agentleFS
lungraylungray/investment-workflow-skill/SKILL.md

investment-workflow

Skill2 starsChanged 4 months agoMITView on GitHub

Use for user-provided holdings or portfolio strategy reports; orchestrates the verified investment pipeline.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. Agentic-Assets/equire-plugin★ 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.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Use when the user provides holdings, references an existing corrected holdings.json, or asks for a portfolio-level investment report.

    line 14
  2. Distinctive:

    Do not skip a hard gate to produce a more complete-looking report.

    line 31
  3. Distinctive:

    No return guarantees and no recurring automation by default.

    line 82

≈ “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

Investment Workflow

Use when the user provides holdings, references an existing corrected holdings.json, or asks for a portfolio-level investment report. Do not use for an unrelated single-stock question or create scheduled reports unless explicitly requested.

Ownership and order

This Skill orchestrates; component Skills own their stage logic:

portfolio-parser
→ holdings validation gate
→ market-data
→ portfolio-analysis
→ optional tradingagents-cn focused deep dive
→ market-screener
→ investment-report
→ final validation

Do not skip a hard gate to produce a more complete-looking report.

Inputs

  • Raw screenshot, PDF, Word, Excel/CSV, Markdown, or text holdings.
  • A corrected holdings JSON from a prior stopped run.

For raw files:

python \
  skills/investment-workflow/scripts/run_investment_workflow.py \
  <holding-file>... -o <output-directory> [--live]

For manually reviewed/corrected holdings, bypass re-parsing:

python \
  skills/investment-workflow/scripts/run_investment_workflow.py \
  --holdings-json <corrected-holdings.json> \
  --confirm-holdings-reviewed \
  -o <output-directory> [--live]

Raw inputs and --holdings-json are mutually exclusive. Confirmation does not excuse missing/invalid symbols or non-positive quantities.

Hard gates

  1. Parsing must produce holdings with a code or name and a positive holding quantity.
  2. Image OCR always requires review against the original screenshot. On review_required or fail, the workflow writes only holdings.json and stops before market calls.
  3. A-share price is CNY; Hong Kong price is HKD; user cost is CNY unless explicitly labelled otherwise. Never compare HKD price directly with CNY cost.
  4. Hong Kong identity does not prove Stock Connect eligibility. Unknown eligibility may be analyzed but not recommended as buyable.
  5. Account assets, wealth-management holdings, bonds, available cash, and withdrawable cash are different fields. Only confirmed available stock-account cash is deployable.
  6. Missing or stale market evidence lowers confidence and actionability; never fabricate a replacement value.
  7. Screening may legitimately return no actionable candidate.
  8. Final output must show data date/mode, currency, limitations, evidence, and the non-advice disclaimer.

TradingAgents-CN modes

  • quick (default): no TradingAgents call.
  • focused: deterministic top-N holdings by market value, then quantity × cost, then input order.
  • full: every supported holding; use only when explicitly justified.

TradingAgents is optional model judgment, not a source of current price, FX, or eligibility. Failure is non-fatal and must be disclosed. Cached reports remain dated evidence and require current market-data refresh.

Default constraints

  • Investable scope: A-shares and confirmed Hong Kong Stock Connect stocks.
  • Exclude US stocks, ETFs, options, funds, convertible bonds, and Beijing Stock Exchange stocks unless the user explicitly expands scope.
  • Preserve the existing investment preferences and scoring strategy; recommendations remain conservative when evidence is incomplete.
  • No return guarantees and no recurring automation by default.

Outputs

Successful runs write holdings.json, market_data.json, analysis.json, screener.json, and investment_report.md. Non-quick TradingAgents runs may also write tradingagents_summaries.json.

See references/rebalance-execution.md, ../../docs/investment-workflow-quick-checklist.md, and ../../docs/investment-workflow-handbook.md.

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.