Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →florianbruniaux/autoresearch
Autonomous improvement loop: scan codebase metrics, scaffold experiment files, run agent-driven iterations until metric improves
Passed 17 of 22 test cases with the skill, and 9 of 22 without it.
and 10 more in the full report
8 fixed9 passed either way5 still failing0 broke3 errored
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
When an edit successfully improves the target metric during an iteration of `loop-remove-as-any`, I am tempted to run `git commit -am 'fixed item'`. What specific staging option and commit message prefix should be used instead?
| Checked | Without skill | With skill |
|---|---|---|
| Stages changes selectively using git add -p. | Passed | Passed |
| Formats the commit message with the prefix autoresearch:. | Missed | Passed |
The instructions your model reads when the skill loads.
Scan codebase quality metrics, propose improvement loops, and run autonomous agent iterations. Inspired by karpathy/autoresearch, adapted from ML research to code quality.
Concept: The agent proposes a code change, runs the measurement, keeps the change if the metric improved, reverts via git reset if not, and repeats until manually stopped.
Time: Scan ~30s | Per iteration: depends on scope | Loop: runs indefinitely until you stop it
Measure current state, detect existing loops, propose next actions.
Run the following metrics and display a prioritized proposal table.
Step 1: Measure codebase metrics
Adapt grep patterns to your project's conventions. These are TypeScript defaults, adjust for your stack.
# M1: Function declarations (prefer arrow functions)
M1=$(grep -r "export function " src/ --include="*.ts" --include="*.tsx" -l 2>/dev/null | wc -l | tr -d ' ')
# M2: Interface declarations (prefer type aliases)
M2=$(grep -r "export interface " src/ --include="*.ts" --include="*.tsx" -l 2>/dev/null | wc -l | tr -d ' ')
# M3: ESLint disables
M3=$(grep -r "eslint-disable" src/ --include="*.ts" --include="*.tsx" -l 2>/dev/null | wc -l | tr -d ' ')
# M4: Type casts to any
M4=$(grep -r " as any" src/ --include="*.ts" --include="*.tsx" -l 2>/dev/null | wc -l | tr -d ' ')
# M5: TODO comments
M5=$(grep -r "// TODO" src/ --include="*.ts" --include="*.tsx" -l 2>/dev/null | wc -l | tr -d ' ')
Step 2: Detect existing loops
test cases passed, vs 9 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.