agentleFS
arunendapallyarunendapally/portfolio-copilot/skills/get-started/SKILL.md

get-started

Skill0 starsChanged 29 days agoMITView on GitHub

Onboard an investor, or import an existing investor's notes. Use for "get started", "set up my portfolio", "I'm new to this", "update my profile", "import my notes", or right after installing the plugin.

23 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

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 22 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Ask which folder to keep their portfolio files in.

    line 11
  2. Very specific:

    Write the first log_append with start_here: goal, current state in one line, next actions, decisions owed.

    line 16
  3. Distinctive:

    Run the check skill for the first snapshot.

    line 17

“Common” is measured: kept by at least 6 in 10 of the 22 edited versions of this file we could read. “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

Get started

Plain language; explain each term (GTT, XIRR, SIP) once in a short parenthesis.

  1. Disclaimer first, and wait for an acknowledgement: "I provide analysis, not investment advice. I'm not SEBI-registered, I never suggest what to buy, and no order runs unless you approve the exact draft by clicking Yes in an inline question that lists every order."
  2. Ask which folder to keep their portfolio files in. Pass it as --folder on the first pc command; it is remembered.
  3. Ask in one friendly message: goal and years to it; a 20% fall in a month: sell, hold or buy more (conservative / balanced / aggressive); monthly investment and idle lump sum; brokers (Zerodha and Kotak Neo connect live; IBKR via its connector; any other broker by CSV import); where the emergency cash buffer is kept (broker or bank).
  4. Save with profile_update, one path at a time: investor.*, brokers.kotak.enabled and brokers.kotak.ucc, cash.buffer_location, allocation.targets if they have them, deployment_plan if they have a staged plan. For the plan, save corpus_source (the name of the holding that is the war chest, e.g. "ARBITRAGE") rather than a fixed corpus_inr, so the corpus is read live, and set stages[i].done_at for stages already deployed. Confirm each in a short summary.
  5. Verdicts: as the investor states a stance on a holding, save verdicts.<SYMBOL> = {stance, reason, exit_level?}. Stances: hold, add, hold_no_add, reduce, exit, or trade (a short-term position with its own stop and target).
  6. Existing notes ("import my notes"): read their files, extract rules only (thresholds, GTT policy, buffer location, allocation targets, staged plan, verdicts with reasons). Show each proposed item and save it only after the investor confirms it. Never import snapshot numbers (quantities, prices, P&L, dated totals) as rules.
  7. Write the first log_append with start_here: goal, current state in one line, next actions, decisions owed.
  8. Run the check skill for the first snapshot. Explain it in 3-4 sentences and the one most important next action.
  9. Offer a routine: "check" each morning, "risk" on Fridays, "gtt" after any buy or sale. A scheduled weekday check works, but Indian brokers expire logins daily, so an unattended run gives macro plus the last snapshot.

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.