AB autoresearch-loop
Apply Karpathy's autoresearch methodology to iteratively improve anything measurable — Claude skills, n8n workflows, system prompts, business processes, or any artifact with a clear quality metric. Inspired by github.com/karpathy/autoresearch (56k stars). The loop: propose a change → test it → measure against the target metric → keep if better, discard if not → repeat until a stopping condition is met. Trigger this skill when the user explicitly requests an iterative improvement loop, e.g.: "improve this skill automatically", "iterate on this workflow", "run autoresearch on", "run experiments on this", "optimize this automatically", "set up an improvement loop", or "run the autoresearch method".
As a process B 73/100 · Nearly there — weak spots: consistency, execution cost
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
-
low Risky intent
intent-offensive-securitySKILL.md:97Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)**Eval quality and designer bias** — if every new artifact hits 100% within 2–3 sessions, your evals are probably too easy. The risk is amplified when the same person designs the eval and runs the loo
quoted
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 13127 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 73/100
- 40Consistency. Frontmatter name (autoresearch-loop) differs from the folder (as-autoresearch-loop)
- 40Execution cost. Instruction body is 13127 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (git, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 85 steps, 2 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 48 branches, has a failure section
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 704: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 85 items
- +3Output format is stated explicitly
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.