SKILLEMALL.ai

AB autoresearch

Autonomous AI research skill for running automated neural network experiments. This skill should be used when the user wants to set up autonomous AI research experiments, run automated neural network training, conduct autonomous machine learning research, or let AI agents experiment with model architectures and hyperparameters. Based on Andrej Karpathy's autoresearch project, this skill enables AI agents to autonomously modify training code, run experiments, evaluate results, and iteratively improve models. Use when: (1) Setting up autonomous research experiments, (2) Running automated neural network training, (3) Conducting AI-driven research optimization, (4) Experimenting with model architectures and hyperparameters, (5) Implementing autonomous research loops, or (6) When the user mentions "autonomous research", "AI experiments", "automated training", "neural network optimization", or "autoresearch".

ClawHub Agent Skills author: baiyunrei2025 v1.0.0 MIT-0 7 files body ≈ 1 474 tokens Open the sourceclawhub.ai analyzed 4 d ago

As a process B 73/100 · Nearly there — weak spots: consistency, running it twice

AnalyzerAI and agentsSoftware developmentInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
A
93/100
safety, quality, tests
Safety 60%
95
Quality 40%
89
Run on models
none yet
Process rating
B
73/100
Nearly there
Running it twice w 4
30
Consistency w 8
40
Tools and files w 18
60
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • 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
    • medium Dangerous commands cmd-pipe-to-shell-known-host README.md:28
      Pipe-to-shell installer from a well-known host (still executes remote code)
      curl -LsSf https://astral.sh/uv/install.sh | sh

    Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 73/100

    • 30Running it twice. 1 mutating operations with no state check
    • 40Consistency. Frontmatter name (autoresearch) differs from the folder (autoresearch-karpathy)
    • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 70When it triggers. States when to use, but not when not to
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 54 steps
    • 100Failures and branches. 2 branches, has a failure section
    • 100Execution cost. Instruction body is 1474 tokens
    • 100Progress reporting. Reports progress
    • low 15 top-level sections: this looks like several domains in one skill

    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

    • +4Description does not say when NOT to use the skill (false activations)
    • +3Description length 916: 120–800 characters recommended
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 5 example trigger phrases
    • +4Structure: 23 headings
    • +3Step-by-step instructions: 54 items
    • +3Output format is stated explicitly
    • +4Has examples (8 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.

    External checks

    ClawHub: suspicious
    This skill is aligned with autonomous ML experimentation, but it should be reviewed because it tells the agent to keep editing code and running GPU jobs indefinitely unless stopped.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026