{"id":"b0ed5280-3676-4518-b393-2be10ec056cd","slug":"small-datacenter-airflow-thermal-optimization-agent-skill","kind":"skill","name":"small-datacenter-airflow-thermal-optimization-agent-skill","summary":"🌡️❄️ Small Data Center Airflow & Thermal Engineering Engine | Production-grade Claude Code harness & Python package (dc_thermal v2.0.0) for small data centers & edge server rooms. Features ASHRAE TC","owner":"dungnotnull","repoUrl":"https://github.com/dungnotnull/small-datacenter-airflow-thermal-optimization-agent-skill","license":"MIT","licenseTier":"permissive","trust":"community","stars":5,"match":null,"fewStars":false,"format":"skill","createdAt":"2026-07-29T08:32:47.000Z","addedAt":"2026-10-21T23:34:00.206Z","logoUrl":"https://avatars.githubusercontent.com/u/97343840?u=4935f461507df6e7decb7b35473e8cd9f8aff38b&v=4","linkOnly":false,"collection":null,"skillPath":null,"categories":["developer-tools","data-analytics","cloud-infra"],"tags":[],"runtime":"python","local":true,"cloudCapable":false,"cloudCapability":"unknown","cloudReadyOnPlatform":false,"needsApiKey":false,"reviewed":false,"syncedAt":"2026-10-25T17:07:08.227Z","sample":false,"url":"https://conduits.dev/tools/small-datacenter-airflow-thermal-optimization-agent-skill","language":"Python","transports":["stdio"],"install":{"pypi":"small-datacenter-airflow-thermal-optimization"},"requirements":{"env":[],"upstreamMayCharge":false},"tools":null,"readme":"# small-datacenter-airflow-thermal-optimization\n\n**Airflow & Temperature Optimization for Small Data Centers**\n\n[![Claude Skill](https://img.shields.io/badge/Claude-Skill-blue)](https://claude.ai/claude-code)\n[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)\n[![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org/downloads/)\n\nA professional-grade Claude Code harness for **Small Data Center Cooling & Airflow Engineering** — gathers real-time authoritative data, applies recognized domain methods (ASHRAE TC 9.9, hot/cold-aisle containment, PUE optimization, CFD/hotspot detection, cooling sizing, free cooling), integrates academic research, and delivers evidence-backed, risk-disclosed outputs.\n\n\n## Architecture Upgrade (v2.0.0)\n\nv2.0.0 upgrades this skill to a bulletproof, production-grade, open-source standard:\n\n- **`dc_thermal/` flexible architecture package** @EM@ skill registry, chain-of-thought\n  router, lifecycle hooks (logging/trace/state-sync), rich tool definitions with JSON\n  schemas, token-budgeted context window, pluggable LLM backends (stub/anthropic),\n  and the same 10 quality gates (U1@EM@U6 + G1@EM@G4).\n- **Modular directories:** `/scripts` (automation), `/references` (domain knowledge +\n  prompt templates), `/assets` (JSON schemas + diagrams + glossary), `/config`\n  (type-safe settings, env > file > defaults).\n- **`SKILL.md`** @EM@ canonical skill-registry documentation (register / resolve /\n  execute / validate + I/O JSON schemas).\n- **Full Unicode/Vietnamese remediation** @EM@ every mojibake literal `?` replaced\n  with the correct character; Vietnamese labels, language table, and Idea paragraph\n  reconstructed with precomposed Unicode.\n\n```python\nfrom dc_thermal import build_default\norch = build_default()\nrr = orch.run(\"Optimize airflow & PUE for a 20-rack, 200 kW small DC in Hanoi (A1)\")\nprint(rr.verdict, rr.gate_summary())   # Conditional (containment)  U1OK ... G4OK\n```\n\n```bash\npython -m dc_thermal.cli --query \"...\" --json --emit-trace\npython scripts/run_all_tests.py        # pytest + validators, combined exit code\n```\n\n## Overview\n\nSmall Data Center Cooling & Airflow Engineering practitioners face fragmented data (ASHRAE, Green Grid, TIA/Uptime, vendors, journals), inconsistent methodology (setpoints without class validation, PUE claims without a metering basis, hotspots without CFD/SHI quantification), and tools that do not self-improve. This skill unifies authoritative real-time data, recognized domain methods, a continuously-updated academic knowledge base, an executable thermal engine, and an executable orchestrator into one evidence-backed, risk-disclosed workflow.\n\n<details>\n<summary><b>Features (click to expand)</b></summary>\n\n- Real-time data aggregation from authoritative Small Data Center Cooling & Airflow Engineering sources\n- Systematic domain analysis methods (ASHRAE TC 9.9 setpoints, hot/cold-aisle containment, PUE optimization, CFD/hotspot detection, cooling sizing, free cooling)\n- Executable thermal engine (`tools/thermal_analysis.py`) — ASHRAE lookup, PUE, cooling sizing, required airflow, SHI/RTI/RHI, inlet profile, free-cooling hours, setpoint validation\n- Executable 6-step orchestrator (`tools/harness.py`) — context management, sub-skill invocation, quality-gate enforcement, graceful degradation, language detection, output templating, pluggable LLM backend\n- Academic research integration with auto-updating knowledge base\n- Risk/limitation-disclosed outputs with best/base/worst scenario coverage\n- Self-improving knowledge pipeline (weekly academic + daily news crawl)\n- 10 quality gates (U1–U6 universal + G1–G4 domain) with auto-fix and 2-retry max\n- 5-level graceful degradation with explicit LIMITATION banners\n- Vietnamese/English language detection\n\n</details>\n\n## Why This Skill\n\nSmall Data Center Cooling & Airflow Engineering practitioners face fragmented data, inconsistent methodology, and tools\nthat do not self-improve. This skill unifies authoritative real-time data, recognized\ndomain methods, and a continuously-updated academic knowledge base into one\nevidence-backed, risk-disclosed workflow.\n\n## Installation\n\n```bash\npip install -r requirements.txt\n```\n\nInstall skill files to `~/.claude/skills/` or use via project `CLAUDE.md`.\n\n## Quick Start\n\n```bash\n# Validate the project against the 8-File Contract\npython tools/validate_project.py\n\n# Run all structural/content scenario checks\npython tools/run_test_scenarios.py\n\n# Run the unit-test suites\npython tools/test_thermal_analysis.py\npython tools/test_knowledge_updater.py\n\n# Dry-run the knowledge crawl (no network writes)\npython tools/knowledge_updater.py --dry-run\n\n# Run the executable harness orchestrator on a query (stub LLM backend by default)\npython tools/harness.py --query \"Optimize airflow & PUE for a 20-rack, 200 kW small DC in Hanoi (ASHRAE A1)\"\n```\n\n## Usage\n\nInvoke the skill in Claude Code:\n\n```\n/small-datacenter-airflow-thermal-optimization [your query]\n```\n\nAnalysis types supported:\n- **Full combined** — airflow + cooling/setpoints + CFD/hotspots + PUE + scenarios (default)\n- **Airflow** — hot/cold aisle, containment, blanking, required-rack-airflow\n- **Cooling & setpoints** — CRAC/CRAH/in-row/liquid sizing + ASHRAE TC 9.9 envelope\n- **PUE** — current/target PUE with levers + free-cooling hours\n- **CFD/hotspot** — inlet profile, SHI/RTI/RHI, hotspot remediation\n\n## Architecture\n\nHarness flow: **requirements — evidence — core analysis — knowledge — synthesis — quality gate**.\nAll numeric computations go through `tools/thermal_analysis.py`; the 6-step flow is provided as an executable orchestrator in `tools/harness.py`.\n\n```\nNNN-small-datacenter-airflow-thermal-optimization/\n├── CLAUDE.md                         # Identity card\n├── CHANGELOG.md                      # Version history\n├── CODE_OF_CONDUCT.md                # Contributor Covenant\n├── CONTRIBUTING.md                   # Contribution guide\n├── LICENSE                           # MIT\n├── PROJECT-detail.md                 # Full technical spec\n├── PROJECT-DEVELOPMENT-PHASE-TRACKING.md\n├── README.md\n├── SECOND-KNOWLEDGE-BRAIN.md         # Living knowledge base\n├── SECURITY.md                       # Security policy\n├── pyproject.toml                    # Python packaging & pytest config\n├── progression.json\n├── requirements.txt\n├── .editorconfig\n├── .gitignore\n├── .github/\n│   ├── workflows/ci.yml              # CI/CD pipeline\n│   ├── ISSUE_TEMPLATE/\n│   │   ├── bug_report.md\n│   │   ├── feature_request.md\n│   │   └── config.yml\n│   └── PULL_REQUEST_TEMPLATE.md\n├── skills/\n│   ├── main.md                       # Harness orchestrator + quality gates\n│   └── sub-*.md                      # 5 sub-skills\n├── tools/\n│   ├── __init__.py                   # Package init with __version__\n│   ├── knowledge_updater.py          # Crawl pipeline\n│   ├── thermal_analysis.py           # Domain thermal engine\n│   ├── harness.py                    # 6-step orchestrator\n│   ├── validate_project.py           # 8-File Contract validator\n│   ├── run_test_scenarios.py         # Structural & content validator\n│   ├── test_knowledge_updater.py     # Unit tests (crawl)\n│   └── test_thermal_analysis.py      # Unit tests (engine)\n├── tests/\n│   ├── __init__.py\n│   ├── conftest.py                   # Pytest configuration\n│   ├── test-scenarios.md\n│   ├── TEST_RESULTS.md\n│   ├── test_thermal_analysis_pytest.py\n│   ├── test_knowledge_updater_pytest.py\n│   └── test_harness_pytest.py\n└── logs/                             # Artifact directory (.gitignored)\n```\n\nSee `PROJECT-detail.md` for the full architecture diagram.\n\n## Quality Gates\n\nUniversal gates U1–U6 plus domain gates defined in `skills/main.md`:\n\n- **U1** ≥3 sources cited, ≥1 academic/authoritative\n- **U2** Disclosure/limitations before recommendation\n- **U3** Evidence hierarchy (Tier 1–4) per source\n- **U4** Language matches user preference\n- **U5** Declared template (all sections)\n- **U6** Every claim traceable or flagged\n- **G1** Airflow containment designed (hot/cold aisle, blanking, cable mgmt)\n- **G2** ASHRAE TC 9.9 setpoints for declared class (A1 recommended 18–27 °C, 40–60% RH; `validate_setpoint` PASS)\n- **G3** CFD hotspots/bypass/recirculation addressed (all top-of-rack inlets ≤ ASHRAE limit OR remediation stated)\n- **G4** PUE optimized; cooling —1.15–1.25—IT; redundancy N+1\n\n## Data Sources\n\n- ASHRAE TC 9.9 data center thermal guidelines\n- ASHRAE Handbook — HVAC Applications (Datacom)\n- The Green Grid — PUE / ERE / CUE references\n- TIA-942 / Uptime Institute Tier Standard\n- CFD for data centers references (6Sigma / Future Facilities)\n- UPS / power redundancy references\n- Applied Thermal Engineering, Int. J. Heat & Mass Transfer, Building and Environment, IEEE TCPMT, Sustainable Computing, Energy and Buildings\n\n## Testing\n\n```bash\npython tools/validate_project.py        # 8-File Contract\npython tools/run_test_scenarios.py      # scenarios + structure\npython tools/test_thermal_analysis.py  # thermal engine unit tests\npython tools/test_knowledge_updater.py # crawl pipeline unit tests\n```\n\nAll suites exit `0` on success.\n\n## Knowledge Base\n\n`SECOND-KNOWLEDGE-BRAIN.md` is auto-updated weekly via `tools/knowledge_updater.py`. Dedup is SHA256 of DOI/URL; scoring is a composite 0–10 of recency (0.4) + keyword relevance (0.4) + citation count (0.2). See `PROJECT-detail.md` for the crawl config and `CLAUDE.md` for the cron schedule.\n\n## Development\n\n```bash\n# Format/lint (recommended)\npython -m py_compile tools/*.py          # byte-compile sanity check\npython tools/test_thermal_analysis.py\npython tools/test_knowledge_updater.py\npython tools/validate_project.py\npython tools/run_test_scenarios.py\n```\n\nThe codebase targets Python 3.11+, uses the stdlib `logging` module, dataclasses for config, type hints throughout, and explicit exit codes. The thermal engine has **zero third-party runtime dependencies** (stdlib only) so it runs anywhere.\n\n## Roadmap\n\n- [x] Phase 0: Architecture\n- [x] Phase 1: Core sub-skills (5)\n- [x] Phase 2: Main harness + gates + degradation\n- [x] Phase 3: Knowledge pipeline\n- [x] Phase 4: Testing\n- [x] Phase 5: Integration & polish — PRODUCTION READY v2.0.0\n  - [x] Encoding audit (UTF-8 no-BOM)\n  - [x] Domain thermal engine (`tools/thermal_analysis.py`)\n  - [x] Executable harness orchestrator (`tools/harness.py`)\n  - [x] 8-File Contract validator (`tools/validate_project.py`)\n  - [x] LICENSE (MIT)\n\n## Contributing\n\nContributions are welcome. Please:\n1. Open an issue describing the change.\n2. Ensure `python tools/validate_project.py`, `tools/run_test_scenarios.py`, `tools/test_thermal_analysis.py`, and `tools/test_knowledge_updater.py` all pass.\n3. Add/expand unit tests for any new domain method.\n4. Keep all files UTF-8 no-BOM.\n\n## Acknowledgments\n\n- ASHRAE TC 9.9 — Thermal Guidelines for Data Processing Environments\n- The Green Grid — PUE / ERE / CUE metrics\n- TIA-942 / Uptime Institute — reliability topology\n- Academic venues: Applied Thermal Engineering, Int. J. Heat & Mass Transfer, Building and Environment, IEEE TCPMT, Sustainable Computing, Energy and Buildings\n\n## License\n\nMIT — see [LICENSE](LICENSE).\n\n## Citation\n\n```bibtex\n@software{small-datacenter-airflow-thermal-optimization,\n  title  = {small-datacenter-airflow-thermal-optimization: Airflow & Temperature Optimization for Small Data Centers},\n  year   = {2026},\n  version= {1.1.0}\n}\n```\n"}