Machine learning

The methods a financial-ML result has to survive before it is evidence — purged cross-validation with an embargo, triple-barrier labelling, sample uniqueness…

Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts.

Automatically translate and sync App Store metadata (description, keywords, what's new, subtitle) to multiple languages using LLM translation and asc CLI.

Add Weave tracing to Python or TypeScript agents and LLM applications.

OpenLoomi entrypoint for skill-only agent runtimes without a plugin mechanism.

OpenLoomi runtime integration for Claude Code.

openloomi HTTP API reference (local-first, served from the OpenLoomi Desktop app at http://localhost:3414).

Eval-driven skill tuning.

Local scVI/scANVI-based single-cell latent embedding and batch-aware integration from raw-count .h5ad or 10x Matrix Market input, with stable integrated…

Standardized cost-estimation framework for great_cto plans.

End-to-end ML phylogenetic tree inference — MSA, trimming, ModelFinder, IQ-TREE2/RAxML-NG.

Create and manage Elastic ML anomaly detection jobs via the API.

Explain Elasticsearch ML anomaly detection scores, model behavior, and result interpretation.

Elastic ML anomaly detection — investigation/RCA, score explanation, job lifecycle troubleshooting, and job operations.

This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration, evaluator bias…

Offensive AI security testing and exploitation framework.

Query and report on API usage costs across LLM, embedding, and tool providers

Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA.

Track and visualize ML training experiments with Trackio.

AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU.

Use Netlify AI Gateway to call OpenAI, Anthropic Claude, Google Gemini, TypeSafe (Jev), or OpenRouter-hosted models (xAI/DeepSeek/Meta/Mistral/Qwen) from…

Suede AI eval design and coverage audit: AI-SPEC, failure-mode rubric with severity scoring, concrete pass/fail eval cases, coverage and infrastructure…

Suede AI code review and A-F ship grade for a diff, PR, branch, or commit range: findings ranked P0-P3 with file:line evidence and a fix path, an A-F grade…

Suede AI competitive-intelligence discipline: evidence-backed profiles of positioning, pricing, messaging, product, proof, reviews, organic search footprint…