SKILLEMALL.ai
GitHub ↗ RU Sign in

BC unsloth

Install, operate, and troubleshoot Unsloth Core, Studio, and Desktop for local inference and model training. Use for Unsloth environment setup, LoRA/QLoRA supervised fine-tuning, coding specialization, verifier audits, chat templates, GRPO and preference training, vision and audio workflows, decision models, local coding agents and tools, dynamic quantization, checkpoint recovery, multi-GPU training, and model export to GGUF or serving engines. Do not use for framework-neutral ML strategy or operating a standalone inference server unrelated to Unsloth.

magnus919/agent-skills Agent Skills author: magnus919 MIT 38 files · 12 scripts body ≈ 3 132 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Install, operate, and troubleshoot Unsloth Core, Studio, and Desktop for local inference and model training.

As a process C 55/100 · Has gaps — References files that are not bundled: scripts/gpu_completion.cpp, assets/train.jsonl, assets/heldout.jsonl

ProcedureDockerSoftware developmentAI and agentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
91/100
safety, quality, tests
Safety 60%
99
Quality 40%
78
Run on models
none yet
Process rating
C
55/100
Has gaps
References files that are not bundled: scripts/gpu_completion.cpp, assets/train.jsonl, assets/heldout.jsonl
Tools and files w 18
0
Progress reporting w 2
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 1

✓ No critical or high findings

Medium and low: 1
  • low Dangerous commands cmd-autorun-instruction references/installation.md:48
    Instructs the agent to auto-run a script on every session (documentation of a security skill)
    First run `scripts/unsloth_preflight.py doctor --json` inside the environment.
    security skill

Files scanned: 35. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: scripts/gpu_completion.cpp
  • warning missing-ref reference to a missing file: assets/train.jsonl
  • warning missing-ref reference to a missing file: assets/heldout.jsonl
  • warning missing-ref reference to a missing file: assets/requirements-gpuslut01.lock

Process rating: all ten parameters 55/100

Will not run. References files that are not bundled: scripts/gpu_completion.cpp, assets/train.jsonl, assets/heldout.jsonl
  • 0Tools and files. 4 referenced file(s) missing: scripts/gpu_completion.cpp, assets/train.jsonl, assets/heldout.jsonl
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 3 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 50When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 20 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3132 tokens
  • low 10 top-level sections: this looks like several domains in one skill
  • low No test case covers injection arriving through data

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +3Output format is not stated: the model decides each time
  • -36 of 12 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 558: enough signal without eating the budget
  • +4Structure: 11 headings
  • +3Step-by-step instructions: 20 items
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (15 of 15)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.