SKILLEMALL.ai

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".

ClawHub Agent Skills author: Didac v1.4.0 MIT-0 65 files body ≈ 13 127 tokens Open the sourceclawhub.ai analyzed 4 d ago

As a process B 73/100 · Nearly there — weak spots: consistency, execution cost

ProcedureGitHubZapierData and analyticsAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
A
92/100
safety, quality, tests
Safety 60%
99
Quality 40%
82
Run on models
none yet
Process rating
B
73/100
Nearly there
Consistency w 8
40
Execution cost w 6
40
Tools and files w 18
60
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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
  • low Risky intent intent-offensive-security SKILL.md:97
    Offensive-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-long SKILL.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.

External checks

ClawHub: suspicious
This optimization skill is not clearly malicious, but it ships conflicting active instructions that can drive long-running file-changing loops with too little user control.
LLM: suspicious (high) · VirusTotal: · 29 May 2026