bankrbot/aeon-autoresearch
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".
$ install --global
skillsauthnpx skillsauth add bankrbot/skills 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: May 13, 2026, 3:48 AM178.5s1 file 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
bankrbot/hunch
data-ai
VerifiedTrustedCommunity
Discover, bet on, track, and settle Hunch prediction markets in natural language. Trigger when a user wants to bet, take a position, or get odds on a crypto outcome — token market-cap milestones and flips, launchpad races (Bankr vs pump.fun volume / #1-days / launches over a cap), token head-to-head outperformance, mcap strike-ladders, and up/down price rounds. Also trigger on "what can I bet on about $TOKEN", "odds on …", "take YES/NO on …", "show my Hunch bets", "did my market resolve". Settles in USDC on Base via x402 (≤ $10 / bet); every bet returns an on-chain proof.
1,143SKILL.mdUpdated Jun 6, 2026
bankrbot/1claw
tools
VerifiedTrustedCommunity
HSM-backed secret management for AI agents. Store API keys (including Bankr `bk_` keys), passwords, and credentials in an encrypted vault; retrieve them at runtime via MCP without keeping secrets in chat context. Bankr Dynamic Key Vending issues short-lived scoped `bk_usr_` keys from a partner key (`bk_ptr_`) without manual rotation. Policy-based access control, secret rotation, sharing, EVM transaction intents (sign/simulate/broadcast), multi-chain signing keys, treasury multisig proposals, OIDC federation for external service auth, built-in prompt injection detection, and optional Shroud TEE LLM proxy. Use when the agent needs secure credential storage, just-in-time secret access, guarded on-chain signing, or security scanning — not for Bankr trading prompts, portfolio checks, or x402 calls (use the bankr skill instead).
1,143SKILL.mdUpdated Jun 5, 2026
bankrbot/gem-miner
testing
VerifiedTrustedCommunity
Stake $GEM tokens on Gem Miner (gemminer.app) to earn yield and unlock the in-game earn/cashout system. Use when the user wants to stake GEM, check their staking balance or rewards, unstake, claim rewards, or check whether they meet the 25M GEM gate. Base mainnet only.
1,143SKILL.mdUpdated Jun 1, 2026
bankrbot/codegrid
development
VerifiedTrustedCommunity
CodeGrid is a native macOS canvas where multiple coding agents (Claude, Codex, Gemini, Cursor, Grok, shells) run side by side in panes and collaborate via a local agent bus — no tmux, no cloud, no account, no stored API keys. Install this skill when an agent should know how to operate inside a CodeGrid pane, drive the workspace from outside (control socket or codegrid:// deep links), spawn or message sibling agents, or coordinate multi-agent work (delegate, review, pipeline, parallel fan-out, monitor, debate). The differentiator: multiple coding agents collaborating on one canvas, addressable by stable session_id, with a read → message → read protocol built for orchestration.
1,143SKILL.mdUpdated Jun 1, 2026