Skip to content
cccskills
FreePublished on GitHub

autoresearch

Run Karpathy-style autoresearch optimization on any content. Generates 50+ variants, scores with a 5-expert simulated panel, evolves winners through multiple rounds, outputs optimized version + full experiment log. Use when optimizing landing pages, email sequences, ad copy, headlines, form pages, CTA text, or any conversion-focused content. Triggers on "optimize this page", "run autoresearch", "score these variants", "A/B test this copy".

The English summary is being prepared. Showing the original description.

LazyIsEfficient/agentic-os
See how to install

Files included (7)

  • SKILL.md4.5 KB
  • README.md3.7 KB
  • references/content-types.md1.6 KB
  • references/execution-protocol.md2.6 KB
  • references/round-structure.md1.9 KB
  • requirements.txt18 B
  • scripts/autoresearch.py17.6 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Autoresearch Skill

Karpathy-style optimization loops for any conversion-focused content. No traffic needed. Simulated expert panel. Minutes, not weeks.

The sequence: Run autoresearch FIRST to hit 85+ simulated score. Then deploy. Then validate with real traffic.

What You'll Produce

Every run outputs 3 files:

FilePurpose
{name}-optimized.{ext}The winning optimized content
data/{name}-experiments.jsonFull experiment log — all variants + all scores
data/{name}-optimization-report.mdHuman-readable summary with winner rationale

Core rules

  1. Intake: parse content type from file extension (HTML → landing/form page; markdown → email/ad copy). List all optimizable elements and confirm with user before starting.
  2. Score every variant against the 5-expert panel in a single batched API call per round — never one call per variant.
  3. Run up to 3 rounds per element; stop early when top variant hits the minimum score threshold (default: 80).
  4. Cross-breed only after each element has its own winner — premature cross-breeding creates incoherent combinations.
  5. Write 3 output files: optimized content, experiments JSON, optimization report.
  6. Report back: winning score, biggest score jump, top 2 runner-ups, file paths, next step.

User Options

OptionDefaultDescription
elementsallWhich elements to optimize
variants_per_round10How many variants per round
min_score80Stop when this score is hit
rounds3Max rounds before stopping
auto_applyfalseOverwrite source file with winners
content_typeauto-detectForce a content type if auto-detect is wrong

Quality Gates

  • < 70: Don't ship. Something fundamental is broken.
  • 70-79: Marginal. One more round targeting the lowest-scoring dimension.
  • 80-84: Good. Shippable. Validate with real traffic.
  • 85-89: Strong. Ship with confidence.
  • 90+: Rare. Ship immediately.

Anti-Patterns

  • Never call the API once per variant. Always batch. A 10-variant round = 1 call.
  • Don't over-optimize for one dimension — a 95 clarity + 45 trust is a misleading overall score.
  • Don't run more than 5 rounds. If not hitting 80 after 3, the problem is strategic, not tactical.

References

Related skills

  • content-ops — quality scoring gate; run after autoresearch optimization
  • conversion-ops — audits a LIVE landing-page URL across CRO dimensions; use it instead when scoring a live page rather than optimizing copy variants pre-launch

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

adversarial-claims-reviewer

Free

Use when adversarially reviewing a document that makes formal or technical claims — math derivations, physics papers, statistical analyses, benchmark reports, whitepapers. Inventories every equation and quantitative claim, verifies each AS NAMED in the text (never a paraphrase or a neighboring statement), and classifies VERIFIED / REFUTED / UNVERIFIABLE / VACUOUS. Triggers on "check this paper", "verify these claims", "is this derivation right", "review this proof", "audit this benchmark", "does the math hold up". For source-code review see code-review-and-quality; for skill/agent library audits see skill-library-review; for content quality scoring see content-ops.

The English summary is being prepared. Showing the original description.

LazyIsEfficient/agentic-os17Updated Jul 17, 2026

browser-testing-with-devtools

Free

Tests in real browsers. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data via Chrome DevTools MCP.

The English summary is being prepared. Showing the original description.

LazyIsEfficient/agentic-os17Updated Jul 17, 2026

code-review-and-quality

Free

Conducts multi-axis code review across correctness, readability, architecture, security, and performance. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Triggers on "review my PR", "review this diff", "code review", "review this changeset", "is this ready to merge", "pre-merge review".

The English summary is being prepared. Showing the original description.

LazyIsEfficient/agentic-os17Updated Jul 17, 2026

codebase-cost-estimator

Free

Estimate the full development cost of an existing codebase from lines of code, architectural complexity, and team-composition overhead. Use for 'how much would this cost to build', 'what did this codebase cost', development-cost or build-cost estimates, calendar-time estimates, and Claude/AI ROI on a delivered codebase. Estimates by measured LOC and complexity, not by ticket volume.

The English summary is being prepared. Showing the original description.

LazyIsEfficient/agentic-os17Updated Jul 17, 2026

content-ops

Free

Auto-assembles a domain-specific expert panel (7–10 experts), scores any content or strategy artifact against a typed rubric, and iterates until the aggregate hits 90+ (max 3 rounds). Use as a quality gate on copy, email sequences, landing-page drafts, strategy docs, charts, titles, or recruiting evaluations — or when another skill needs a final review gate on its output. Triggers on "expert panel this", "score this", "rate these variants", "quality check this", "panel review", "expert score", "evaluate this copy/strategy/page". For variant generation and multi-round conversion optimization see autoresearch; for live-URL CRO auditing see conversion-ops; for the scripted content-production pipeline see content-pipeline.

The English summary is being prepared. Showing the original description.

LazyIsEfficient/agentic-os17Updated Jul 17, 2026

content-pipeline

Free

Non-interactive content-production toolkit: mine quotable moments from podcast RSS feeds and meeting notes, discover clip-worthy moments in video transcripts, repurpose long-form source into platform-native drafts (X, LinkedIn, YouTube Shorts, newsletter), and batch-score/gate those drafts before publish. Use when asked to "mine quotes from this podcast", "find clips in this video", "repurpose this into a thread / LinkedIn post / Short", "turn this transcript into posts", "extract viral moments", or "gate this batch of drafts". Runs Python scripts end to end. For interactive expert-panel scoring of a single artifact see content-ops.

The English summary is being prepared. Showing the original description.

LazyIsEfficient/agentic-os17Updated Jul 17, 2026

See all skills by LazyIsEfficient

Report a problem with this skill