agentleFS
Sign inStart free
JayuanlabJayuanlab/zhiyu/skills/single-etf-position-advisor/SKILL.md

single-etf-position-advisor

Skill0 starsChanged 2 months agoApache-2.0View on GitHub

Use only for legacy or explicit ETF position-state advisory loops that review one ETF position without placing simulated or real orders.

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 9 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    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. Very specific:

    Treat positionStateValue=0 as out of market and positionStateValue=1 as full-position held.

    line 13
  2. Distinctive:

    Do not infer real holdings, cost, quantity, or broker account state from missing data.

    line 14
  3. Distinctive:

    Do not call simulated order tools.

    line 15
  4. Distinctive:

    Do not call real broker or payment tools.

    line 16
  5. Distinctive:

    Do not claim a buy or sell was executed.

    line 17
  6. Distinctive:

    Only update durable position memory after the owner explicitly confirms that the position state changed.

    line 18
  7. Very specific:

    Read workshop memory for the latest declared positionStateValue, source, and confirmation time.

    line 22
  8. Distinctive:

    Read the latest advisory plan or timing report if available.

    line 23
  9. Distinctive:

    Check current ETF quote, trend, market state, and major holding basket only to evaluate whether the declared position state remains …

    line 24
  10. Very specific:

    If position state is unknown, report position_unknown and ask for owner confirmation instead of assuming a real holding.

    line 25
  11. Very specific:

    If position state is out of market, sell checks are not_applicable_no_position.

    line 26
  12. Distinctive:

    If position state is full-position held, evaluate whether the existing sell trigger or thesis invalidation is active.

    line 27
  13. Distinctive:

    Every run should report:

    line 31

≈ “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

Single ETF Position Advisor

This skill exists for legacy ETF position-state loops and explicit owner-approved position-review tasks. The current 515980 workshop strategy is handled by single-etf-timing-advisor; use this skill only when a loop is explicitly about historical/declared position state rather than generating the all-in/all-out timing plan.

Boundary

  • Study only the specified ETF and its declared position state.
  • Treat positionStateValue=0 as out of market and positionStateValue=1 as full-position held.
  • Do not infer real holdings, cost, quantity, or broker account state from missing data.
  • Do not call simulated order tools.
  • Do not call real broker or payment tools.
  • Do not claim a buy or sell was executed.
  • Only update durable position memory after the owner explicitly confirms that the position state changed.

Workflow

  1. Read workshop memory for the latest declared positionStateValue, source, and confirmation time.
  2. Read the latest advisory plan or timing report if available.
  3. Check current ETF quote, trend, market state, and major holding basket only to evaluate whether the declared position state remains reasonable.
  4. If position state is unknown, report position_unknown and ask for owner confirmation instead of assuming a real holding.
  5. If position state is out of market, sell checks are not_applicable_no_position.
  6. If position state is full-position held, evaluate whether the existing sell trigger or thesis invalidation is active.

Output Contract

Every run should report:

  • positionStateValue
  • positionState
  • positionStateSource
  • etfState
  • trendState
  • holdingBasketState
  • advisoryDecision
  • ownerActionRequired
  • riskNotes
  • nextCheck

Visible reports should be Markdown and should clearly separate observed facts, advisory judgment, and actions not taken.

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