leeroo-ai
- 15 skills
- 0 followers
- 1 day ago last updated
- ▌ Kapso 2 · leeroo-aiOperate Kapso (PyPI leeroo-kapso), the self-improving AI software factory, from a coding session — verify the install with kapso doctor, launch and follow an evolve campaign toward a scored goal, answer a campaign that is WAITING ON YOU, resume an interrupted run, learn from a finished campaign into the lesson bank, ingest repos and research into the knowledge graph, and deploy the winner. Use when the user mentions Kapso or kapso evolve, learn, research, deploy, doctor, watch, inbox, bank, or asks to push a measurable metric (accuracy, latency, score) in a project where kapso is installed. Do not use for ordinary code edits, or for hand-tuning a metric when Kapso is neither installed nor asked for.
- ▌ Kapso 3 · leeroo-ai bundleOptimize code using KAPSO (Knowledge-Grounded Optimization). Use when you need to write, optimize, or fix code. Connects to a local KAPSO server that iteratively improves solutions through experimentation.
- ▌ Kapso · leeroo-ai bundleOperate Kapso (PyPI leeroo-kapso), the self-improving AI software factory, from a coding session — verify the install with kapso doctor, launch and follow an evolve campaign toward a scored goal, answer a campaign that is WAITING ON YOU, resume an interrupted run, learn from a finished campaign into the lesson bank, ingest repos and research into the knowledge graph, and deploy the winner. Use when the user mentions Kapso or kapso evolve, learn, research, deploy, doctor, watch, inbox, bank, or asks to push a measurable metric (accuracy, latency, score) in a project where kapso is installed. Do not use for ordinary code edits, or for hand-tuning a metric when Kapso is neither installed nor asked for.
- ▌ Leeroopedia MCP · leeroo-ai bundleUse Leeroopedia MCP to fetch grounded ML/AI best practices, build and review ML plans, debug failures, verify code/math correctness, and expand KB citations via get_page.
- ▌
- ▌
- ▌
- ▌
- ▌ Ml Plan · leeroo-aiUse when the user wants an implementation plan, architecture design, or multi-step ML pipeline — "build X", "implement X", "design X", "set up X"
- ▌ Ml Debug · leeroo-aiUse when something is failing in ML/AI work — OOM, NaN, divergence, crashes, bad throughput, wrong outputs, dependency conflicts
- ▌ Ml Verify · leeroo-aiUse when the user wants to verify code, config, or math before running — or proactively before any expensive training job or deployment
- ▌ Ml Iterate · leeroo-aiUse when the user is stuck, needs ranked next steps, or wants alternatives after initial experiments — "I tried X and got Y, what next?"
- ▌ Ml Research · leeroo-aiUse when the user wants to understand an ML/AI topic, compare approaches, or survey framework capabilities — "how does X work?", "compare X vs Y"
- ▌ Ml Experiment · leeroo-aiUse when starting, logging, or reviewing ML experiments — maintains a persistent experiment journal with hypotheses, results, and learnings across sessions
- ▌ Using Superml · leeroo-aiUse when starting any conversation involving ML/AI — establishes how to use Leeroopedia KB tools and workflow skills