SaaS Scaffolder
alirezarezvani/claude-skills
Generates complete, production-ready SaaS project boilerplate including authentication, database schemas, billing integration, API routes, and a working dashboard using Next.js 14+ App Router…
Use this before implementing a product, feature, SaaS, AI app, or side project to score product risk and choose the smallest validation step.
MITAuto-check passed
Install Before You Build
$ npx skills add cosmicstack-labs/mercury-agent-skills --skill before-you-build -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cosmicstack-labs/mercury-agent-skills before-you-build --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/categories/product/before-you-build .claude/skills/before-you-build && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "before-you-build" agent skill from https://github.com/cosmicstack-labs/mercury-agent-skills/tree/main/categories/product/before-you-build into .claude/skills/before-you-build/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "before-you-build", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/cosmicstack-labs/mercury-agent-skills/tree/main/categories/product/before-you-buildType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add cosmicstack-labs/mercury-agent-skills --skill before-you-build -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cosmicstack-labs/mercury-agent-skills before-you-build --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/categories/product/before-you-build .agents/skills/before-you-build && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "before-you-build" agent skill from https://github.com/cosmicstack-labs/mercury-agent-skills/tree/main/categories/product/before-you-build into .agents/skills/before-you-build/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "before-you-build", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cosmicstack-labs/mercury-agent-skills --skill before-you-build -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cosmicstack-labs/mercury-agent-skills before-you-build --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/categories/product/before-you-build .cursor/skills/before-you-build && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "before-you-build" agent skill from https://github.com/cosmicstack-labs/mercury-agent-skills/tree/main/categories/product/before-you-build into .cursor/skills/before-you-build/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "before-you-build", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/cosmicstack-labs/mercury-agent-skills.git --path categories/product/before-you-build--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add cosmicstack-labs/mercury-agent-skills --skill before-you-build -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cosmicstack-labs/mercury-agent-skills before-you-build --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/categories/product/before-you-build .gemini/skills/before-you-build && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "before-you-build" agent skill from https://github.com/cosmicstack-labs/mercury-agent-skills/tree/main/categories/product/before-you-build into .gemini/skills/before-you-build/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "before-you-build", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install cosmicstack-labs/mercury-agent-skills before-you-buildInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add cosmicstack-labs/mercury-agent-skills --skill before-you-build -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/categories/product/before-you-build .github/skills/before-you-build && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "before-you-build" agent skill from https://github.com/cosmicstack-labs/mercury-agent-skills/tree/main/categories/product/before-you-build into .github/skills/before-you-build/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "before-you-build", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cosmicstack-labs/mercury-agent-skills --skill before-you-build -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install cosmicstack-labs/mercury-agent-skills before-you-build --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/categories/product/before-you-build .opencode/skills/before-you-build && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "before-you-build" agent skill from https://github.com/cosmicstack-labs/mercury-agent-skills/tree/main/categories/product/before-you-build into .opencode/skills/before-you-build/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "before-you-build", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
before-you-build- GitHub stars
- 476
- Token cost
- ~2.2k tokens
- SKILL.md length
- 1,189 words
- Files
- 1
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- MIT
At a glance
Use this before implementing a product, feature, SaaS, AI app, or side project to score product risk and choose the smallest validation step.
- Works in 7 steps: Demand Risk → Monetization Risk → Distribution Risk → …
- SKILL.md covers Purpose, When To Use, Core Principle and Inputs To Ask For, plus 7 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Before You Build is an agent skill from cosmicstack-labs/mercury-agent-skills. Use this before implementing a product, feature, SaaS, AI app, or side project to score product risk and choose the smallest validation step.
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: A curated registry of reusable Mercury Agent, Open Claw or Hermes Agent skills designed for real developer workflows, persistent memory, and token-efficient execution. The licence is MIT.
Example prompts
- “/before-you-build”
Workflow steps
7 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 30392fb. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Before You Build loads about 2.2k tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 1,189 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from cosmicstack-labs/mercury-agent-skills at commit 30392fb, republished under its MIT licence (© cosmicstack-labs). 1,189 words, ~2,214 tokens.
Download SKILL.mdSave it as
.claude/skills/before-you-build/SKILL.md (or your agent's skills folder).- name
- before-you-build
- description
- Use this before implementing a product, feature, SaaS, AI app, or side project to score product risk and choose the smallest validation step.
- metadata.author
- bin1874
- metadata.version
- 1.0.0
- metadata.category
- product
- metadata.tags
- product-risk, validation, product-discovery, demand, distribution, monetization, retention, ai-coding
Before You Build
Purpose
Use this skill before an agent starts building a product, feature, SaaS tool, AI app, side project, or startup idea.
The goal is not to block shipping. The goal is to avoid spending engineering time on an idea whose biggest risk is still outside the codebase.
Before implementation, produce:
- A short risk verdict
- A score across product risk dimensions
- The riskiest assumption
- The smallest validation step worth doing next
- A clear build, test, or stop recommendation
When To Use
Use this skill when the user says they want to:
- Build a new product or feature
- Add an AI workflow to an existing product
- Turn an idea into an MVP
- Copy a competitor or trend
- Ship a side project quickly
- Start coding before talking to users
- Ask whether an idea is worth building
- Decide between multiple product bets
Do not use this for:
- Pure code debugging
- Refactoring existing implementation
- UI polish after the product bet is already validated
- Legal, financial, medical, or security review
- Choosing a tech stack
Core Principle
Most early product failures are not caused by missing code.
They usually come from one or more of these gaps:
- The buyer does not feel the problem strongly enough
- The user likes the idea but will not pay
- The product depends on a platform that can change access
- The founder has no repeatable channel to reach buyers
- The workflow is useful once but does not create repeat use
- The trust burden is higher than the product can carry
- The feature is nice to have but not a decision-changing reason to buy
Your job is to find the biggest unknown before implementation expands the cost of being wrong.
Inputs To Ask For
If the user has not provided enough context, ask for the minimum needed:
- What is being built?
- Who is the target user or buyer?
- What painful job does it solve?
- What will the user do differently after adopting it?
- How will the product reach the first 10 real users?
- How will it make money or justify internal investment?
- What evidence already exists?
- What would make the user abandon the product?
If the user cannot answer all of these, continue with low confidence and call out the missing assumptions.
Risk Dimensions
Score each dimension from 1 to 5.
- 1 means low risk or already validated
- 3 means unclear and needs evidence
- 5 means high risk and should be tested before building
1. Demand Risk
Ask whether the target user has an urgent, frequent, or expensive problem.
High-risk signs:
- The user says it is "interesting" but does not describe a current workaround
- The problem is rare or only mildly annoying
- The buyer and user are different, but only the user has been considered
- The idea starts from available technology instead of a painful job
2. Monetization Risk
Ask whether someone has a reason to pay, approve budget, or allocate internal time.
High-risk signs:
- The product saves time but not enough to justify switching
- The target user has no budget
- Pricing depends on future scale instead of early willingness to pay
- Free alternatives are good enough
3. Distribution Risk
Ask how the product will reach qualified users repeatedly.
High-risk signs:
- The plan is "post on Product Hunt" or "share on social"
- Search demand is assumed but not checked
- The market is crowded and discovery depends on luck
- The founder has no audience, channel partner, or outbound motion
4. Retention Risk
Ask whether the product creates a reason to come back.
High-risk signs:
- The job happens once
- The product produces a one-time output
- There is no stored history, habit loop, team workflow, or recurring trigger
- The value is easy to copy manually after the first use
5. Trust Risk
Ask whether the product needs data, permissions, money movement, or judgment that users may not trust.
High-risk signs:
- The product asks for sensitive account access before proving value
- AI output affects business, health, legal, or financial decisions
- The user needs to share private data with an unknown vendor
- The product promises accuracy without verification or fallback
6. Platform Risk
Ask whether the product depends on another platform's API, policy, ranking, data, or distribution.
High-risk signs:
- A single API change can break the product
- The product depends on scraping or unofficial access
- App store, marketplace, or social platform rules are central to growth
- The fallback plan is unclear
Show full SKILL.md (463 more words)Show less
7. Feature Adoption Risk
Ask whether the proposed feature changes behavior or merely adds surface area.
High-risk signs:
- Existing users have not asked for it in their own words
- The feature adds complexity to satisfy a hypothetical segment
- The feature improves demo appeal but not activation, retention, or revenue
- No one can name the metric it should move
Scoring Rubric
Create a table:
| Dimension | Score | Evidence | What would reduce risk |
|---|---|---|---|
| Demand | 1-5 | Current evidence | Smallest evidence needed |
| Monetization | 1-5 | Current evidence | Smallest evidence needed |
| Distribution | 1-5 | Current evidence | Smallest evidence needed |
| Retention | 1-5 | Current evidence | Smallest evidence needed |
| Trust | 1-5 | Current evidence | Smallest evidence needed |
| Platform | 1-5 | Current evidence | Smallest evidence needed |
| Feature adoption | 1-5 | Current evidence | Smallest evidence needed |
Then calculate:
- Total score: sum of all seven scores
- Highest-risk dimension: the largest score
- Confidence: high, medium, or low based on evidence quality
Interpretation:
- 7-13: Build a small version if the main assumption is clear
- 14-22: Run one validation test before building
- 23-35: Do not build yet; validate or narrow the bet first
Evidence Quality
Rank evidence from strongest to weakest:
- Paid purchase, signed contract, or budget approval
- Repeated manual workflow with measurable pain
- Real user interview with specific recent behavior
- Waitlist with qualified users and clear intent
- Competitor traction with a reachable wedge
- Social likes, vague comments, or founder intuition
Do not treat compliments as validation.
Smallest Validation Step
Pick one step that can reduce the highest risk within days, not weeks.
Examples:
- Demand: interview 5 target users about their last workaround
- Monetization: ask 10 qualified buyers to prepay or approve a pilot
- Distribution: run 20 targeted outbound messages and measure replies
- Retention: manually deliver the value twice to the same user
- Trust: test whether users will share the required data after seeing value
- Platform: verify official API terms and design a fallback path
- Feature adoption: show the workflow to 5 existing users and ask what they would stop doing if it shipped
The validation step must produce a decision:
- Build now
- Build a smaller version
- Change target user
- Change channel
- Stop
Output Format
Return this structure:
## Before You Build Verdict
Verdict: Build / Validate first / Do not build yet
Confidence: High / Medium / Low
### One-sentence read
<Plain-English summary of the product risk.>
### Risk score
| Dimension | Score | Evidence | What would reduce risk |
|---|---:|---|---|
| Demand | | | |
| Monetization | | | |
| Distribution | | | |
| Retention | | | |
| Trust | | | |
| Platform | | | |
| Feature adoption | | | |
Total: <score>/35
### Riskiest assumption
<The assumption most likely to make the build fail.>
### Smallest validation step
<One concrete action that can be done before implementation.>
### Build scope if validated
<The smallest useful version to build after the test passes.>Common Mistakes
- Starting with architecture before the buyer is clear
- Treating a landing page signup as proof of payment intent
- Asking users what they want instead of what they did recently
- Building for "everyone who uses AI" instead of one reachable segment
- Ignoring distribution until after launch
- Assuming a platform will keep API access stable
- Adding more features when the core value is still unproven
- Using a large MVP to answer a question a manual test could answer
Final Rule
If the riskiest assumption can be tested without code, test it before code.
If it cannot be tested without code, build only the smallest artifact that tests that assumption.
© cosmicstack-labs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in categories/product/before-you-build of cosmicstack-labs/mercury-agent-skills.
Open the folder on GitHubat commit 30392fb
Compare with similar skills
Before You Build next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Before You Build this skillcosmicstack-labs/mercury-agent-skills | 476 | — | ~2.2k | Automated safety check: Pass | MIT | |
| SaaS Scaffolderalirezarezvani/claude-skills | 28k | 1 repos | ~2.6k | Automated safety check: Pass | MIT | |
| SaaS Mvp Launchersickn33/agentic-awesome-skills | 47k | 2 repos | ~1.9k | Automated safety check: Notes | MIT | |
| SaaS Pricing Strategistsickn33/agentic-awesome-skills | 47k | 1 repos | ~1.5k | Automated safety check: Pass | MIT | |
| Remotion SaaSremotion-dev/remotion | 62k | 3 repos | ~264 | Automated safety check: Pass | Custom licence | |
| SaaS Multi Tenantdavila7/claude-code-templates | 32k | 3 repos | ~3.1k | Automated safety check: Pass | MIT |
Similar skills
SaaS Mvp Launcher
sickn33/agentic-awesome-skills
A skill your agent uses when planning or building a SaaS MVP from scratch.
SaaS Pricing Strategist
sickn33/agentic-awesome-skills
Design, optimize, and test pricing strategies for SaaS products using data-driven frameworks, competitive analysis, and psychological pricing principles.
- Official
Remotion SaaS
remotion-dev/remotion
Build an app with Remotion
SaaS Multi Tenant
davila7/claude-code-templates
Design and implement multi-tenant SaaS architectures with row-level security, tenant-scoped queries, shared-schema isolation, and safe cross-tenant admin patterns in PostgreSQL and TypeScript.
Implementing Zero Trust For SaaS Applications
mukul975/Anthropic-Cybersecurity-Skills
Secures SaaS apps (Microsoft 365, Google Workspace, Salesforce, Slack) via CASB/SSPM deployment, conditional access policies, OAuth app governance, and session-level DLP controls enforcing identity…
More from cosmicstack-labs/mercury-agent-skills
All 12 skills in this repoHyperframes CLI
cosmicstack-labs/mercury-agent-skills
HyperFrames CLI dev loop — project scaffolding, validation (lint/inspect), browser preview with live reload, MP4/WebM rendering, and environment troubleshooting (doctor, browser, info, upgrade).
Hyperframes Media
cosmicstack-labs/mercury-agent-skills
Asset preprocessing for HyperFrames compositions — local text-to-speech narration (Kokoro-82M, no API key), audio/video transcription (Whisper), and background removal for transparent overlays…
Agent Handoff Protocols
cosmicstack-labs/mercury-agent-skills
Design and implement agent-to-agent handoff protocols for multi-agent systems.
Agent Health Monitoring
cosmicstack-labs/mercury-agent-skills
Monitor AI agent health, detect anomalies, set up alerting, and maintain observability dashboards for production multi-agent systems.
Agent Task Delegation
cosmicstack-labs/mercury-agent-skills
Design and operate task delegation systems for multi-agent fleets.
Any2pdf
cosmicstack-labs/mercury-agent-skills
Convert Markdown to publication-quality PDF with reportlab — CJK/Latin mixed text, themes, cover pages, watermarks, callouts, formulas, and interactive theme selection
Questions about Before You Build
What does Before You Build do?
Use this before implementing a product, feature, SaaS, AI app, or side project to score product risk and choose the smallest validation step. Before You Build is an agent skill from cosmicstack-labs/mercury-agent-skills. Use this before implementing a product, feature, SaaS, AI app, or side project to score product risk and choose the smallest validation step.
How do I install Before You Build in Claude Code?
Run `npx skills add cosmicstack-labs/mercury-agent-skills --skill before-you-build -a claude-code`. Or copy the skill folder (categories/product/before-you-build in cosmicstack-labs/mercury-agent-skills) into .claude/skills/before-you-build in your project. Claude Code loads it when a task matches its description.
How do I install Before You Build in Codex?
Run `npx skills add cosmicstack-labs/mercury-agent-skills --skill before-you-build -a codex`. Or copy the skill folder (categories/product/before-you-build in cosmicstack-labs/mercury-agent-skills) into .agents/skills/before-you-build in your project. Codex loads it when a task matches its description.
Can I use Before You Build in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cosmicstack-labs/mercury-agent-skills --skill before-you-build -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/before-you-build, .gemini/skills/before-you-build, .github/skills/before-you-build and .opencode/skills/before-you-build in your project.
What does Before You Build need to run?
SKILL.md names no scripts, command-line tools or credentials: Before You Build is instructions for the agent only.
Does Before You Build access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Before You Build safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Before You Build use?
Before You Build is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Before You Build use?
About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Before You Build?
Skills that share tags, products or a category with Before You Build: SaaS Scaffolder (alirezarezvani/claude-skills, 28k stars), SaaS Mvp Launcher (sickn33/agentic-awesome-skills, 47k stars), SaaS Pricing Strategist (sickn33/agentic-awesome-skills, 47k stars) and Remotion SaaS (remotion-dev/remotion, 62k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Before You Build?
cosmicstack-labs (a GitHub organization) maintains it in cosmicstack-labs/mercury-agent-skills, which has 476 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on August 25, 2026.
Source: cosmicstack-labs/mercury-agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.