HidayAgentStart

Hiday

Multi-Agent Autonomous Startup System for Enterprise

Transform a PRD into a fully deployed, revenue-generating product with zero human intervention.

What is Hiday?

Hiday is a Claude Code skill that orchestrates 37 specialized AI agents across 6 swarms to autonomously build, deploy, and operate a complete startup. Just say "Hiday" and provide a PRD.

PRD → Competitive Research → Architecture → Development → Testing → Deployment → Marketing → Revenue

Features

Category	Capabilities
Multi-Agent System	37 agents across Engineering, Operations, Business, Data, Product, and Growth swarms
Parallel Code Review	3 specialized reviewers (code, business, security) running simultaneously
Quality Gates	14 automated gates including security scans, load tests, accessibility
Deployment	AWS, GCP, Azure, Vercel, Railway with blue-green and canary strategies
Business Ops	Marketing, Sales, HR, Legal, Finance, Investor Relations agents
Reliability	Circuit breakers, dead letter queues, exponential backoff, state recovery
Observability	External alerting (Slack, PagerDuty), backup/restore, log rotation

Agent Swarms

Engineering (8)

eng-frontend eng-backend eng-database eng-mobile eng-api eng-qa eng-perf eng-infra

Operations (8)

ops-devops ops-sre ops-security ops-monitor ops-incident ops-release ops-cost ops-compliance

Business (8)

biz-marketing biz-sales biz-finance biz-legal biz-support biz-hr biz-investor biz-partnerships

Data (3)

data-ml data-eng data-analytics

Product (3)

prod-pm prod-design prod-techwriter

Growth (4)

growth-hacker growth-community growth-success growth-lifecycle

Review (3)

review-code review-business review-security

Installation

Skill File Structure

SKILL.md              # ← THE SKILL (required) - contains YAML frontmatter
references/
├── agents.md         # Agent definitions
├── deployment.md     # Deployment guides
└── business-ops.md   # Business workflows

For Claude.ai (Web)

1. Go to Releases
2. Download hiday-X.X.X.zip or hiday-X.X.X.skill
3. Go to Claude.ai → Settings → Features → Skills
4. Upload the zip/skill file

The zip has SKILL.md at the root level as Claude.ai expects.

For Anthropic API Console (console.anthropic.com)

1. Go to Releases
2. Download hiday-api-X.X.X.zip (note: the -api- version)
3. Go to console.anthropic.com → Skills
4. Upload the zip file

The API version has SKILL.md inside a hiday/ folder as the API requires.

For Claude Code (CLI)

Option A: Download from Releases

# Download the Claude Code version
cd ~/.claude/skills

# Get latest version number
VERSION=$(curl -s https://api.github.com/repos/asklokesh/claudeskill-hiday/releases/latest | grep tag_name | cut -d'"' -f4 | tr -d 'v')

# Download and extract
curl -L -o hiday.zip "https://github.com/asklokesh/claudeskill-hiday/releases/download/v${VERSION}/hiday-claude-code-${VERSION}.zip"
unzip hiday.zip && rm hiday.zip
# Creates: ~/.claude/skills/hiday/SKILL.md

Option B: Git Clone

# For personal use (all projects)
git clone https://github.com/asklokesh/claudeskill-hiday.git ~/.claude/skills/hiday

# For a specific project only
git clone https://github.com/asklokesh/claudeskill-hiday.git .claude/skills/hiday

Option C: Minimal Install (curl)

mkdir -p ~/.claude/skills/hiday/references
curl -o ~/.claude/skills/hiday/SKILL.md https://raw.githubusercontent.com/asklokesh/claudeskill-hiday/main/SKILL.md
curl -o ~/.claude/skills/hiday/references/agents.md https://raw.githubusercontent.com/asklokesh/claudeskill-hiday/main/references/agents.md
curl -o ~/.claude/skills/hiday/references/deployment.md https://raw.githubusercontent.com/asklokesh/claudeskill-hiday/main/references/deployment.md
curl -o ~/.claude/skills/hiday/references/business-ops.md https://raw.githubusercontent.com/asklokesh/claudeskill-hiday/main/references/business-ops.md

Verify Installation

# Check the skill is in place
cat ~/.claude/skills/hiday/SKILL.md | head -5
# Should show YAML frontmatter with name: hiday

Usage

Quick Start (Recommended)

Use the autonomous runner - it handles everything:

# Run with a PRD (fully autonomous with auto-resume)
./autonomy/run.sh ./docs/requirements.md

# Run interactively
./autonomy/run.sh

The autonomous runner will:

1. Check all prerequisites (Claude CLI, Python, Git, etc.)
2. Verify skill installation
3. Initialize the .hiday/ directory
4. Start status monitor (updates .hiday/STATUS.txt every 5s)
5. Start Claude Code with live output (see what's happening)
6. Auto-resume on rate limits or interruptions
7. Continue until completion or max retries

Live Output

No more staring at a blank screen! Claude's output is displayed in real-time:

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  CLAUDE CODE OUTPUT (live)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

[You see Claude working in real-time here...]

Status Monitor

Monitor task progress in another terminal:

# Watch status updates live
watch -n 2 cat .hiday/STATUS.txt

Output:

╔════════════════════════════════════════════════════════════════╗
║                      HIDAY STATUS                              ║
╚════════════════════════════════════════════════════════════════╝

Phase: DEVELOPMENT

Tasks:
  ├─ Pending:     10
  ├─ In Progress: 1
  ├─ Completed:   5
  └─ Failed:      0

Manual Mode

If you prefer manual control:

# Launch Claude Code with autonomous permissions
claude --dangerously-skip-permissions

# Then say:
> Hiday

# Or with a specific PRD:
> Hiday with PRD at ./docs/requirements.md

Autonomy Configuration

Environment variables to customize the autonomous runner:

# Example with custom settings
HIDAY_MAX_RETRIES=100 \
HIDAY_BASE_WAIT=120 \
HIDAY_MAX_WAIT=7200 \
./autonomy/run.sh ./docs/requirements.md

Variable	Default	Description
HIDAY_MAX_RETRIES	50	Maximum retry attempts before giving up
HIDAY_BASE_WAIT	60	Base wait time in seconds
HIDAY_MAX_WAIT	3600	Maximum wait time (1 hour)
HIDAY_SKIP_PREREQS	false	Skip prerequisite checks

How Auto-Resume Works

./autonomy/run.sh prd.md
         │
         ▼
┌─────────────────────┐
│ Check Prerequisites │ ← Claude CLI, Python, Git, etc.
└─────────────────────┘
         │
         ▼
┌─────────────────────┐
│ Initialize .hiday/  │ ← State, queues, logs
└─────────────────────┘
         │
         ▼
┌─────────────────────┐
│ Run Claude Code     │◄─────────────────┐
└─────────────────────┘                  │
         │                               │
    Exit code?                           │
         │                               │
    ┌────┴────┐                          │
    ▼         ▼                          │
 Success   Rate Limit                    │
    │         │                          │
    ▼         ▼                          │
 DONE!    Wait (exponential backoff) ────┘

Resuming After Interruption

If you stop the script (Ctrl+C) or it crashes:

# Just run it again - state is saved automatically
./autonomy/run.sh ./docs/requirements.md

See autonomy/README.md for detailed documentation.

How It Works

Phase Execution

Phase	Description
0. Bootstrap	Create .hiday/ directory structure, initialize state
1. Discovery	Parse PRD, competitive research via web search
2. Architecture	Tech stack selection with self-reflection
3. Infrastructure	Provision cloud, CI/CD, monitoring
4. Development	Implement with TDD, parallel code review
5. QA	14 quality gates, security audit, load testing
6. Deployment	Blue-green deploy, auto-rollback on errors
7. Business	Marketing, sales, legal, support setup
8. Growth	Continuous optimization, A/B testing, feedback loops

Parallel Code Review Pattern

Every task goes through 3 reviewers simultaneously:

IMPLEMENT → REVIEW (3 parallel) → AGGREGATE → FIX → RE-REVIEW → COMPLETE
                │
                ├─ code-reviewer (opus)
                ├─ business-logic-reviewer (opus)
                └─ security-reviewer (opus)

Severity-Based Issue Handling

Severity	Action
Critical/High/Medium	Block. Fix immediately. Re-review.
Low	Add // TODO(review): ... comment, continue
Cosmetic	Add // FIXME(nitpick): ... comment, continue

Directory Structure

When running, Hiday creates:

.hiday/
├── state/          # Orchestrator and agent states
├── queue/          # Task queue (pending, in-progress, completed, dead-letter)
├── messages/       # Inter-agent communication
├── logs/           # Audit logs
├── config/         # Configuration files
├── prompts/        # Agent role prompts
├── artifacts/      # Releases, reports, backups
└── scripts/        # Helper scripts

Configuration

Circuit Breakers

# .hiday/config/circuit-breakers.yaml
defaults:
  failureThreshold: 5
  cooldownSeconds: 300

External Alerting

# .hiday/config/alerting.yaml
channels:
  slack:
    webhook_url: "${SLACK_WEBHOOK_URL}"
    severity: [critical, high]

Example PRDs for Testing

Test the skill with these pre-built PRDs in the examples/ directory:

PRD	Complexity	Time	Description
simple-todo-app.md	Low	~10 min	Basic todo app - tests core functionality
api-only.md	Low	~10 min	REST API only - tests backend agents
static-landing-page.md	Low	~5 min	HTML/CSS only - tests frontend/marketing
full-stack-demo.md	Medium	~30-60 min	Complete bookmark manager - full test

# Example: Test with simple todo app
claude --dangerously-skip-permissions
> Hiday with PRD at examples/simple-todo-app.md

Running Tests

The skill includes a comprehensive test suite:

# Run all tests
./tests/run-all-tests.sh

# Run individual test suites
./tests/test-bootstrap.sh        # Directory structure, state init
./tests/test-task-queue.sh       # Queue operations, priorities
./tests/test-circuit-breaker.sh  # Failure handling, recovery
./tests/test-agent-timeout.sh    # Timeout, stuck process handling
./tests/test-state-recovery.sh   # Checkpoints, recovery

Requirements

• Claude Code with --dangerously-skip-permissions flag
• Internet access for competitive research and deployment
• Cloud provider credentials (for deployment phase)
• Python 3 (for test suite)

Comparison

Feature	Basic Skills	Hiday
Agents	1	37
Swarms	-	6
Code Review	Manual	Parallel 3-reviewer
Deployment	None	Multi-cloud
Business Ops	None	Full stack
State Recovery	None	Checkpoint/resume
Alerting	None	Slack/PagerDuty

Integrations

Vibe Kanban (Visual Dashboard)

Optionally integrate with Vibe Kanban for a visual kanban board to monitor Hiday's agents:

# Install Vibe Kanban
npx vibe-kanban

# Export Hiday tasks to Vibe Kanban
./scripts/export-to-vibe-kanban.sh

Benefits:

• Visual progress tracking of all 37 agents
• Manual intervention/prioritization when needed
• Code review with visual diffs
• Multi-project dashboard

See integrations/vibe-kanban.md for full setup guide.

Contributing

Contributions welcome! Please read the skill and open issues for bugs or feature requests.

License

MIT License - see LICENSE for details.

Acknowledgments

• Inspired by LerianStudio/ring subagent-driven-development pattern
• Built for the Claude Code ecosystem

---

Keywords: claude-code, claude-skills, ai-agents, autonomous-development, multi-agent-system, sdlc-automation, startup-automation, devops, mlops, deployment-automation