agentleFS
Sign inStart free
EskyeeEskyee/agentbot-opensource/skills/aeon-token-pick/SKILL.md

aeon-token-pick

Skill17 starsChanged 5 months agoMITView on GitHub

One token recommendation and one prediction-market pick per run — with falsifiable thesis, entry, sizing guidance, and an explicit kill criterion. Skip branch fires when no candidate has both a named/dated catalyst and asymmetric upside. The discipline is the skip branch — empirically the highest-EV output on flat days is no pick. Triggers: "what should I trade today", "give me a token pick", "prediction-market rec", "is there an asymmetric setup".

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If no candidate clears the bar — named, dated catalyst plus asymmetric setup — the skill returns NO_PICK with the top three near-misses and …

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

aeon-token-pick

At most one token pick and one prediction-market pick per run. Each pick must have:

  • Falsifiable thesis — one sentence.
  • Entry — price + venue.
  • Kill criterion — the specific signal that says the thesis is wrong.
  • Sizing — small / medium / large vs the operator's stack.
  • Time horizon — hours / days / weeks.

If no candidate clears the bar — named, dated catalyst plus asymmetric setup — the skill returns NO_PICK with the top three near-misses and what would have tipped them over.

Sample output

TOKEN: $XYZ — entry $0.42 on Base (Aerodrome WETH/XYZ pool)
Thesis: ProductHunt launch May 15 + commit-velocity surge signals real shipping
Kill: launch delayed past May 22 OR daily commits drop below 5 for 3 days
Sizing: medium · Horizon: 2-3 weeks

MARKET: NO on "EIGEN unlock delayed past Q2" @ 0.31
Thesis: on-chain timelock activity confirms unlock; delay risk overpriced
Kill: official delay announcement before market resolves
Sizing: small (binary) · Resolution: July 1

No-pick output:

NO_PICK — 2026-05-12

Top near-misses:
1. $XYZ — catalyst unclear, asymmetry weak (upside +30%, downside -50%)
2. NO on "EIGEN delayed past Q2" — mispriced but no dated resolution

Would tip the call: a dated catalyst on $XYZ; a specific committee date for EIGEN.

Rules

  • Falsifiable thesis or no pick.
  • Cite the catalyst by name and date. "Sentiment turning" is not a catalyst.
  • Crowdedness penalty — if every newsletter is recommending it, the asymmetry is gone.
  • NO_PICK is a valid output. Manufactured picks burn capital.

Pairs naturally with aeon-narrative-tracker (narrative fit), aeon-monitor-runners (momentum candidates), aeon-unlock-monitor (supply-side risk), and Bankr Submit / AgenticBets for execution.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free