scaffold-project
Skill73 starsChanged 4 months agoMITView on GitHub
Scaffold a new project with standard structure, configs, and CLAUDE.md
- Reads credentials
11 other projects use a version of this.
Adopted by
Most recently taken up by
- mxrsv/agents-skillstheir own version, first seen Nov 1, 2026
- ankit4479/outbound-builder-plugintheir own version, first seen Oct 20, 2026
- MartinKChen/harness-claude-codetheir own version, first seen Oct 20, 2026
- navjyotnishant/nj-agentstheir own version, first seen Oct 15, 2026
- plugin87/ux-ui-agent-skillstheir own version, first seen Oct 13, 2026
- tejastn10/workbenchtheir own version, first seen Oct 13, 2026
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- plugin87/ux-ui-agent-skills★ 3.1ksame name
- sendaifun/solana-new★ 178same name
- cardano-foundation/cardano-dev-skills★ 38same name
- eldermoraes/quarkus-agentic-scaffolding★ 27same name
- 0gfoundation/0g-agent-skills★ 15same name
- mxrsv/agents-skills★ 11same name
- navjyotnishant/nj-agents★ 1same name
- tejastn10/workbench★ 1same name
- ankit4479/outbound-builder-plugin★ 0same name
- MartinKChen/harness-claude-code★ 0same name
1 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- memory/CLAUDE.mdCLAUDE.md
- changelogSkill
- db-checkSkill
- deploy-checkSkill
- e2e-checkSkill
- elicit-requirementsSkill
- load-sessionSkill
- pr-reviewSkill
- register-projectSkill
- review-diffSkill
- review-fullSkill
- save-diarySkill
- save-sessionSkill
- self-auditSkill
- session-endSkill
- sprint-planSkill
- statusSkill
- tech-radarSkill
- test-checkSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
next: Use {PROJECTS_ROOT}/{BOILERPLATE_NAME} as template, copy into new directory, update package name and README.
- Very specific: line 19
vue-springboot: Use {PROJECTS_ROOT}/{BOILERPLATE_NAME} as template, copy into new directory, update backend/frontend names and README.
- Very specific: line 20
expo: Use {PROJECTS_ROOT}/{BOILERPLATE_NAME} as template, copy into new directory, update app.json name and README.
- Distinctive: line 21
node: Create Express/Fastify project with TypeScript, Prisma, Vitest
- Distinctive: line 22
library: Create npm package with TypeScript, Vitest, tsup bundler
- Very specific: line 34
Register in memory: Create project entry in ./memory/projects/active/ using the coding template at ./memory/templates/coding-template.md
“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Before using: Replace
{PROJECTS_ROOT}and{BOILERPLATE_NAME}with your actual paths in your copy of this skill. (./memory/is the built-in memory folder, no replacement needed.)Example only, these scaffolds target JS/TS stacks (Nuxt, Next, Node, npm library). This is a project generator, so its type menu is intentionally stack-specific. Replace the
type:list and the per-type steps below with your own stack's scaffolds, such asrails new,django-admin startproject,cargo new,dotnet new,go mod init,mvn archetype:generate, etc.
Initialize a new project at {PROJECTS_ROOT}/$ARGUMENTS:
- Parse arguments: Extract project name and type (default: nuxt)
- Create project based on type (before copying any boilerplate: verify the template directory exists with
test -d. If missing, fall back to framework CLI scaffolding, such as npx nuxi, npx create-next-app, etc.):- nuxt (or from template): Use
{PROJECTS_ROOT}/{BOILERPLATE_NAME}as template, copy or clone into new directory, then replace app name in package.json/README. Alternatively:npx nuxi@latest init [name]then add Tailwind, Prisma, Vitest. - next: Use
{PROJECTS_ROOT}/{BOILERPLATE_NAME}as template, copy into new directory, update package name and README. - vue-springboot: Use
{PROJECTS_ROOT}/{BOILERPLATE_NAME}as template, copy into new directory, update backend/frontend names and README. - expo: Use
{PROJECTS_ROOT}/{BOILERPLATE_NAME}as template, copy into new directory, update app.json name and README. - node: Create Express/Fastify project with TypeScript, Prisma, Vitest
- library: Create npm package with TypeScript, Vitest, tsup bundler
- nuxt (or from template): Use
- When using a boilerplate template: Copy the template folder to {PROJECTS_ROOT}/[project-name], then update any project-specific names (package.json name, README title, app.json slug, etc.). Skip step 4 if template already has CLAUDE.md and .env.example.
- Generate standard files (if not from template or if template is minimal):
CLAUDE.mdwith project-specific instructions, commands, and stack description.env.examplewith required environment variables.gitignoretailored to the stackvitest.config.tswith sensible defaults (for JS/TS projects)
- Initialize git:
git initand create initial commit (if not already a git repo) - Register in memory: Create project entry in
./memory/projects/active/using the coding template at./memory/templates/coding-template.md - Report: Show project structure and next steps. For templates, remind user to set env vars (e.g. DATABASE_URL, NEXTAUTH_SECRET, JWT_SECRET) per template README.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

