Menu
Pointers for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/TheAdaply/re-forge --skill unslothThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Showing SKILL.md
Correlation-to-causation discipline for any "does X cause Y", "what is the effect of X", or "should we do X" question. Use when a decision rests on a causal claim drawn from observational data, an A/B test, an event study, or a regression with controls — before reporting any effect as causal. Enforces draw-the-DAG-first, identification-before-estimation, the design hierarchy (RCT > natural experiment > diff-in-diff > IV > controls), A/B-test pitfalls, and unmeasured-confounder sensitivity analysis.
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
Use this skill for long-horizon agentic coding where a feature spans many turns and the agent drifts: it freezes a re-readable contract before code. Writes EARS-style requirements -> design -> task breakdown -> verification evidence, one feature directory per feature, with status gates and grep-able traceability IDs. Triggers on 'spec this out', 'write a spec', 'spec-driven', 'requirements then design', or planning a multi-session build.
Based on SOC occupation classification
| name | unsloth |
| description | Pointers for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization |
| version | 1.0.0 |
| author | Orchestra Research |
| license | MIT |
| tags | ["Fine-Tuning","Unsloth","Fast Training","LoRA","QLoRA","Memory-Efficient","Optimization","Llama","Mistral","Gemma","Qwen"] |
| dependencies | ["unsloth","torch","transformers","trl","datasets","peft"] |
Unsloth provides 2-5x faster fine-tuning with 50-80% less memory for LoRA/QLoRA on models like Llama, Mistral, Gemma, and Qwen.
This skill should be triggered when: