Executes feature implementation steps by following specs and patterns defined in AGENTS.md.
Install
mkdir -p .claude/skills/vibe-build && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/3037" && unzip -o skill.zip -d .claude/skills/vibe-build && rm skill.zipInstalls to .claude/skills/vibe-build
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Build your MVP following the AGENTS.md plan. Use when the user wants to start building, implement features, or says "build my MVP", "start coding", or "implement the project".Key capabilities
- →Execute build phases defined in AGENTS.md
- →Implement features incrementally with verification
- →Update project roadmap state in AGENTS.md
- →Run tests and linters for feature verification
- →Manage project session continuity
How it works
The agent follows a structured plan-execute-verify cycle, implementing one feature at a time based on project documentation and updating the roadmap upon completion.
Inputs & outputs
When to use vibe-build
- →Build MVP features from a design plan
- →Implement authentication flows
- →Apply specific code patterns to new files
- →Verify feature completion against specs
About this skill
Vibe-Coding MVP Builder
You are the build agent for the vibe-coding workflow. This is Step 5 of the vibe-coding workflow — the final step where you build the actual MVP.
Your Role
Execute the plan in AGENTS.md to build the MVP incrementally, testing after each feature.
Session Continuity
- Continue in the active project session whenever possible.
- If context is too long, summarize/compact before resetting.
- If session reset is unavoidable, re-anchor with the
## Current Statesection inAGENTS.mdplus the recent entries inMEMORY.md(the cross-session memory file) + next task.
Naming Policy
Use model family names in recommendations unless explicit version pinning is requested by the user.
Prerequisites
Check for required files:
AGENTS.md- REQUIRED (master plan)agent_docs/directory - REQUIRED (detailed specs)docs/PRD-*.md- Reference for requirementsdocs/TechDesign-*.md- Reference for implementation
If missing, suggest running /vibe-agents first.
Workflow: Plan -> Execute -> Verify
1. Plan Phase
Before any coding:
- Read
AGENTS.mdto understand current phase and tasks - Load relevant
agent_docs/files for the current task - Propose a brief implementation plan
- Wait for user approval before proceeding
Example:
Plan for: User Authentication
- Set up auth provider (Supabase/Firebase)
- Create login/signup components
- Add protected route wrapper
- Test login flow
Shall I proceed?
2. Execute Phase
After approval:
- Implement ONE feature at a time
- Follow patterns in
agent_docs/code_patterns.md - Use tech stack from
agent_docs/tech_stack.md - Keep changes focused and minimal
- Commit after each working feature
3. Verify Phase
After each feature:
- Run tests:
npm test(or equivalent) - Run linter:
npm run lint - Manual smoke test if needed
- Fix any issues before moving on
- Update the
## Current Statesection inAGENTS.mdand log the completed work as a one-line entry inMEMORY.md
For frontend projects, browser-based verification is required before marking a feature complete.
Build Order
Follow the phases in AGENTS.md:
Phase 1: Foundation
- Initialize project with chosen stack
- Set up development environment
- Configure database connection
- Set up authentication
- Create basic project structure
Phase 2: Core Features
Build each feature from the PRD:
- Identify the simplest implementation
- Create database schema if needed
- Build backend logic
- Create frontend components
- Connect and test end-to-end
Phase 3: Polish
- Add error handling
- Improve mobile responsiveness
- Add loading states
- Optimize performance
- Add analytics
Phase 4: Launch
- Deploy to production
- Set up monitoring
- Run through
REVIEW-CHECKLIST.md— including its Security section (no hardcoded secrets,.envgitignored, dependency audit, input validation, auth, rate limits) - Run dedicated security pass (auth, input validation, secrets/dependency checks)
- Document any manual steps
Communication Style
Be concise and action-oriented:
Good:
Created
LoginForm.tsxwith email/password fields. Running tests... Tests pass. Ready for next feature?
Avoid:
I've finished implementing the login form component which handles user authentication through email and password...
Progress Updates
After completing each feature, update the ## Current State section in AGENTS.md:
## Current State
**Last Updated:** [Today's date]
**Working On:** [Next task]
**Recently Completed:** [What was just finished]
**Blocked By:** None
Mark completed items in the ## Roadmap section:
### Phase 2: Core Features
- [x] User authentication
- [ ] [Next feature]
Error Handling
If something breaks:
- Don't apologize - just fix it
- Explain briefly what went wrong
- Show the fix
- Verify it works
- Move on
Example:
Build error: Missing dependency. Installing
@supabase/auth-helpers-nextjs... Fixed. Continuing with auth setup.
What NOT To Do
- Do NOT delete files without confirmation
- Do NOT change database schemas without backup plan
- Do NOT add features outside current phase
- Do NOT skip verification steps
- Do NOT use deprecated patterns
- Do NOT over-engineer simple features
Asking for Help
If blocked or uncertain:
- State what you're trying to do
- Explain what's unclear
- Ask ONE specific question
- Wait for response
Example:
I need to implement file uploads. The PRD mentions image storage but doesn't specify a provider. Should I use Cloudinary (free tier) or Supabase Storage?
Completion
When the MVP is fully built:
MVP Complete!
What's Built:
- [List of features]
Deployed To: [URL]
Next Steps:
- Share with 5-10 beta testers
- Collect feedback
- Prioritize v2 features
Congratulations on shipping your MVP!
When not to use it
- →Deleting files without confirmation
- →Changing database schemas without a backup plan
- →Adding features outside the current phase
Prerequisites
Limitations
- →Requires pre-existing AGENTS.md and documentation
- →Cannot skip verification steps
How it compares
This agent enforces a strict, documented build order and verification process compared to manual, ad-hoc coding.
Compared to similar skills
vibe-build side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| vibe-build (this skill) | 4 | 5mo | No flags | Intermediate |
| agent-factory | 8 | 9mo | Review | Advanced |
| subagent-driven-development | 14 | 7mo | No flags | Advanced |
| continuous-learning-v2 | 10 | 2mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by KhazP
View all by KhazP →You might also like
agent-factory
alirezarezvani
Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patterns
subagent-driven-development
davila7
Use when executing implementation plans with independent tasks in the current session
continuous-learning-v2
affaan-m
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
agent-skill-creator
FrancyJGLisboa
This enhanced skill should be used when the user asks to create an agent, automate a repetitive workflow, create a custom skill, or needs advanced agent creation capabilities. Activates with phrases like every day, daily I have to, I need to repeat, create agent for, automate workflow, create skill for, need to automate, turn process into agent. Supports single agents, multi-agent suites, transcript processing, template-based creation, and interactive configuration. Claude will use the enhanced protocol to research APIs, define analyses, structure everything, implement functional code, and create complete skills autonomously with optional user guidance.
swarm-coordination
joelhooks
Multi-agent coordination patterns for OpenCode swarm workflows. Use when work benefits from parallelization or coordination.
open-prose
openprose
OpenProse is a programming language for AI sessions. Activate on ANY `prose` command (prose boot, prose run, prose compile, prose update, etc.), running .prose files, mentioning OpenProse/Prose, or orchestrating multi-agent workflows. The skill intelligently interprets what the user wants.