How do I install the Startup Validating skill?

Run npx skillmds add majiayu000/startup-validating in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Startup Validating safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Startup Validating?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Startup Validating free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Startup Validating?

majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Startup Validating by majiayu000 — Agent Skill

Name: Startup Validating
Rating: 4.5 (4 reviews)
Author: majiayu000

Startup Validating

Orchestrate a 6-stage startup idea validation pipeline with decision gates, confidence scoring, and composable domain presets. Use when user runs /startup-validate command, wants to validate a startup idea, mentions "startup validation", "idea validation", "market validation", "feasibility analysis", or "go-to-market plan".

majiayu000 707a034 2 files · 3.6 KB Updated Sep 9, 2026 567 repo stars

File contents

Startup Validation Pipeline

Orchestrate a 6-stage startup validation pipeline. Each stage is executed by a dedicated agent, produces a confidence-scored markdown report, and presents a decision gate.

Pipeline Stages

#	Stage	Agent	Decision Gate
1	Problem & Market Validation	`market-validator`	Is this a real problem worth solving?
2	Feasibility Analysis	`feasibility-analyst`	Can this be built legally and operationally?
3	Product & Solution Design	`product-designer`	Can we design a differentiated product?
4	Business Model & Strategy	`business-strategist`	Can this become profitable and defensible?
5	Go-to-Market & Growth	`growth-strategist`	Can we acquire users sustainably?
6	Execution Roadmap	`execution-planner`	Can we build and launch realistically?

Arguments

Parse from $ARGUMENTS:

Flag	Effect
`"<idea>"`	The startup idea to validate (required — or use `@file`)
`@<file>`	Provide idea description or research brief from a file
`--preset <name>`	Load preset from `presets/` dir (composable)
`--fast`	Skip decision gates, run all stages autonomously
`--deep`	Spawn parallel sub-agents per stage + critic synthesis
`--from <N>`	Resume from stage N (reads prior reports from disk)
`--stage <N>`	Run only stage N in isolation
`--name <slug>`	Override auto-generated run slug

Orchestration

See WORKFLOW.md for the complete orchestration protocol including:

Slug generation and output directory setup
Preset loading and composition
Stage execution (standard and deep modes)
Decision gate interaction
Summary scorecard generation

Output

Reports are saved to startup-validation/{slug}/ in the current project:

startup-validation/{slug}/
├── idea.md
├── pipeline-state.json          ← created on PAUSE, consumed on resume
├── stage-1-market-validation.md
├── stage-2-feasibility.md
├── stage-3-product-design.md
├── stage-4-business-model.md
├── stage-5-go-to-market.md
├── stage-6-execution-roadmap.md
└── summary.md

Examples

See EXAMPLES.md for usage examples.

Troubleshooting

See TROUBLESHOOTING.md for common issues.

---name: startup-validatingdescription: Orchestrate a 6-stage startup idea validation pipeline with decision gates, confidence scoring, and composable domain presets. Use when user runs /startup-validate command, wants to validate a startup idea, mentions "startup validation", "idea validation", "market validation", "feasibility analysis", or "go-to-market plan".--- # Startup Validation Pipeline Orchestrate a 6-stage startup validation pipeline. Each stage is executed by a dedicated agent, produces a confidence-scored markdown report, and presents a decision gate. ## Pipeline Stages | # | Stage | Agent | Decision Gate | |---|-------|-------|--------------| | 1 | Problem & Market Validation | `market-validator` | Is this a real problem worth solving? | | 2 | Feasibility Analysis | `feasibility-analyst` | Can this be built legally and operationally? | | 3 | Product & Solution Design | `product-designer` | Can we design a differentiated product? | | 4 | Business Model & Strategy | `business-strategist` | Can this become profitable and defensible? | | 5 | Go-to-Market & Growth | `growth-strategist` | Can we acquire users sustainably? | | 6 | Execution Roadmap | `execution-planner` | Can we build and launch realistically? | ## Arguments Parse from `$ARGUMENTS`: | Flag | Effect | |------|--------| | `"<idea>"` | The startup idea to validate (required — or use `@file`) | | `@<file>` | Provide idea description or research brief from a file | | `--preset <name>` | Load preset from `presets/` dir (composable) | | `--fast` | Skip decision gates, run all stages autonomously | | `--deep` | Spawn parallel sub-agents per stage + critic synthesis | | `--from <N>` | Resume from stage N (reads prior reports from disk) | | `--stage <N>` | Run only stage N in isolation | | `--name <slug>` | Override auto-generated run slug | ## Orchestration See [WORKFLOW.md](WORKFLOW.md) for the complete orchestration protocol including: - Slug generation and output directory setup - Preset loading and composition - Stage execution (standard and deep modes) - Decision gate interaction - Summary scorecard generation ## Output Reports are saved to `startup-validation/{slug}/` in the current project: ``` startup-validation/{slug}/ ├── idea.md ├── pipeline-state.json ← created on PAUSE, consumed on resume ├── stage-1-market-validation.md ├── stage-2-feasibility.md ├── stage-3-product-design.md ├── stage-4-business-model.md ├── stage-5-go-to-market.md ├── stage-6-execution-roadmap.md └── summary.md ``` ## Examples See [EXAMPLES.md](EXAMPLES.md) for usage examples. ## Troubleshooting See [TROUBLESHOOTING.md](TROUBLESHOOTING.md) for common issues.

Frequently asked questions