agentleFS
arunendapallyarunendapally/portfolio-copilot/skills/risk/SKILL.md

risk

Skill0 starsChanged 30 days agoMITView on GitHub

Risk and allocation review. Use for "risk check", "weekly risk update", "monthly rebalance", "allocation check", "review my MFs", "fund review", "rate sensitivity", "quarterly review", or "basket for [amount]".

5 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions5 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 5

    1. ruujOnChain/HedgeFund-Skills★ 17same name
    2. davidromeo/tradeblocks-skills★ 3same name
    3. tradeblocks-org/tradeblocks-skills★ 3same name
    4. hailneed/agent-blackbox★ 0same name
    5. Olayeeeyo/claude-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the check skill's connect and pull steps if today's data is not live.

    line 8
  2. Very specific:

    Call check. From its text, present: cash vs buffer (say where the buffer is held), concentration alerts with their base (% of book, % of …

    line 9
  3. Very specific:

    Call rate_map. Before an RBI policy meeting, call out the most exposed names.

    line 10
  4. Very specific:

    No deployment suggestion while check reports cash below buffer (unless the profile says the buffer is in the bank).

    line 13
  5. Very specific:

    After any new verdict, call verdict_notes and offer its text for the investor to paste into their notes file.

    line 15

“Common” is measured: kept by at least 6 in 10 of the 4 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

Risk

  1. Run the check skill's connect and pull steps if today's data is not live.
  2. Call check. From its text, present: cash vs buffer (say where the buffer is held), concentration alerts with their base (% of book, % of direct equity, % of fund book), allocation drift vs targets.
  3. Call rate_map. Before an RBI policy meeting, call out the most exposed names.
  4. Funds ("review my MFs"): for each active fund held, apply the fund screen in this order and say which step it fails: (a) is there a structural reason an index fund cannot do this job; (b) total expense ratio vs the index alternative; (c) overlap with other holdings. Past returns are never a reason to hold. Cite a dated source for every fee and figure (fetch it; prefer static pages such as Advisorkhoj over JS-rendered ones).
  5. Rebalancing: close drift with new money first, not sales. Name the buckets that are under target. To turn an amount into orders, call draft_basket (amount + destinations the investor names or the saved deployment_plan.destinations). Show its text, then follow its instructions: the inline Yes/No question, then one Kite MCP place_order per row with the arguments shown (the order gate allows each once), then read orders again and run the gtt skill for the new shares. IBKR orders go through draft_orders and the IBKR create_order_instruction the same way.
  6. No deployment suggestion while check reports cash below buffer (unless the profile says the buffer is in the bank).
  7. Buffer and cover: call protection_check. It measures the emergency fund against 6 to 12 months of expenses and reports term cover, health cover and SIPs from the investor's saved inputs. Missing inputs are asked for, then saved with profile_update (protection.*, sips).
  8. After any new verdict, call verdict_notes and offer its text for the investor to paste into their notes file; the profile stays the source.
  9. log_append the findings.

Analyze only what the investor holds or names; never suggest new securities.

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.