Finetuning
ericrisco/rsc-harnessUse when adapting an open-weight model to a target form or behavior — tone, output format, reasoning pattern — via LoRA/QLoRA or full fine-tuning with TRL SFTTrainer, then preference optimization (DPO/ORPO/KTO/GRPO), and for fine-tune vs prompt vs RAG. NOT adding facts to a model (that is rag); NOT the single-GPU Unsloth backend or GGUF export (that is unsloth).
At a glance
This skill is for Coding and helps you fine-tune an open-weight model with lora, adapt a model's tone or output format, and optimize model preferences with dpo.
git clone --depth 1 https://github.com/ericrisco/rsc-harness
cp -r rsc-harness/skills/finetuning ~/.claude/skills/finetuning
Setup, runtime and requirements describe ericrisco/rsc-harness, the repo this skill ships in.
LoraQroradpoOrpoModel AdaptationTrl
Also in ericrisco/rsc-harness
View the repoUse when designing or analyzing a controlled experiment — falsifiable hypothesis, sample size from an MDE, reading significance/CI/power, CU...
Use when making a web UI conform to WCAG 2.2 Level AA — axe-core or Lighthouse a11y violations, keyboard operability, focus management, ARIA...
Use when running or fixing paid acquisition on Google or Meta — campaign structure (Performance Max, Demand Gen, Search, Advantage+), platfo...
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge,...
Use when bounding an LLM agent that already runs — scoping its task domain, gating tools to least privilege, defending against prompt inject...
Use when a creative goal must become a finished media file: pick and order generative-media models per modality — AI voiceover, image-to-vid...
Use when instrumenting product or web analytics — GA4/PostHog SDK wiring, event taxonomy, funnels, double-counted events, consent gating, PI...
Use when constitution, spec, plan and tasks all exist and you want them cross-read against each other before any code is written — the rsc-s...
Use when building, refactoring, or debugging Angular (v20/21+): standalone components, signals, zoneless change detection, @if/@for/@defer c...
Use when writing a client for someone else's REST or GraphQL API: auth flow choice and token refresh, pagination to exhaustion, retry-with-j...
Use when settling the contract of an API you expose, before implementation: resources/URLs, REST vs GraphQL, versioning, one RFC 9457 error...
Use when writing one long-form article end to end — answer-first lede, question-shaped headings, plus its on-page surface (title, meta, slug...
Other Coding skills
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make...
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI be...
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-design...
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model...
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS,...
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.