Evolve a skill by generating variations, evaluating them, and updating the best version

Closes the contributor flywheel — turns the weekly fork-contributor-leaderboard ranking into a tier-priced rewards plan, writes it into memory/distributions.yml, and hands off to distribute-tokens for the actual on-chain send

Generate a complete new skill from a one-line prompt and ship it as a PR

Generate a small app or tool and deploy it live to Vercel via API

Send tokens to a list of contributors via Bankr Wallet API with per-recipient idempotency, two-phase resolve→execute, dry-run, and recovery from partial runs

Proactively enhance watched repos — fix issues, add features, improve code

Build a feature for every watched repo in one run — iterates the full repo list, picks one feature per repo from yesterday's repo-actions ideas first

Monitor managed Aeon instances — check health, dispatch skills, aggregate status

Daily fleet-wide scorecard across this instance and every managed instance in memory/instances.json — runs, tokens (OpenRouter shape), est. cost, skills, and reliability, with day-over-day deltas and alerts

Improve the agent itself — better skills, prompts, workflows, and config based on recent performance

Validate skill outputs against assertions, diff vs prior eval to flag regressions, file issues for new failures, and queue concrete fixes

Audit skill metrics, file/resolve issues in memory/issues/, and notify on state change only

Diagnose and fix failing or degraded skills automatically — systemic-first triage, per-category playbooks, verification plan

Clone this Aeon agent into a new GitHub repo — fork, configure skills, validate, register in fleet

Audit trending repos for real security vulnerabilities and disclose responsibly via PVR or dependency PRs