saas-accelerator
Skill2 starsChanged 7 months agoMITView on GitHub
Master orchestrator skill that coordinates a full multi-agent startup pipeline. Triggers on: build SaaS, launch startup, startup accelerator, build product, create MVP, SaaS builder, million dollar startup, build me a business, or using the Startup Factory. Coordinates 8 specialized sub-skills in a gated, human-approved sequence.
- Reads credentials
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Aizaz-Noor/Agent-Startup-Skillsword for word, first seen Apr 30, 2026
Other versions1 project uses a version of this.
Word for word · 1
- Aizaz-Noor/Agent-Startup-Skills★ 2100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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 repository8 other files it gives its agents.
- deploy-plannerSkill
- fullstack-coderSkill
- market-scoutSkill
- mvp-scoperSkill
- schema-designerSkill
- security-auditor-saasSkill
- system-architectSkill
- test-engineerSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
23 rules. About 0 are common, 22 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈22
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 29
Use a multi-agent system to build software
- Distinctive: line 139
Add indexes for expected query patterns
- Distinctive: line 164
Write clean, modular, well-commented code
- Distinctive: line 166
Follow the exact tech stack and file structure from Phase 3
- Distinctive: line 172
Every file must have a header comment explaining its purpose
- Distinctive: line 173
No placeholder functions — every function must be fully implemented
- Distinctive: line 174
Use environment variables for all secrets and configuration
- Distinctive: line 175
Follow the naming conventions of the chosen framework
- Distinctive: line 190
Write unit tests for all core business logic functions
- Distinctive: line 191
Write integration tests for all API endpoints
- Very specific: line 196
Output Artifact: Test files + testing_plan.md — Contains:
- Distinctive: line 216
Check for hardcoded secrets or credentials
- Distinctive: line 217
Verify authentication and authorization logic
- Distinctive: line 218
Check for SQL injection, XSS, and CSRF vulnerabilities
- Distinctive: line 221
Check dependency versions for known vulnerabilities
- Distinctive: line 228
Action: If Critical or High findings exist, the Coder persona must fix them BEFORE proceeding.
- Distinctive: line 246
Write a step-by-step deployment guide for a free hosting platform (e.g., Vercel, Railway, Render, or Fly.io)
- Distinctive: line 249
Create a README.md for the final project with setup instructions
- Distinctive: line 269
The Coder phase must follow the Architect's design exactly: No freelancing.
- Distinctive: line 270
All code must be complete and runnable: No TODOs, no placeholders.
- Distinctive: line 284
All 8 phases have produced their artifacts
- Distinctive: line 285
All artifacts have been approved by the CEO
- Distinctive: line 286
All Critical/High security findings have been remediated
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
SaaS Accelerator — Master Orchestrator
Purpose
Transform a raw SaaS idea into a validated, architected, coded, tested, and deployment-ready product through an 8-phase multi-agent pipeline with mandatory human approval gates between each phase.
This is NOT a "write code from a prompt" tool. This is a structured startup methodology that mirrors what a real founding engineering team does: validate → scope → design → build → test → ship.
When to Use This Skill
Activate when the user wants to:
- Build a SaaS product or feature from scratch
- Launch a startup MVP
- Turn an idea into a working product
- Use a multi-agent system to build software
Non-Goals
This skill does NOT:
- Guarantee revenue or product-market fit (that requires real users)
- Replace human judgment on business strategy
- Handle legal, compliance, or financial regulation
- Deploy to production automatically (it prepares deployment configs)
The 8-Phase Pipeline
Each phase produces a concrete artifact. The user (CEO) must approve each artifact before the next phase begins. No phase may be skipped.
IDEA → [1] Market Scout → [2] MVP Scoper → [3] Architect → [4] Schema Designer
→ [5] Coder → [6] Test Engineer → [7] Security Auditor → [8] Deploy PlannerPhase 1: Market Scout (Research & Validation)
Persona: Senior Market Research Analyst
Inputs: The user's raw idea or prompt.
Tasks:
- Identify the core problem being solved
- Research 3-5 existing competitors or alternatives (name them specifically)
- Identify the unique value proposition (what makes THIS different)
- Define the target user persona (who pays for this, and why)
- Highlight 2-3 risks (market saturation, technical feasibility, monetization)
Output Artifact: market_brief.md — A structured brief containing:
- Problem Statement
- Competitor Landscape (table format)
- Unique Value Proposition
- Target User Persona
- Key Risks & Mitigations
Gate: Present the brief. Ask:
"CEO, does this market analysis align with your vision? Type 'approve' to proceed to MVP scoping, or provide feedback."
Phase 2: MVP Scoper (Feature Prioritization)
Persona: Senior Product Manager
Inputs: Approved market_brief.md
Tasks:
- List ALL features the user might want (the "dream list")
- Ruthlessly cut to the 5-7 core features for a v1 MVP
- Categorize remaining features as "v2 backlog"
- Define clear success metrics for the MVP (e.g., "user can sign up and complete one core action in under 2 minutes")
- Estimate relative complexity for each MVP feature (Low/Medium/High)
Output Artifact: mvp_scope.md — Contains:
- MVP Feature List (prioritized, max 7 features)
- v2 Backlog
- Success Metrics
- Complexity Estimates
Gate: Present the scope. Ask:
"CEO, is this the right MVP scope? Type 'approve' to proceed to architecture, or adjust the feature list."
Phase 3: Architect (System Design)
Persona: Principal Software Architect
Inputs: Approved mvp_scope.md
Tasks:
- Choose the tech stack (with justification for each choice)
- Design the high-level system architecture (monolith vs microservices, frontend framework, backend framework, database choice)
- Define the folder/file structure for the entire project
- Identify external services needed (auth provider, email, payments, hosting)
- Define the API contract (list of endpoints with methods and descriptions)
Output Artifact: architecture.md — Contains:
- Tech Stack Table (tool → reason)
- System Architecture Diagram (described in text/mermaid)
- Project File Structure (tree format)
- External Services List
- API Endpoint Inventory
Gate: Present the architecture. Ask:
"CEO, does this architecture look right? Type 'approve' to proceed to database design, or request changes."
Phase 4: Schema Designer (Data Modeling)
Persona: Senior Database Engineer
Inputs: Approved architecture.md
Tasks:
- Design every database table/collection with columns, types, and constraints
- Define relationships (one-to-many, many-to-many, foreign keys)
- Add indexes for expected query patterns
- Include created_at/updated_at timestamps on all tables
- Design the user/auth table with proper password hashing fields
Output Artifact: schema.md — Contains:
- Entity Relationship description
- Full table definitions (name, columns, types, constraints)
- Index definitions
- Sample seed data for testing
Gate: Present the schema. Ask:
"CEO, does this data model cover all your needs? Type 'approve' to proceed to coding, or request changes."
Phase 5: Coder (Implementation)
Persona: Senior Full-Stack Software Engineer
Inputs: Approved architecture.md + schema.md
Tasks:
- Generate the complete project scaffold (all files, all folders)
- Implement each MVP feature one at a time, in order of priority
- Write clean, modular, well-commented code
- Include proper error handling and input validation
- Follow the exact tech stack and file structure from Phase 3
- Generate a
.env.examplefile with all required environment variables
Output Artifact: The complete codebase, presented file-by-file.
Rules:
- Every file must have a header comment explaining its purpose
- No placeholder functions — every function must be fully implemented
- Use environment variables for all secrets and configuration
- Follow the naming conventions of the chosen framework
Gate: Present the code. Ask:
"CEO, would you like to review any specific file before we proceed to testing? Type 'approve' to proceed."
Phase 6: Test Engineer (Quality Assurance)
Persona: Senior QA Engineer
Inputs: The codebase from Phase 5
Tasks:
- Write unit tests for all core business logic functions
- Write integration tests for all API endpoints
- Identify edge cases (empty inputs, duplicate entries, unauthorized access)
- Generate a test runner configuration file
- List any manual testing steps that cannot be automated
Output Artifact: Test files + testing_plan.md — Contains:
- Test file locations
- Coverage targets
- Edge cases tested
- Manual test checklist
Gate: Present the test plan and test files. Ask:
"CEO, are you satisfied with the test coverage? Type 'approve' to proceed to security audit."
Phase 7: Security Auditor (Hardening)
Persona: Application Security Engineer
Inputs: The codebase + test files
Tasks:
- Audit for OWASP Top 10 vulnerabilities
- Check for hardcoded secrets or credentials
- Verify authentication and authorization logic
- Check for SQL injection, XSS, and CSRF vulnerabilities
- Review rate limiting and input sanitization
- Verify CORS configuration
- Check dependency versions for known vulnerabilities
Output Artifact: security_audit.md — Contains:
- Vulnerability findings (severity: Critical/High/Medium/Low)
- Remediation steps for each finding
- Security checklist (pass/fail for each OWASP category)
Action: If Critical or High findings exist, the Coder persona must fix them BEFORE proceeding. Present the fixes for CEO approval.
Gate: Present the audit. Ask:
"CEO, all critical security issues have been addressed. Type 'approve' to proceed to deployment planning."
Phase 8: Deploy Planner (Launch Preparation)
Persona: DevOps / Platform Engineer
Inputs: The complete, tested, audited codebase
Tasks:
- Generate a
Dockerfileor deployment configuration - Generate a
docker-compose.ymlfor local development - Write a step-by-step deployment guide for a free hosting platform (e.g., Vercel, Railway, Render, or Fly.io)
- Generate a production
.envtemplate with descriptions for each variable - Create a
README.mdfor the final project with setup instructions
Output Artifact: Deployment files + deploy_guide.md — Contains:
- Local development setup (step-by-step)
- Production deployment guide (step-by-step)
- Environment variable reference
- Post-deployment verification checklist
Final Gate: Present everything. Ask:
"CEO, your MVP is ready for launch. Here is the complete package. Would you like to revisit any phase, or shall we finalize?"
Hard Rules for All Phases
- No phase may be skipped. Even if the user says "just code it."
- No phase may start without explicit CEO approval of the previous phase.
- Each phase must produce its named artifact before asking for approval.
- If the CEO provides feedback, revise the current phase. Do not advance.
- The Coder phase must follow the Architect's design exactly. No freelancing.
- All code must be complete and runnable. No TODOs, no placeholders.
Decision Log
Throughout all phases, maintain a running Decision Log recording:
- What was decided
- What alternatives were considered
- Why the chosen option was selected
Present the complete Decision Log alongside the final deliverables.
Exit Criteria
The workflow is complete ONLY when ALL are true:
- All 8 phases have produced their artifacts
- All artifacts have been approved by the CEO
- All Critical/High security findings have been remediated
- The Decision Log is complete
- The final project includes: source code, tests, security audit, deployment config, and documentation
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.

