agentleFS
latour-ailatour-ai/skills/key-debates-ledger/SKILL.md

key-debates-ledger

Skill69 starsChanged 24 days agoNo licenceView on GitHub

Maintain an explicit bull/bear debate ledger for each significant position: the two to four decidable questions that will actually determine the outcome, the current evidence on each side with source and date cited, and the pre-registered upcoming data point most likely to resolve each debate. As new filings, earnings transcripts, sell-side notes, and internal call notes arrive, it files each data point against the ledger — bull side, bear side, or neither — flags when the balance of evidence has meaningfully shifted, screens for genuinely new debates, and retires settled ones with the evidence that settled them. For research analysts and PMs running fundamental equity and credit books. Trigger on phrases like "update the debates ledger," "what are the key debates on [ticker]," "does this change the debate," "build a debates ledger from this thesis memo," "where does this data point land," "what would change our mind on this name," or when a user pastes new material against an existing ledger. Do NOT use to extract a single earnings call into a memo — use the earnings-call-extractor skill. Do NOT use to stress-test the whole thesis adversarially — use the thesis-red-team skill. Do NOT use to synthesize a stack of expert transcripts — use the expert-call-synthesis skill. Not investment advice.

The file

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.