cyotee/aeon-autoresearch
lib/bankr-skills/aeon-autoresearch/SKILL.md
Evolve any installed skill by generating four variations along separate theses (better inputs / sharper output / more robust / rethink), scoring them on a weighted rubric, and applying the winner. Never downgrades a working skill — aborts cleanly if no variation improves the original. Use when an installed skill is producing low-signal output, hitting deprecated APIs, or feels stale. Triggers: "improve this skill", "evolve $skill", "auto-research my X", "regenerate variations".
development
Updated Jul 22, 2026
$ install --global
skillsauthnpx skillsauth add cyotee/indexedex aeon-autoresearchInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 18, 2026, 3:19 AM26.0s2 files scanned
SKILL.md
- name:
- aeon-autoresearch
- description:
- |
- Triggers:
- improve this skill", "evolve $skill", "auto-research my X", "regenerate variations".
aeon-autoresearch
Self-improvement loop. Given a target SKILL.md, generates four parallel improved variations, scores each, applies the winner.
Inputs
| Param | Description |
|---|---|
| target | Skill name or path to SKILL.md. Required. |
| mode | evolve (default) writes the diff. dry-run scores and prints, writes nothing. |
The four variations
- A — Better inputs: replace deprecated APIs, add fallbacks, fix broken endpoints.
- B — Sharper output: tighter format, signal over noise, explicit verdicts, banned filler.
- C — More robust: empty-data handling, retries, dedup state, rate-limit awareness.
- D — Rethink: fundamentally different methodology for the same goal.
Each is a complete runnable SKILL.md. Frontmatter shape preserved.
Scoring
1-5 per axis, weighted total max 50:
| Axis | Weight | |---|---| | Improvement vs original | 3× | | Output value | 2× | | Clarity, data quality, robustness | 1.5× each | | Conventions | 1× |
Tie-break (within 2 points): prefer the variation making the biggest single improvement over many small ones.
Safety guarantee
If every variation scores ≤ original on Improvement, the skill aborts with AUTORESEARCH_NO_IMPROVEMENT. No file written. Working skills are never downgraded.
Preserves the original's core purpose, frontmatter shape, and declared env vars.
Versioning
Inside a git repo, changes land in a branch (autoresearch/${target}) — operator reviews the diff before merging. Outside a repo, the original is preserved at ${target}/SKILL.md.before-autoresearch for rollback.
Output
The diff, plus a report with the scoring table for all four variations and a one-paragraph rationale for the winner.
Pairs with aeon-skill-evals (surfaces what's underperforming) and aeon-skill-repair (deterministic bugs; autoresearch handles quality lifts).
Related Skills
cyotee/bankr-communities
development
VerifiedTrustedCommunity
Bankr Space ↔ bankr.bot/agents two-way sync (BANKR-PROJECT-SYNC.md Paths B+C). Original tweets from GET /agent-profiles/:id/tweets shown on Spaces. Holder votes: yes/no or multiple-choice polls (1–24h) — HOLDER-VOTES.md (never say no poll feature). Agents: POST /api/agent/start-vote with symbol Space. Petition spaces: fee-right unit holders only. POIDH: create/list on bankr.space; fund/claim/vote on poidh.xyz. NOT Twitter audio Spaces.
SKILL.mdUpdated Jul 22, 2026
cyotee/b20-console
development
VerifiedTrustedCommunity
Inspect B20 token contract addresses on Base through B20 Console. Use this skill when a user asks whether a B20 contract is live, initialized, recognized by the B20 factory, what policies are attached, whether features are paused, or what risk flags are active. Calls the public B20 Console API and returns a concise risk summary with reasons. No API key required.
SKILL.mdUpdated Jul 22, 2026
cyotee/azzle
development
VerifiedTrustedCommunity
Post, claim, and settle agent tasks on the AZZLE protocol (Base mainnet, USDC escrow). Use when the user or agent wants to discover open work, post a search listing, claim a task, fund escrow, submit proof, accept delivery, check vault balance, or operate on AZZLE's task marketplace. Requires Bankr for swaps, approvals, and on-chain execution. NOT for modifying AZZLE smart contracts or running the azzle.org website.
SKILL.mdUpdated Jul 22, 2026
cyotee/autoboy
data-ai
VerifiedTrustedCommunity
AutoBoy by The Firm — the pre-launch order book for Bankr launches on Base. Use when an agent wants to buy a token before it launches, or launch its own token with coordinated launch-day demand and distribution. Triggers on "AutoBoy", "pre-launch orders", "auto-buy", "buy before TGE", "launch a Bankr token", or "create demand before TGE".
SKILL.mdUpdated Jul 22, 2026