원클릭으로 Manus에서 모든 스킬 실행

cursor-project-starter

Generates a complete Cursor AI IDE project starter kit — 7 documents — from a brainstorming conversation with the user. Use this skill whenever the user wants to start a new project, says "let's start a new project", "I have a project idea", "help me plan a new app/system/tool", "set up my Cursor project", or wants to brainstorm and immediately get working project files. Also trigger when the user says things like "I want to build X from scratch" or "help me plan out X before I start coding". Always use this skill proactively when a new project is being initiated — don't wait for the user to ask for documentation explicitly.

Manus에서 실행

개요

설치 명령

npx skills add https://github.com/Hemkumar247/Ai-Skills --skill cursor-project-starter

이 명령을 Claude Code에 복사하여 붙여넣어 스킬을 설치하세요

출처

Hemkumar247/Ai-Skills

스타0

포크0

업데이트2026년 4월 2일 09:17

파일 탐색기

8 개 파일

SKILL.md

readonly

이 저장소의 다른 Skills

같은 저장소

docx

Hemkumar247/Ai-Skills

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

2026-04-020

file-reading

Hemkumar247/Ai-Skills

Use this skill when a file has been uploaded but its content is NOT in your context — only its path at /mnt/user-data/uploads/ is listed in an uploaded_files block. This skill is a router: it tells you which tool to use for each file type (pdf, docx, xlsx, csv, json, images, archives, ebooks) so you read the right amount the right way instead of blindly running cat on a binary. Triggers: any mention of /mnt/user-data/uploads/, an uploaded_files section, a file_path tag, or a user asking about an uploaded file you have not yet read. Do NOT use this skill if the file content is already visible in your context inside a documents block — you already have it.

2026-04-020

pdf-reading

Hemkumar247/Ai-Skills

Use this skill when you need to read, inspect, or extract content from PDF files — especially when file content is NOT in your context and you need to read it from disk. Covers content inventory, text extraction, page rasterization for visual inspection, embedded image/attachment/table/form-field extraction, and choosing the right reading strategy for different document types (text-heavy, scanned, slide-decks, forms, data-heavy). Do NOT use this skill for PDF creation, form filling, merging, splitting, watermarking, or encryption — use the pdf skill instead.

2026-04-020

pptx

Hemkumar247/Ai-Skills

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.

2026-04-020

xlsx

Hemkumar247/Ai-Skills

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

2026-04-020

competitive-intelligence

Hemkumar247/Ai-Skills

Run this skill whenever the user wants to analyze competitors, understand the competitive landscape, find market gaps, or position their product against others. Trigger on phrases like "who are my competitors", "competitive analysis", "how do I differentiate", "what's the competition doing", "competitor mapping", "market positioning", "where's the gap in the market", or "how do I stand out". Produces a senior analyst-level competitive intelligence report with positioning maps, moat analysis, and strategic recommendations.

2026-04-020

출처

Hemkumar247

Hemkumar247/Ai-Skills

GitHub 저장소 열기 Creator 저장소 보기

설치 명령

다운로드

Manus에서 실행

유용한 대상SOC

소프트웨어 개발자컴퓨터 및 수학직15-1252L4

name

cursor-project-starter

description

Cursor Project Starter Kit

Generates 7 structured project documents through a brainstorming interview, ready to drop into Cursor (or any AI IDE) so the AI understands the full project from the start.

The 7 Documents This Skill Produces

File	Purpose
`PRD.md`	Product Requirements — features, goals, metrics, risks
`technical-spec.md`	Architecture, tech stack, functions, API details
`app-flow.md`	User journeys, system states, edge cases
`schema.md`	Database/data structure — all tables/collections + columns
`implementation-plan.md`	Phased build checklist with tasks and checkboxes
`README.md`	Project index — explains every file, how to use in Cursor
`.cursorrules`	Cursor AI rules — code style, naming, patterns, anti-patterns

Step 1 — Brainstorm Interview

Before writing any documents, conduct a structured interview. Ask ALL of these questions in a single conversational message (not one at a time). Group them naturally.

Core Questions

What is the project?

What does it do in one sentence?
Who are the users (primary + secondary)?
What problem does it solve?

Tech Stack:

What language/runtime? (e.g., Python, Node.js, Google Apps Script, React)
What database or storage? (e.g., PostgreSQL, Firestore, Google Sheets, MongoDB)
What external APIs or services? (e.g., OpenAI, Stripe, WhatsApp, Google Maps)
Any hosting/deployment target? (e.g., Vercel, GCP, AWS, serverless)

Features:

What are the 3–5 core features for MVP?
What is explicitly OUT OF SCOPE for now?
Any "nice to have" features?

Data:

What are the main data entities? (e.g., users, orders, products, sessions)
What fields does each entity need?

Flows:

Walk through the main user journey step by step
Are there admin/owner flows separate from customer flows?
What are 2–3 key edge cases or failure scenarios?

Constraints:

Timeline or deadline?
Cost constraints (free tier only? budget ok?)
Any security or compliance requirements?

Step 2 — Fill Gaps & Confirm

After the user answers:

Infer anything not explicitly stated (e.g., if they say "React app", infer Vite/Next.js as likely choice)
Ask for clarification ONLY on blockers (missing DB choice, unclear primary user)
Summarize your understanding in 3–5 bullet points
Ask: "Does this match your vision? Ready to generate the files?"

Step 3 — Generate All 7 Documents

Generate all files in sequence. Write each one completely before moving to the next. Use the templates in templates/ as structural guides — replace all placeholder content with the user's actual project details.

Generation order:

PRD.md — establish requirements first (everything else references this)
technical-spec.md — architecture derived from PRD
schema.md — data model derived from tech spec
app-flow.md — user journeys referencing the features in PRD
implementation-plan.md — phased tasks referencing all above
.cursorrules — rules derived from tech stack and patterns established above
README.md — index file written last (references all others)

Quality checks per document:

No placeholder text like [FILL IN] or YOUR_VALUE left in final output
Tech stack must be consistent across ALL documents
Function names in .cursorrules must match function names in technical-spec.md
Schema column names in schema.md must match references in technical-spec.md
All phase tasks in implementation-plan.md should reference the correct companion doc

Step 4 — Package & Deliver

Save all 7 files to /mnt/user-data/outputs/ in a flat structure (no subfolder needed). Present them to the user with present_files.

Tell the user:

"Drop all these files into your Cursor project root folder. Cursor will auto-detect .cursorrules. Then start prompting with references like: 'Read PRD.md and technical-spec.md, then write the [function name] function'"

Document Templates

See templates/ folder for the structural template of each document. Read the relevant template before generating that document.

templates/PRD-template.md
templates/technical-spec-template.md
templates/app-flow-template.md
templates/schema-template.md
templates/implementation-plan-template.md
templates/cursorrules-template.md
templates/README-template.md

Key Principles

Project-specific, not generic — every document must feel written FOR this project, not copy-pasted
Cross-referenced — documents must refer to each other (e.g., implementation-plan references PRD phases)
Cursor-optimized — README must include ready-to-use Cursor prompt examples specific to the project
No server assumption — if user didn't mention a server, default to serverless/managed options
Indian context awareness — if project targets India, default to INR, Indian phone format (+91), UPI/Razorpay, Aadhaar-aware considerations where relevant