the full walkthrough.
- ---
- ## 💻 Platform Support
- | Platform | Status | Shell | Notes |
- |----------|--------|-------|-------|
- | **macOS** | Full support | bash/zsh | Notifications via osascript |
- | **Linux** | Full support | bash | Notifications via notify-send |
- | **Windows 11** | Full support | Git Bash | Hooks use Node.js runner to avoid WSL issues |
- | **WSL** | Works | bash | Native Linux behavior inside WSL |
- **Requirements:** Claude Code 2.1.139 or later (the hooks use exec form), Node.js (comes with Claude Code), Git, bash (Git Bash on Windows).
- ---
- ## 🆕 What's New
- **November 2026 — Audit, efficiency pass, and a plugin install**
- - **Fixes for people who are not the maintainer:** setup scripts no longer rewrite your `origin` or disable pushing on your own repos; the installer no longer writes a broken `.mcp.json`. If you installed earlier, see the CHANGELOG's "If you installed before November 2026".
- - **Skills-only plugin:** `/plugin marketplace add travisjneuman/.claude`, then `tjn-skills` or one of ten domain bundles. No hooks, settings or background jobs.
- - **Guard covers PowerShell**, and hooks start without a shell (exec form), which matters most on Windows.
- - **Skills follow the 500-line guidance:** 37 long skills are now an overview plus `references/` files, with every line kept.
- - **Security policy and trust model:** [`SECURITY.md`](./SECURITY.md) says what a full-access setup trusts and how to narrow it.
- - **Sessions are kept**, not deleted after 30 days; the website builds again; counts refreshed on 2026-11-10.
- **September 2026 — Modernization for current Claude Code**
- - **Lean always-on context:** 23 core skills keep full descriptions; every other skill and command is `name-only` (still installed and invocable) and discoverable through the generated `INDEX.md` / `index/graph.json` and the new `toolkit-router` skill. Language rules are path-scoped.
- - **Full Access+++ in `CLAUDE.md`:** rewritten, shorter constitution (autonomous execution, explicit prohibitions, zero testing (validate by review), pull-first git, no AI attribution). `attribution` settings disable commit/PR trailers at the source.
- - **Hooks fixed and trimmed:** the Bash and write guards now actually work (they read an env var Claude Code never set); per-prompt git injection, per-turn session summaries, and GSD update checks are gone; the pull runs at most daily and never auto-commits or pushes; new status line.
- - **AGENTS.md support:** `claude-md-and-agents-md` so projects shared with Codex and other agents load their `AGENTS.md`.
- - **Private `local/` layer:** gitignored rules, hooks, and host settings, plus a pre-commit public-safety gate. Template in `local.example/`.
- - **Marketplaces:** manifest-only in `.gitmodules`; clones are local, `no_push`, blocked from commits by pre-commit and pre-push checks. `scripts/add-marketplace.sh <url>` adds one.
- - **GSD removed:** the `gsd-core` marketplace is no longer registered, routed to, or counted; the old GSD tutorial is in `archive/`.
- **March 2026 — Comprehensive audit, new repos, full domain coverage**
- - **6 new marketplace repos:** `blader/humanizer` (11.4K stars), `phuryn/pm-skills` (8.3K stars, 100+ PM skills), `Lum1104/Understand-Anything` (6.6K stars), `SawyerHood/dev-browser` (4.9K stars), `slavingia/skills` (4.5K stars), `millionco/expect` (2.3K stars). Current manifest: 109 repos total.
- - **Marketplace clone cleanup:** Fixed orphaned directories, standardized the `.gitmodules` manifest, verified `no_push` protection on marketplace clones
- - **Full domain coverage:** New skills and agents for blockchain/Web3, data engineering, embedded/IoT, edge computing, compliance, and more
- - **New stack rules:** Added Go, Rust, Java/Kotlin, C/C++, Swift/iOS, Flutter/Dart rules — path-scoped for zero token cost when not relevant
- - **Count synchronization:** All counts now accurate across README, plugin.json, counts.json (127 skills, 86 agents, 94 commands, 109 repos)
- **Earlier in March 2026:**
- - **Marketplace routing:** All repos now surface naturally by domain — routing coverage went from 23% to 100%
- - **CLAUDE.md condensed:** Auto-routing table reduced from 72 to 29 rows, saving ~600 tokens per conversation
- - **start-task trimmed:** 156 → 82 lines, removed duplication with CLAUDE.md
- See **[CHANGELOG.md](./CHANGELOG.md)** for the full history.
- ---
- ## 📚 Documentation
- | Document | Description |
- |----------|-------------|
- | [CLAUDE.md](./CLAUDE.md) | Core rules (the always-loaded constitution) |
- | [INDEX.md](./INDEX.md) | Generated toolkit index: grep by domain or keyword |
- | [Docs front door](./docs/README.md) | Every guide and reference doc, routed by need |
- | [CHANGELOG.md](./CHANGELOG.md) | Version history |
- | [Architecture](./docs/ARCHITECTURE.md) | System design and component interactions |
- | [Setup Guide](./docs/SETUP-GUIDE.md) | First-time installation walkthrough |
- | [New Device Setup](./docs/NEW-DEVICE-SETUP.md) | Multi-machine configuration |
- | [Workflow Guide](./docs/WORKFLOW-GUIDE.md) | Development workflow patterns |
- | [Marketplace Guide](./docs/MARKETPLACE-GUIDE.md) | Community skill catalog |
- | [Count Pipeline](./docs/COUNT-PIPELINE.md) | Public populations, snapshot evidence and explicit publication |
- | [Agent Teams](./docs/AGENT-TEAMS.md) | Multi-agent coordination |
- | [MCP Servers](./docs/MCP-SERVERS.md) | MCP server reference |
- | [Configuration](./docs/CONFIGURATION.md) | Full settings.json reference |
- | [Folder Structure](./docs/FOLDER-STRUCTURE.md) | Directory layout and purpose |
- | [Skills Index](./skills/MASTER_INDEX.md) | All skills with descriptions |
- | [Agents Index](./agents/README.md) | All agents with descriptions |
- ---
- ## 💡 Philosophy
- This toolkit follows three core principles:
- 1. **Everything activates dynamically.** Describe what you want — the system loads what's needed. No memorizing commands.
- 2. **Token efficiency over completeness.** Domain content loads on-demand, not upfront. Unused skills cost zero tokens.
- 3. **Safety by default.** Dangerous commands are blocked, secrets are scanned, protected files are guarded — all before you make a mistake.
- ---
- <div align="center">
- **Maintained by [Travis Neuman](https://travisjneuman.com)** · **[claude.travisjneuman.com](https://claude.travisjneuman.com)** · **MIT License**
- <picture>
- <source media="(prefers-color-scheme: dark)" srcset="https://capsule-render.vercel.app/api?type=waving&color=0:1a1a2e,50:6366f1,100:d946ef&height=120§ion=footer" />
- <source media="(prefers-color-scheme: light)" srcset="https://capsule-render.vercel.app/api?type=waving&color=0:e0e7ff,50:6366f1,100:9333ea&height=120§ion=footer" />
- <img alt="" src="https://capsule-render.vercel.app/api?type=waving&color=0:1a1a2e,50:6366f1,100:d946ef&height=120§ion=footer" width="100%" />
- </picture>
- </div>
Version history
v3.5.010/18/2026
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.