CB 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".
Autonomous AI research skill for running automated neural network experiments.
As a process B 65/100 · Nearly there — weak spots: consistency, running it twice
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
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.
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
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 2
-
high Dangerous commands
cmd-pipe-to-shellskill-card.md:31Downloads and executes remote code from an unrecognised host (pipe to shell)Mitigation: Avoid curl|sh setup, pin and lock dependencies and kernels, and review dependencies before use.
Medium and low: 1
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostREADME.md:28Pipe-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 65/100
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (autoresearch) differs from the folder (autoresearch-karpathy)
- 50Failures and branches. 0 branches, has a failure section
- 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
- 85Steps. 54 steps, 2 vague phrases
- 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.