turbo-mono-platform
Full-stack TypeScript monorepo specialist: Turborepo, Next.js, Hono, tRPC, Drizzle, Postgres.
Skill by therealtinhtute
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/therealtinhtute-turbo-mono-platform
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, frontend, backend, security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 5
biomejs.dev· found in codecodeload.github.com· found in install commandjson.schemastore.org· found in codeturbo.build· found in codeui.shadcn.com· found in code
Files it touches
~/.claude/skills/turbo-mono-platform
Tools it pre-approves 2
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
BashEdit
What's inside
- Skill name
turbo-mono-platform- Description
- Full-stack TypeScript monorepo specialist: Turborepo, Next.js, Hono, tRPC, Drizzle, Postgres. Use when working on this stack or any layer (auth, db, trpc, ui, kv, api). Invoke only from a mono-mode playbook step or when the user asks for it by name.
- License
- MIT
- Compatibility
- Designed for Claude Code
- Allowed tools
- Bash, Edit
- Metadata
- version: 1.0.0 · package-scope: @rp/ · shadcn-preset: b1tMcUv91 · stack-version: 2026-q2
- Instructions
- 111 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
- Pre-approves any shell command
Files (37)
- SKILL.md
- .env.local.example · assets/
- biome.json · assets/
- components.json · assets/
- tsconfig.base.json · assets/
- turbo.json · assets/
- evals.json · evals/
- bad-cache.ts · evals/files/
- bad-imports.ts · evals/files/
- bad-middleware.ts · evals/files/
- architecture.md · references/
- base-scaffold.md · references/
- ci.md · references/
- companion-skills.md · references/
- design-systems.md · references/
- dev-commands.md · references/
- layer-api.md · references/
- never-rules.md · references/
- next16-breaking.md · references/
- output-format.md · references/
- package-analyzer.md · references/
- package-ownership.md · references/
- shadcn-rules.md · references/
- shadcn.md · references/
- stack-versions.md · references/
- supabase-drizzle.md · references/
- turbo-cli.md · references/
- turbo-tasks.md · references/
- analyze-project.sh · scripts/
- check-imports.sh · scripts/
- gen-auth.sh · scripts/
- gen-package.sh · scripts/
- gen-schema.sh · scripts/
- gen-trpc-router.sh · scripts/
- migrate.sh · scripts/
- scaffold-base.sh · scripts/
- scaffold-packages.sh · scripts/
SKILL.md (first lines)
<role>
Act as a full-stack TypeScript monorepo specialist. Handle Turborepo 2.9, Next.js 16, Hono 4,
tRPC v11, Drizzle ORM + Supabase, Better Auth, Upstash Redis, TanStack Query, shadcn/ui,
TailwindCSS v4, Bun, and Biome. Scaffold projects, add packages, write code for any layer
(auth, db, trpc, ui, kv, api). Run runtime context on existing
projects, check companion skills at load, never generate layer code without loading reference
files, run Package Analyzer before scaffolding.
</role>
<security>
- Block destructive operations without confirmation
- Scan for secrets before commits; never commit credentials or API keys
</security>
<context>
## When to Use
- Working on Turborepo + Next.js 16 + tRPC + Drizzle stack
- Scaffolding new monorepo projects
- Adding packages to existing monorepos
- Writing code for auth, db, trpc, ui, kv, or api layers
- Any question about this specific stack
## Defer To Instead
- `check` — auditing TypeScript code quality and running tests and type checks
- `brainstorm` — comparing monorepo vs polyrepo architecture
## Companion Skills
Check at load — see `references/companion-skills.md` for detection logic and responsibility table.
```
!`ls ~/.claude/skills/ .claude/skills/ 2>/dev/null | grep -E "shadcn|turborepo" | sort || echo "none"`
```
</context>
<instructions>
## Behavior Instructions
- **Check the stack conventions first** before writing any code, config, or command
- **Run runtime context** (`!cat package.json`, `!ls apps/ packages/`) on existing projects
- **Check companion skills** at skill load — see Companion Skills section
- **Never generate layer code without loading its reference file** — check routing table
- **New project → always run Package Analyzer first**, never scaffold without defining tiers
- **Base tier scaffolds first** — then optional packages per project needs
- **One clarifying question max** on ambiguous requests, then proceed
- **All code runnable** — no pseudocode, no stubs, no placeholder values
- **Bun only** for any install/run/exec
- **Fix cross-package errors** → run `bash scripts/check-imports.sh` first
- **Adding UI components** → `bunx shadcn@latest add <n> -c apps/web`
## Package Analyzer — Run Before Scaffold
Load `references/package-analyzer.md`. Run `bash scripts/analyze-project.sh`. Ask 5 questions (type, features, entities, API surface, deployment) one at a time — confirm package list before scaffolding.
## Dev Commands
See `references/dev-commands.md` for full command reference.
## Output Format
See `references/output-format.md` for full spec.
- Scaffolding: console output with created files and next steps.
- Analysis: Save to: `docs/audit/{YYYY-MM-DD}-turbo-analysis.md` — Frontmatter: title, description, status, created, tags.
</instructions>
<references>
Load as needed from `{baseDir}/references/`:
- `never-rules.md` — stack conventions, what each replaces, and why
- `stack-versions.md` — Version matrix
- `package-ownership.md` — Package responsibilities
- `architecture.md` — Two-tier structure
- `dev-commands.md` — Daily bun commands + script helpers
- `companion-skills.md` — Companion skill detection and responsibility table
- `package-analyzer.md` — Package analyzer interview workflow
- `output-format.md` — Scaffolding and analysis report formats
- `design-systems.md` — Design system choice
- `base-scaffold.md` — Base scaffold
- `supabase-drizzle.md` — Supabase + Drizzle
- `layer-api.md` — Auth / tRPC / Redis
- `next16-breaking.md` — Next.js 16 breaking changes
- `shadcn.md` — shadcn CLI usage
- `shadcn-rules.md` — shadcn component rules
- `turbo-tasks.md` — Turbo tasks
- `ci.md` — CI/CD
</references>From therealtinhtute/mono-harness, MIT.
More from therealtinhtute/mono-harness
- 0.624score
create-cli
therealtinhtute
Design CLI interfaces (commands, flags, I/O, errors, config) and produce implementation roadmaps with framework choice and shipping strategy.
SkillAFreshness: A★ 5Claude Code +9 - 0.621score
librarian
therealtinhtute
GitHub code research via gh CLI, no cloning.
SkillAFreshness: A★ 5Claude Code +9 - 0.621score
read
therealtinhtute
Search the web and fetch URLs or PDFs as clean Markdown via a privacy-first cascade (local, gh, TinyFish/Firecrawl/Exa, opt-in proxy).
SkillAFreshness: A★ 5Claude Code +9 - 0.621score
git
therealtinhtute
Git operations with conventional commits.
SkillAFreshness: A★ 5Claude Code +9 - 0.621score
hunt
therealtinhtute
Find the root cause before any fix: build a red-capable repro loop, rank falsifiable hypotheses, prove, fix, sweep siblings.
SkillAFreshness: A★ 5Claude Code +9 - 0.621score
think
therealtinhtute
Reason hard before building: attack premises, run named thinking lenses, compare real alternatives, give one verdict.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
retro
therealtinhtute
Session retrospective: evidence-cited, severity-ranked findings about the agent's environment, then one user-approved fix — a guard or a rerun-gated experiment.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
arena
therealtinhtute
Design bakeoff: sub-agents build one artifact several ways, a rubric picks the base, the best parts of the rest are grafted on.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
mono-mode
therealtinhtute
Entry router: match a task to one of twelve playbooks (feature, bug-fix, refactoring, perf, research, ship, ...) and run its skill steps as a todo list.
SkillAFreshness: A★ 5Claude Code +9 - 0.618score
prompt-leverage
therealtinhtute
Strengthen a raw prompt into an execution-ready instruction set for Claude Code or another AI agent.
SkillAFreshness: A★ 5Claude Code +9 - 0.616score
work
therealtinhtute
Execution orchestrator after `brainstorm` (and `to-plan` for high-risk).
SkillAFreshness: A★ 5Claude Code +9 - 0.616score
check
therealtinhtute
Pre-commit and pre-merge gate.
SkillAFreshness: A★ 5Claude Code +9
Compare and alternatives
Featured in
Signals
- Stars
- 5
- Forks
- 1
- Open issues
- 1
- Last commit (this folder)
- Oct 22, 2026 (5 days ago)
- Last release
- Oct 23, 2026 (4 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.0.0
- License
- MIT
- Repository
- github.com/therealtinhtute/mono-harness
- Website
- harness.tinhtute.me
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from therealtinhtute
- 0.624score
create-cli
therealtinhtute
Design CLI interfaces (commands, flags, I/O, errors, config) and produce implementation roadmaps with framework choice and shipping strategy.
SkillAFreshness: A★ 5Claude Code +9 - 0.621score
git
therealtinhtute
Git operations with conventional commits.
SkillAFreshness: A★ 5Claude Code +9 - 0.621score
librarian
therealtinhtute
GitHub code research via gh CLI, no cloning.
SkillAFreshness: A★ 5Claude Code +9 - 0.621score
think
therealtinhtute
Reason hard before building: attack premises, run named thinking lenses, compare real alternatives, give one verdict.
SkillAFreshness: A★ 5Claude Code +9 - 0.621score
hunt
therealtinhtute
Find the root cause before any fix: build a red-capable repro loop, rank falsifiable hypotheses, prove, fix, sweep siblings.
SkillAFreshness: A★ 5Claude Code +9 - 0.621score
read
therealtinhtute
Search the web and fetch URLs or PDFs as clean Markdown via a privacy-first cascade (local, gh, TinyFish/Firecrawl/Exa, opt-in proxy).
SkillAFreshness: A★ 5Claude Code +9
Cite this page
turbo-mono-platform skill. Agent Mart. https://agentmart.dev/skills/therealtinhtute-turbo-mono-platform (last updated 2026-10-24)