Home Spirulina Farming System

Home Spirulina Farming System — Skill Registry

Overview

This document serves as the comprehensive skill registry for the home-spirulina-farming-system Claude Code skill. It provides complete documentation for skill registration, resolution, execution, and validation, including input/output JSON schemas for all components.

Skill Identity

• Name: home-spirulina-farming-system
• Version: 1.0.0
• Category: Domain-Specific Analysis / Agriculture / Biotechnology
• Phase: Production Ready
• Last Updated: 2026-07-15

Skill Architecture

Modular Directory Structure

279-home-spirulina-farming-system/
├── config/                    # Configuration management
│   ├── __init__.py
│   ├── schemas.py             # Type-safe configuration schemas
│   └── config_manager.py      # Environment variable management
├── lib/                       # Core library modules
│   ├── __init__.py
│   ├── logging_system.py      # Structured logging
│   ├── error_handler.py       # Error handling & recovery
│   ├── token_tracker.py       # Token consumption tracking
│   └── context_manager.py     # Context window optimization
├── hooks/                     # Lifecycle management
│   ├── __init__.py
│   ├── lifecycle_hooks.py     # Step execution hooks
│   ├── state_sync.py          # State synchronization
│   └── event_emitter.py       # Event management
├── tools/                     # Tool definitions
│   ├── __init__.py
│   ├── tool_registry.py       # Tool registration & execution
│   ├── tools_factory.py       # Predefined tools
│   ├── knowledge_updater.py   # Knowledge crawl pipeline
│   └── test_knowledge_updater.py
├── skills/                    # Sub-skill definitions
│   ├── main.md                # Main harness orchestrator
│   ├── sub-gather-requirements.md
│   ├── sub-evidence-collector.md
│   ├── sub-core-analysis.md
│   ├── sub-knowledge-updater.md
│   └── sub-advisor.md
├── references/                # Domain knowledge templates
│   ├── domain_concepts.md
│   ├── evidence_hierarchy.md
│   └── output_templates.md
├── assets/                    # Static resources
│   ├── diagrams/
│   └── schemas/
├── scripts/                   # Automation scripts
│   ├── setup.sh
│   └── validate.sh
├── tests/                     # Test scenarios
│   ├── test-scenarios.md
│   └── TEST_RESULTS.md
├── SECOND-KNOWLEDGE-BRAIN.md  # Living knowledge base
├── CLAUDE.md                  # Project instructions
├── PROJECT-detail.md          # Technical specification
├── PROJECT-DEVELOPMENT-PHASE-TRACKING.md
├── README.md
├── requirements.txt
├── .gitignore
└── SKILL.md                   # This file

Skill Registration

Main Skill Registration

The main skill is registered in skills/main.md with the following frontmatter:

---
name: home-spirulina-farming-system
description: Home Spirulina Farming System Design & Operation
---

Sub-Skill Registration

Each sub-skill is registered with its own frontmatter:

| Sub-Skill | Purpose | Trigger Condition | |-----------|---------|-------------------| | sub-gather-requirements | Clarify analysis scope | Step 1 of harness | | sub-evidence-collector | Fetch authoritative data | Step 2 of harness | | sub-core-analysis | Domain analysis | Step 3 of harness | | sub-knowledge-updater | Query knowledge base | Step 4 of harness | | sub-advisor | Synthesize recommendations | Step 5 of harness |

Skill Resolution

Resolution Order

1. Direct invocation: /home-spirulina-farming-system [query]
2. Pattern matching: User message contains spirulina/farming keywords
3. Context detection: User discusses algae cultivation
4. Manual trigger: User explicitly requests analysis

Resolution Parameters

{
  "skill_name": "home-spirulina-farming-system",
  "resolution": {
    "method": "pattern_match",
    "confidence": 0.95,
    "matched_keywords": ["spirulina", "farming", "cultivation"],
    "context": "home_scale_agriculture"
  }
}

Skill Execution

Execution Protocol

The skill follows a 6-step execution protocol:

1. Pre-Flight: Language detection
2. Step 1: sub-gather-requirements → Structured requirements
3. Step 2: sub-evidence-collector → Evidence bundle
4. Step 3: sub-core-analysis → Domain analysis
5. Step 4: sub-knowledge-updater → Academic evidence
6. Step 5: sub-advisor → Final recommendations
7. Quality Gate: Verify all gates passed

Input/Output Schemas

Main Skill Input Schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "User's analysis request"
    },
    "language": {
      "type": "string",
      "enum": ["en", "vi"],
      "default": "en"
    },
    "context": {
      "type": "object",
      "description": "Additional context or inputs"
    }
  },
  "required": ["query"]
}

Main Skill Output Schema

{
  "type": "object",
  "properties": {
    "report": {
      "type": "string",
      "description": "Formatted analysis report"
    },
    "verdict": {
      "type": "string",
      "enum": ["optimal", "conditional", "toxin_risk", "inconclusive"],
      "description": "Analysis verdict category"
    },
    "confidence": {
      "type": "number",
      "minimum": 0,
      "maximum": 1,
      "description": "Confidence score"
    },
    "evidence_count": {
      "type": "integer",
      "description": "Number of sources cited"
    },
    "gates_passed": {
      "type": "array",
      "items": {"type": "string"},
      "description": "Quality gates that passed"
    },
    "warnings": {
      "type": "array",
      "items": {"type": "string"},
      "description": "Warnings or limitations"
    }
  },
  "required": ["report", "verdict"]
}

Sub-Skill Input/Output Schemas

sub-gather-requirements

Input:

{
  "type": "object",
  "properties": {
    "user_message": {"type": "string"},
    "provided_inputs": {"type": "object"}
  }
}

Output:

{
  "type": "object",
  "properties": {
    "object": {"type": "string"},
    "scope": {"type": "string"},
    "timeframe": {"type": "string"},
    "available_inputs": {"type": "object"},
    "target_audience": {"type": "string"},
    "language": {"type": "string"},
    "analysis_type": {"type": "string"}
  },
  "required": ["object"]
}

sub-evidence-collector

Input:

{
  "type": "object",
  "properties": {
    "requirements": {"$ref": "#/definitions/sub-gather-requirements-output"}
  }
}

Output:

{
  "type": "object",
  "properties": {
    "current_data": {"type": "object"},
    "authoritative_docs": {"type": "array"},
    "recent_news": {"type": "array"},
    "reference_benchmarks": {"type": "array"}
  }
}

sub-core-analysis

Input:

{
  "type": "object",
  "properties": {
    "setup": {"type": "string"},
    "strain": {"type": "string"},
    "space": {"type": "string"},
    "light": {"type": "string"},
    "language": {"type": "string"}
  }
}

Output:

{
  "type": "object",
  "properties": {
    "medium": {"type": "object"},
    "light_T_agitation": {"type": "object"},
    "growth": {"type": "object"},
    "harvest_drying": {"type": "object"},
    "contamination": {"type": "object"},
    "scenarios": {"type": "object"}
  }
}

sub-knowledge-updater

Input:

{
  "type": "object",
  "properties": {
    "keywords": {"type": "array", "items": {"type": "string"}}
  }
}

Output:

{
  "type": "object",
  "properties": {
    "citations": {"type": "array"},
    "tier_labels": {"type": "object"},
    "coverage_rating": {"type": "string"},
    "flagged_gaps": {"type": "array"}
  }
}

sub-advisor

Input:

{
  "type": "object",
  "properties": {
    "core_analysis": {"type": "object"},
    "evidence_bundle": {"type": "object"},
    "knowledge_evidence": {"type": "object"}
  }
}

Output:

{
  "type": "object",
  "properties": {
    "conclusion": {"type": "string"},
    "scenarios": {"type": "object"},
    "key_risks": {"type": "array"},
    "evidence_chain": {"type": "array"},
    "remediation": {"type": "array"},
    "disclosure": {"type": "string"}
  }
}

Quality Gates

Universal Gates (U1-U6)

| Gate | Check | Auto-Fix | Enforcement | |------|-------|----------|------------| | U1 | ≥3 sources, ≥1 academic | Fetch from KB | Append before delivery | | U2 | Disclosure before recommendation | Prepend disclosure | Block until present | | U3 | Evidence hierarchy per source | Tag sources | Mark each source | | U4 | Language matches preference | Translate output | Run detection | | U5 | Output template complete | Reformat | Check sections | | U6 | Claims traceable | Flag unsupported | Mark claims |

Domain Gates (G1-G4)

| Gate | Check | Auto-Fix | Enforcement | |------|-------|----------|------------| | G1 | Medium (Zarrouk/pH) set | Set medium | Configure medium | | G2 | Light/T/agitation configured | Configure light/T | Set parameters | | G3 | Contamination/toxin control | Add control | Implement checks | | G4 | Harvest/food safety | Add safety | Add procedures |

Validation

Skill Validation

The skill is validated using the 8-File Contract:

1. ✅ CLAUDE.md — Skill identity card
2. ✅ PROJECT-detail.md — Technical specification
3. ✅ PROJECT-DEVELOPMENT-PHASE-TRACKING.md — Build roadmap
4. ✅ README.md — Public documentation
5. ✅ skills/main.md — Main harness
6. ✅ skills/sub-*.md — Sub-skills
7. ✅ SECOND-KNOWLEDGE-BRAIN.md — Knowledge base
8. ✅ tools/knowledge_updater.py — Crawl pipeline

Execution Validation

• [ ] All steps complete in order
• [ ] Quality gates pass
• [ ] Output template complete
• [ ] Evidence hierarchy respected
• [ ] Language detection working
• [ ] Graceful degradation functional

Tool Integration

Available Tools

• WebSearch — Live domain data
• WebFetch — Scrape authoritative sources
• Read/Write — File operations
• Bash — Command execution
• Skill — Sub-skill invocation

Tool Registry

Tools are registered in tools/tool_registry.py with schema validation and execution tracking.

Configuration

Environment Variables

ENVIRONMENT=production
MODEL_PROVIDER=anthropic
MODEL_NAME=claude-sonnet-4-20250514
MODEL_TEMPERATURE=0.7
LOG_LEVEL=INFO
FEATURE_ENABLE_CRAWL=true
FEATURE_ENABLE_CACHE=true

Configuration Schema

See config/schemas.py for complete configuration schema definition.

Hooks & Events

Lifecycle Hooks

• before_step — Before step execution
• after_step — After step completion
• on_error — On error occurrence
• on_completion — On harness completion
• on_validation — On quality gate validation

Event Types

• step_start — Step execution started
• step_complete — Step execution completed
• step_error — Step execution failed
• data_fetched — Data fetched successfully
• analysis_complete — Analysis completed
• report_generated — Report generated
• error_occurred — Error occurred
• warning_issued — Warning issued

Knowledge Pipeline

Crawl Schedule

• Weekly Academic: Mondays 08:00
• Daily News: Daily 07:00

Knowledge Config

Located in tools/knowledge_updater.py:

KNOWLEDGE_CONFIG = {
    "domain": "Home-Scale Microalgae (Spirulina) Cultivation",
    "keywords": [...],
    "arxiv_categories": [],
    "rss_feeds": [],
    "authoritative_docs": [...],
}

Error Handling

Error Categories

• Network
• Data Source
• Validation
• Processing
• Authentication
• Rate Limit
• Dependency
• Internal

Recovery Strategies

Each error category has a recovery strategy with retry logic, exponential backoff, and fallback handlers.

Performance Monitoring

Token Tracking

• Input tokens per operation
• Output tokens per operation
• Total consumption tracking
• Cost estimation
• Optimization suggestions

Context Management

• Current usage percentage
• Compression threshold
• Truncate strategy
• Section preservation

Logging

• Structured JSON logging
• Correlation ID tracking
• Log level configuration
• File rotation
• Performance metrics

Integration Points

MCP Servers

• CodeGraph — Code intelligence
• Context7 — Documentation queries
• Supabase — Database operations

External APIs

• ArXiv API
• Semantic Scholar API
• RSS feeds

Testing

Test Scenarios

Located in tests/test-scenarios.md:

1. Standard analysis
2. Minimal input
3. Comparison case
4. Risk/conflict case
5. Degraded mode

Test Execution

python tools/test_knowledge_updater.py
python tools/run_test_scenarios.py --all

Maintenance

Knowledge Updates

python tools/knowledge_updater.py
python tools/knowledge_updater.py --dry-run
python tools/knowledge_updater.py --news-only

Configuration Updates

# Edit .env file
vim .env

# Reload configuration
python -c "from config import reload_config; reload_config()"

License

MIT License — see LICENSE file.

Citation

@software{home-spirulina-farming-system,
  title = {home-spirulina-farming-system: Home Spirulina Farming System Design & Operation},
  author = {Claude Code},
  year = {2026},
  version = {1.0.0},
  url = {https://github.com/972026/279-home-spirulina-farming-system}
}

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: dungnotnull
• Source: dungnotnull/home-spirulina-farming-system-agent-skill
• License: MIT

Install and usage instructions live in the source repository linked above.