agentsclimarketplace

Autoresearch

Skill YousefNabil-SOC/claude-apex/skills/autoresearch

Public mirror + teaching install of my Claude Code environment: 1,276 skills, 185 agents, 235 commands, 8 wired MCP servers, three-layer auto-routing (10 CARL domains). Curated original core + the open plugin/marketplace ecosystem, all credited. MIT.

Install
npx -y skills add YousefNabil-SOC/claude-apex --skill autoresearch

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Autonomous goal-directed iteration. Define a goal with a measurable metric, then modify-measure-keep/discard-repeat until the goal is met.

SKILL.md

1.6 KB, as published. Nobody here has run it

Autoresearch — Autonomous Optimization

Inspired by iterative research methodology. Apply to ANY task with a measurable metric.

Core Loop

1. Define GOAL (what you want to achieve)
2. Define METRIC (how you measure success)
3. Define DIRECTION (higher is better / lower is better)
4. Define VERIFY (how to check the metric)

REPEAT:
  a. Make ONE modification
  b. Measure the metric
  c. If improved: KEEP the change
  d. If worsened: DISCARD (revert)
  e. Log the attempt and result
  f. Choose next modification
UNTIL: goal is met OR no more improvements found

Example Applications

Performance optimization

  • Goal: Page load under 2 seconds
  • Metric: Lighthouse performance score
  • Direction: Higher is better
  • Verify: Run Lighthouse audit

Bundle size reduction

  • Goal: Main bundle under 200KB
  • Metric: Bundle size in KB
  • Direction: Lower is better
  • Verify: Run build and check output

Test coverage

  • Goal: 80%+ code coverage
  • Metric: Coverage percentage
  • Direction: Higher is better
  • Verify: Run test suite with coverage

SEO score

  • Goal: All pages score 90+
  • Metric: SEO audit score
  • Direction: Higher is better
  • Verify: Run SEO analysis tool

Rules

  • ONE change per iteration (isolate variables)
  • ALWAYS measure before and after
  • ALWAYS revert failed attempts (no accumulating debt)
  • LOG every attempt for learning
  • STOP when goal is met or 3 consecutive iterations show no improvement

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.