New Project logo

New Project

Community
peterbamuhigire
new-project

Use when the task matches skill: new project scaffold and this skill's local workflow.

Overview

Publisherpeterbamuhigire
Repositorychwezi-dev-engine
Skill namenew-project
Stars
29
Forks
6
Bundled files
155
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 155 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by peterbamuhigire on GitHub. Read the source before you install it.

Installation

Install the New Project AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/peterbamuhigire/chwezi-dev-engine/tree/main/00-meta-initialization/new-project
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/peterbamuhigire/chwezi-dev-engine.git /tmp/chwezi-dev-engine
mkdir -p .claude/skills
cp -r /tmp/chwezi-dev-engine/00-meta-initialization/new-project .claude/skills/new-project
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable New Project in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads New Project on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so New Project is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Skill: New Project Scaffold

Evidence Produced

CategoryArtifactFormatExample
Release evidenceProject initialisation evidence packMarkdown plus filesystem validationselected methodology, created paths, preserved files, validation result, rollback, and handoff

Inputs

ArtefactRequired?Purpose
Approved project profile and roadmapyesDrive scaffold scope
Repository conventions and existing filesyesPreserve local structure

Outputs

ArtefactConsumerAcceptance condition
Project documentation scaffoldProject teamNo destructive overwrite, links resolve, roadmap represented

Capability contract

Read/search are required. File creation requires explicit scaffold authority. Do not install tools, initialise remote services, or publish artefacts implicitly.

Degraded mode

Fallback without write access: return the directory tree and file templates as a proposed patch.

Decision rules

StateActionFailure avoided
Empty projectCreate approved minimal scaffoldContext overload
Existing partial documentationFill gaps and preserve contentDestructive replacement
Conflicting methodology filesStop and reconcile with roadmapContradictory process

Domain anti-patterns

  • Creating empty placeholder documents. Fix: include purpose, owner, and next action.
  • Copying a universal scaffold. Fix: derive files from the approved roadmap.
  • Replacing existing project rules. Fix: preserve and reconcile them.
  • Adding tool-specific adapters as canonical truth. Fix: keep sources model-neutral.
  • Claiming setup is complete without link checks. Fix: validate the scaffold and references.

Trigger

User says any of: "start a new project", "create a new project", "scaffold a project", "new client project", "initialize project"

First Step: Shared Understanding

Start with the engine's own design gate: skills/sdlc-meta/world-class-engineering §2 "Create Shared Understanding". Record user journeys, non-goals, scale and trust boundaries, ranked quality attributes and hard constraints, and state the ceremony class (spike, bounded or architectural) before scaffolding anything. If the Superpowers plugin is present, its process skills (for example superpowers:brainstorming) may be used; this engine's gates remain authoritative.


How to Use the Chwezi SDLC Documentation engine (PRIME Workflow)

Every skill in this engine follows the PRIME methodology (Kodukula & Vinueza, 2024):

StepWhat the Consultant DoesChwezi SDLC Documentation Equivalent
P — PrepareGather all project data before promptingPopulate _context/ files with real stakeholder data, not placeholders
R — RelaySubmit the prompt with precise instructionsInvoke the SKILL.md (tell Claude: "Run the [skill name] skill")
I — InspectCritically evaluate AI output against objectivesRead the generated document; check it against _context/ source files
M — ModifyRefine if output diverges from expectationsEdit the output or update _context/ and re-invoke the skill
E — ExecuteApprove and build the final artifactRun build-doc.sh to produce the .docx

Quality rule: Never execute (build the .docx) without completing Inspect and Modify. The first AI output is a draft, not a deliverable.

The _context/ directory is the Project Input Folder (PIF) for this project — a living repository of project-specific context that feeds every skill. The richer the PIF, the higher the quality of every generated document (Kodukula & Vinueza, 2024).


Interview Protocol

After brainstorming, ask these questions ONE AT A TIME. Do not ask the next until the previous is answered.

Q1: What is the project name? (This becomes the directory name — use hyphens, e.g., Livecare-Hospital-ERP)

Q2: In 2–3 sentences, what does this software do and what problem does it solve? (This pre-populates _context/vision.md and is used to deduce the domain)

Q3: Which methodology best fits this project?

  • A) Waterfall — regulated industry, fixed scope, formal IEEE 830 SRS required
  • B) Agile — iterative delivery, user stories, Scrum/Kanban
  • C) Hybrid — formal SRS for backend/core + agile user stories for frontend/features

Q4: Who is the project owner / primary client contact name?


Domain Deduction (NO USER INPUT REQUIRED)

After Q2, Claude analyses the project description and deduces the domain automatically using these signals:

If description mentions...Deduce domain
patients, hospitals, clinics, EMR, EHR, PHI, medical, healthcare, pharmacy, nursinghealthcare
banking, payments, ledger, transactions, trading, insurance, loans, fintech, accountingfinance
students, courses, LMS, grades, enrollment, university, school, e-learningeducation
inventory, POS, e-commerce, retail, products, orders, cart, warehouse (retail context)retail
fleet, shipments, tracking, logistics, freight, warehouse (supply chain), delivery, routinglogistics
government, citizens, public services, procurement, permits, case management, municipalgovernment
farm, crops, livestock, agriculture, harvest, planting, irrigation, cattle, poultry, FMISagriculture

If ambiguous (two domains equally match): Ask the user during the brainstorming session — e.g., "This sounds like it could be healthcare OR government — which primary domain applies?"

If no domain matches: Use other — no domain defaults are injected; scaffold only the directory structure and empty context files.


Additional Guidance

Extended project-scaffold guidance was moved to references/new-project-deep-dive.md to keep this entrypoint compact and fast to load.

Use that deep dive for:

  • Scaffold Actions
  • Quick Links
  • What We Are Building
  • Document Inventory by Phase
  • Context Files (_context/)
  • Progress Summary
  • Immediate Next Steps
  • Problem Statement
  • Goals
  • Stakeholders
  • Success Criteria
  • Feature Name
  • Additional deep-dive sections continue in the reference file.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

and 95 more files.

Frequently asked questions

What does the New Project AI skill do?

Use when the task matches skill: new project scaffold and this skill's local workflow.

Why use New Project on TypingMind?

Because you install it once and use it with any model. New Project is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install New Project in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/peterbamuhigire/chwezi-dev-engine/tree/main/00-meta-initialization/new-project. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use New Project?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with New Project?

As many as you like. As long as a model supports skills, you can use New Project with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the New Project AI skill free?

Yes. It is published on GitHub by peterbamuhigire under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇