{"name":"compute.md","version":"2.1","description":"A skill that makes AI agents careful compute buyers: size the work, set up the stack you want, get prices from your own providers, launch inside rules you set, tear everything down. Levers cover spend, stop rules, machines, storage, network, models, access, security and data. Optional API and MCP server to write limits, check plans and size models. No prices listed; the levers and plan checks name no providers.","skill":{"url":"https://compute.md/compute.md","sha256":"b2f755936cfd6bf17bef069901bcbab5a8c0a6560bfaa86f189f21ea0027f15f","format":"Agent Skills (SKILL.md frontmatter)","limits":"https://compute.md/compute.md?preset=web_app&budget_usd=100&memory_gb=8"},"levers":{"catalog":"https://compute.md/api/v1/levers","limits":"https://compute.md/api/v1/limits","presets":["core","recommended","locked","web_app","inference","gpu_job","data_pipeline","dev_box","static_site"]},"check":{"url":"https://compute.md/api/v1/check","method":"POST","body":"{limits?, limits_url?, plan}","schema":"https://compute.md/openapi.json"},"api":{"index":"https://compute.md/api/v1","openapi":"https://compute.md/openapi.json","endpoints":["GET https://compute.md/compute.md","GET https://compute.md/api/v1/levers","GET https://compute.md/api/v1/limits","POST https://compute.md/api/v1/check","GET https://compute.md/api/v1/fit","GET https://compute.md/api/v1/gpus","GET https://compute.md/api/v1/models"]},"mcp":{"url":"https://compute.md/mcp","transport":"Streamable HTTP (stateless, JSON responses, no auth)","tools":["fit_model","gpu_specs","model_spec","build_limits","check_plan"],"prompts":["compute (optional preset and lever arguments)"],"resources":["https://compute.md/compute.md","https://compute.md/api/v1/levers"]},"llms_txt":"https://compute.md/llms.txt","sources":[{"data":"Model sizes and architectures","name":"Public Hugging Face model repositories (model info, file sizes, config.json)","url":"https://huggingface.co","refresh":"read on request, cached for a day"},{"data":"Accelerator specs","name":"Vendor datasheets, collected by hand","url":"https://compute.md/api/v1/gpus","refresh":"by hand"},{"data":"Limits and plans","name":"Your own request: levers in the link or body, and the plan you describe","url":"https://compute.md/api/v1/levers","refresh":"used to answer that request only; never stored"}],"never":["books or bills compute","holds credentials","stores limits or plans","accepts payment"],"disclaimer":"Use at your own risk. compute.md is provided as is, without warranty. Information here may be inaccurate, incomplete or not current, and is not verified; sizing figures are estimates. Not financial, legal or procurement advice. Confirm everything with your providers before you rent or buy.","terms":"https://compute.md/terms","sibling_specs":["https://stablecoins.md/stablecoins.md","https://insurance.md/insurance.md","https://manage.md/manage.md"],"contact":"proofmdorg [ at ] gmail.com","license":"MIT"}