AgentStack
SKILL verified MIT Self-run

New Project

skill-peterbamuhigire-skills-web-dev-new-project · by peterbamuhigire

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

No reviews yet
0 installs
11 views
0.0% view→install

Install

$ agentstack add skill-peterbamuhigire-skills-web-dev-new-project

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of New Project? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Skill: New Project Scaffold

Trigger

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

MANDATORY FIRST STEP

Before anything else, invoke superpowers:brainstorming to explore the project intent, requirements, and design. Do NOT skip this step. Do NOT ask clarifying questions before invoking brainstorming.


How to Use the SRS-Skills Engine (PRIME Workflow)

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

| Step | What the Consultant Does | SRS-Skills Equivalent | |------|--------------------------|----------------------| | P — Prepare | Gather all project data before prompting | Populate _context/ files with real stakeholder data, not placeholders | | R — Relay | Submit the prompt with precise instructions | Invoke the SKILL.md (tell Claude: "Run the [skill name] skill") | | I — Inspect | Critically evaluate AI output against objectives | Read the generated document; check it against _context/ source files | | M — Modify | Refine if output diverges from expectations | Edit the output or update _context/ and re-invoke the skill | | E — Execute | Approve and build the final artifact | Run 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, nursing | healthcare | | banking, payments, ledger, transactions, trading, insurance, loans, fintech, accounting | finance | | students, courses, LMS, grades, enrollment, university, school, e-learning | education | | inventory, POS, e-commerce, retail, products, orders, cart, warehouse (retail context) | retail | | fleet, shipments, tracking, logistics, freight, warehouse (supply chain), delivery, routing | logistics | | government, citizens, public services, procurement, permits, case management, municipal | government | | farm, crops, livestock, agriculture, harvest, planting, irrigation, cattle, poultry, FMIS | agriculture |

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](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.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.