New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Better Fullstack

by Marve10s in Marve10s/Better-Fullstack

Scaffold, plan, or extend Better Fullstack projects with the generator, CLI, or MCP server.

MITAuto-check passedDevelopment

Install Better Fullstack

skills CLI
$ npx skills add Marve10s/Better-Fullstack --skill better-fullstack -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Marve10s/Better-Fullstack better-fullstack --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Marve10s/Better-Fullstack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/better-fullstack .claude/skills/better-fullstack && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
better-fullstack
GitHub stars
752
Token cost
~1.5k tokens
SKILL.md length
582 words
Files
2
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Scaffold, plan, or extend Better Fullstack projects with the generator, CLI, or MCP server.

  • Works in 4 steps: A local CLI path provided by the prompt… → A preinstalled Better Fullstack command… → An attached Better Fullstack MCP server… → …
  • A user asks to create
  • SKILL.md covers Choose The Path, Default CLI Workflow, CLI Rules and Mapping Hints, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Better Fullstack is an agent skill from Marve10s/Better-Fullstack. Scaffold, plan, or extend Better Fullstack projects with the generator, CLI, or MCP server. Use when a user asks to create, generate, or scaffold a fullstack starter; choose a Better Fullstack stack; add Better Fullstack capabilities; compare agent scaffolding paths; or avoid hand-authoring boilerplate project files.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Development, covering Project scaffolding. It works with Model Context Protocol, React and TypeScript. The repository describes itself as: Scaffold production-ready full-stack apps in TypeScript, Rust, Python, Go, and Java with a visual builder and CLI. Choose your frontend, backend, database, auth, AI, payments… The licence is MIT.

When your agent uses it

  • A user asks to create
  • Scaffold a fullstack starter
  • Choose a Better Fullstack stack
  • Add Better Fullstack capabilities

Example prompts

  • “/better-fullstack”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. A local CLI path provided by the prompt or current repository.
  2. A preinstalled Better Fullstack command available on PATH.
  3. An attached Better Fullstack MCP server or tool.
  4. A command explicitly provided or approved by the user.

What it can do on your machine

Read from SKILL.md and the folder at commit b03f092. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Better Fullstack loads about 1.5k tokens when it runs. Until then it costs about 84 tokens; SKILL.md has 582 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~84
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Marve10s/Better-Fullstack at commit b03f092, republished under its MIT licence (© Marve10s). 582 words, ~1,452 tokens.

Download SKILL.mdSave it as .claude/skills/better-fullstack/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
better-fullstack
description
Scaffold, plan, or extend Better Fullstack projects with the generator, CLI, or MCP server. Use when a user asks to create, generate, or scaffold a fullstack starter; choose a Better Fullstack stack; add Better Fullstack capabilities; compare agent scaffolding paths; or avoid hand-authoring boilerplate project files.

Better Fullstack

Use the Better Fullstack generator as the source of truth for starter generation. Do not hand-write a full starter when a trusted Better Fullstack interface can produce it.

Choose The Path

Use an already-available CLI by default. The benchmarked best framing is: map the stack, dry-run the CLI, then run the same non-interactive command for real.

Use MCP only when the user explicitly asks for MCP, when CLI access is unavailable, or when the request needs structured schema lookup beyond what a concise CLI command can safely express. If using MCP, start with bfs_get_guidance, then use schema, compatibility, plan, and create/add tools in that order.

Use a trusted Better Fullstack interface in this order:

  1. A local CLI path provided by the prompt or current repository.
  2. A preinstalled Better Fullstack command available on PATH.
  3. An attached Better Fullstack MCP server or tool.
  4. A command explicitly provided or approved by the user.

If none is available, ask the user for the command, service, tool, or docs source they want used. Do not invent a bootstrap command.

Default CLI Workflow

  1. Map the user's stack into Better Fullstack graph parts and flat flags.
  2. Build one non-interactive command.
  3. Run it with --dry-run.
  4. If the dry run succeeds, run the same command without --dry-run.
  5. If the CLI rejects a combination, adjust to the closest valid Better Fullstack stack and report the adjustment.

CLI Rules

  • Create exactly the requested project directory, using a relative project name.
  • Prefer create <project-name> --part ... for explicit or multi-ecosystem stacks.
  • Pass --no-install --no-git for agent-driven scaffolding unless the user explicitly asks for side effects.
  • Pass --package-manager bun when the user or project expects Bun.
  • Pass --ai-docs agents-md for reusable projects, or --ai-docs none for benchmarks and throwaway scaffolds.
  • Use none explicitly for categories the user wants disabled.
  • Do not start a dev server.

Mapping Hints

  • React + Vite: frontend:typescript:react-vite
  • Hono: backend:typescript:hono
  • Bun runtime: backend.runtime:typescript:bun
  • SQLite: database:universal:sqlite
  • Drizzle: backend.orm:typescript:drizzle
  • tRPC: backend.api:typescript:trpc
  • Tailwind: frontend.css:typescript:tailwind
  • DaisyUI: frontend.ui:typescript:daisyui
  • Pino: backend.logging:typescript:pino
  • Biome: codeQuality:universal:biome

Graph Part Examples

Use graph parts as category:ecosystem:option.

bash
<better-fullstack-cli> create my-app \
  --part frontend:typescript:react-vite \
  --part backend:typescript:hono \
  --part database:universal:sqlite \
  --part backend.runtime:typescript:bun \
  --part backend.api:typescript:trpc \
  --part backend.orm:typescript:drizzle \
  --part frontend.css:typescript:tailwind \
  --part frontend.ui:typescript:daisyui \
  --part backend.logging:typescript:pino \
  --part codeQuality:universal:biome \
  --forms none \
  --validation none \
  --ai-docs none \
  --package-manager bun \
  --no-install \
  --no-git
bash
<better-fullstack-cli> create api-app \
  --part backend:python:fastapi \
  --part database:universal:postgres \
  --part backend.orm:python:sqlmodel \
  --part backend.validation:python:pydantic \
  --part backend.auth:python:jwt \
  --part codeQuality:python:ruff \
  --ai-docs agents-md \
  --no-install \
  --no-git
Show full SKILL.md (238 more words)Show less

Existing Projects

For a generated project with bts.jsonc, use the Better Fullstack add command or MCP add tools. Use canonical Stack Part specs so each capability keeps its category and owner, for example:

bash
<better-fullstack-cli> add --project-dir ./my-app --part staticAnalysis:typescript:knip --part workspaceRunner:universal:turborepo --no-install

For MCP lifecycle work, use this sequence:

  1. bfs_get_project_status reads configuration and manifest prerequisites without running toolchains or writing files.
  2. bfs_check_project runs every generated target check. It requires installed dependencies and required toolchains; missing prerequisites are failures. It does not rewrite Better Fullstack source/configuration directly, though build tools may fetch dependencies and write locks, caches, compiler output, or build artifacts.
  3. bfs_plan_project_update reads current-template drift. It returns a reviewToken only when a supported manifest-v1 baseline exists and all exact structured-merge content fits the 32 KiB per-file MCP review bound. Oversized content is withheld with size/SHA metadata and no token.
  4. After explicit approval, pass the same absolute project path and exact unchanged token to bfs_apply_project_update with acknowledgeUnprovenManifestV1: true. Missing, stale, cross-project, or bounded-review-ineligible tokens fail closed. Apply destructively overwrites currently actionable template files and advances the v1 manifest without installing dependencies.

Manifest v1 does not prove generator release/SHA provenance or cross-version eligibility, and the current apply path has no transactional backup or automated recovery. Do not promise those Wave 1 guarantees.

Final Response

Report the command or tool path used, any compatibility adjustments, the project directory, and the next install/test/run commands. Do not claim dependencies are installed when --no-install or MCP creation skipped them.

© Marve10s, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/better-fullstack of Marve10s/Better-Fullstack.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit b03f092

Compare with similar skills

Better Fullstack next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Better Fullstack compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Better Fullstack this skillMarve10s/Better-Fullstack752—~1.5kAutomated safety check: PassMIT
Deepseek Automationzhu1090093659/deepseek-pp1.9k—~2.1kAutomated safety check: NotesApache-2.0
Code Reviewnteract/semiotic2.7k—~1.5kAutomated safety check: PassApache-2.0
Agentbro PR Mergeshirenchuang/agentbro203—~648Automated safety check: PassApache-2.0
Pixijs Createpixijs/pixijs-skills346—~3.1kAutomated safety check: PassMIT
Dynamo Webview Component ScaffoldDynamoDS/Dynamo2k—~991Automated safety check: PassApache-2.0

Similar skills

  • Deepseek Automation

    zhu1090093659/deepseek-pp

    A skill your agent uses when implementing, resuming, reviewing, or verifying the DeepSeek++ Codex-style automation feature in this repository.

    1.9k GitHub stars~2.1k tokensUpdated 1 mo ago
    DevelopmentAuto-check: notes

  • Code Review

    nteract/semiotic

    Review Semiotic pull requests for behavioral bugs, regressions, contract drift, and missing evidence.

    2.7k GitHub stars~1.5k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Agentbro PR Merge

    shirenchuang/agentbro

    A skill your agent uses when reviewing, fixing CI for, approving workflows for, or merging AgentBro pull requests into dev/main, especially external contributor PRs where contributor attribution…

    203 GitHub stars~648 tokensUpdated 7 days ago
    DevelopmentAuto-check passed

  • Pixijs Create

    pixijs/pixijs-skills

    A skill your agent uses when scaffolding a new PixiJS v8 project with the create-pixi CLI or adding PixiJS to an existing project.

    346 GitHub stars~3.1k tokensUpdated 6 days ago
    DevelopmentAuto-check passed

  • Dynamo Webview Component Scaffold

    DynamoDS/Dynamo

    Scaffolds a new Dynamo package repo that hosts a view extension with a WebView2-embedded React frontend.

    2k GitHub stars~991 tokensUpdated today
    DevelopmentAuto-check passed

  • holaOS App Builder SDK

    holaboss-ai/holaOS

    Builds new holaOS apps with @holaboss/app-builder-sdk, either as integration-only MCP modules or as dashboard apps with a shadcn UI under src/client/.

    11k GitHub stars~11k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

More from Marve10s/Better-Fullstack

All 8 skills in this repo

  • Remotion Bits

    Marve10s/Better-Fullstack

    Animation components and utilities for Remotion video projects.

    752 GitHub starsUsed in 1 repo~8.2k tokens
    Auto-check passed

  • Create Remotion Geist

    Marve10s/Better-Fullstack

    Create Remotion videos using the Geist design system aesthetic.

    752 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Modern Short Video

    Marve10s/Better-Fullstack

    Create modern product launch/pitch videos using Remotion. An agent skill from Marve10s/Better-Fullstack.

    752 GitHub stars~1.8k tokensUpdated today
    Auto-check: notes

  • Remotion Animation

    Marve10s/Better-Fullstack

    Generates animation configurations for Remotion including spring configs, interpolations, easing functions, and timing logic.

    752 GitHub stars~3.2k tokensUpdated today
    Auto-check passed

  • Add To Project

    Marve10s/Better-Fullstack

    Add capabilities, addons, deployment targets, generated CI, services, or stack updates to an existing Better Fullstack project.

    752 GitHub stars~507 tokensUpdated today
    Auto-check passed

  • Scaffold Project

    Marve10s/Better-Fullstack

    Scaffold a new app, API, backend, fullstack project, mobile app, polyglot service, monorepo, or starter with Better Fullstack.

    752 GitHub stars~716 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Better Fullstack

What does Better Fullstack do?

Scaffold, plan, or extend Better Fullstack projects with the generator, CLI, or MCP server. Better Fullstack is an agent skill from Marve10s/Better-Fullstack. Scaffold, plan, or extend Better Fullstack projects with the generator, CLI, or MCP server.

When should I use Better Fullstack?

Better Fullstack fits situations like: A user asks to create; scaffold a fullstack starter; choose a Better Fullstack stack; add Better Fullstack capabilities.

How do I install Better Fullstack in Claude Code?

Run `npx skills add Marve10s/Better-Fullstack --skill better-fullstack -a claude-code`. Or copy the skill folder (.agents/skills/better-fullstack in Marve10s/Better-Fullstack) into .claude/skills/better-fullstack in your project. Claude Code loads it when a task matches its description.

How do I install Better Fullstack in Codex?

Run `npx skills add Marve10s/Better-Fullstack --skill better-fullstack -a codex`. Or copy the skill folder (.agents/skills/better-fullstack in Marve10s/Better-Fullstack) into .agents/skills/better-fullstack in your project. Codex loads it when a task matches its description.

Can I use Better Fullstack in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Marve10s/Better-Fullstack --skill better-fullstack -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/better-fullstack, .gemini/skills/better-fullstack, .github/skills/better-fullstack and .opencode/skills/better-fullstack in your project.

What does Better Fullstack need to run?

SKILL.md names no scripts, command-line tools or credentials: Better Fullstack is instructions for the agent only.

Does Better Fullstack access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Better Fullstack safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Better Fullstack use?

Better Fullstack is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Better Fullstack use?

About 1.5k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Better Fullstack?

Skills that share tags, products or a category with Better Fullstack: Deepseek Automation (zhu1090093659/deepseek-pp, 1.9k stars), Code Review (nteract/semiotic, 2.7k stars), Agentbro PR Merge (shirenchuang/agentbro, 203 stars) and Pixijs Create (pixijs/pixijs-skills, 346 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Better Fullstack?

Marve10s (a GitHub user) maintains it in Marve10s/Better-Fullstack, which has 752 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 7, 2026.

Source: Marve10s/Better-Fullstack on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.