stock-picker-orchestrator_skill

This skill coordinates stock analysis across data, macro, and valuation modules under budget controls to deliver transparent, end-to-end recommendations.
  • Python

2.5k

GitHub Stars

2

Bundled Files

2 months ago

Catalog Refreshed

3 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill openclaw/skills --skill stock-picker-orchestrator

  • _meta.json481 B
  • SKILL.md7.6 KB

Overview

This skill coordinates stock-analysis workflows and routes requests across data, macro/news, and valuation modules while enforcing explicit API and news budgets. It turns user intent into a reproducible pipeline, producing transparent outputs that list fetched sources, assumptions, confidence, gaps, and next-step options. The orchestrator never replaces domain modules; it directs them and aggregates results into a decision-grade response.

How this skill works

On request it classifies intent into one of four modes (Single-Ticker Deep Dive, Multi-Ticker Screening, Macro/News-Led Investigation, Portfolio Refresh), picks a budget preset (Light/Standard/Deep), and invokes upstream skills in the prescribed order. It estimates and enforces vnstock and news call limits, reuses caches when possible, validates intermediate outputs for freshness and conflicts, runs valuation at the requested depth, aggregates per-module confidence with a shared rubric, and returns a mandatory structured output contract.

When to use it

  • When you want a coordinated end-to-end stock analysis that balances cost and depth
  • When comparing multiple tickers or screening a sector with controlled API/news spend
  • When macro or news context should drive candidate selection
  • When you need a reproducible valuation plus transparent assumptions and gaps
  • When refreshing a portfolio to surface risk and rebalance candidates

Best practices

  • State desired mode and budget upfront (Light/Standard/Deep) to avoid scope creep
  • Provide any API key or indicate guest mode so budgets map correctly
  • If you want deep DCFs, accept the Deep preset and longer runtimes
  • Ask for partial results if budget limits stop execution mid-run
  • Request explicit reuse of cached artifacts to save API calls

Example use cases

  • Deep-dive a single ticker with full valuation and risk register (Single-Ticker Deep Dive)
  • Screen VN30 for top value-quality names, quick-rank, then deep-value top 3
  • Start from macro shock signals to map sector exposures and value 1-2 winners
  • Refresh a portfolio: re-score holdings, apply macro stress overlay, flag rebalance candidates
  • Compare three tickers with unified evidence, confidence and monitoring triggers

FAQ

The orchestrator estimates required calls before execution, picks the smallest viable preset, paces requests per free-tier limits, reuses cached artifacts, and halts scope expansion when remaining budget <10%.

What if a required upstream skill is unavailable?

Fallback behavior: proceed without the missing module, note the gap in the output contract, downgrade confidence, and offer follow-up options to retry or deepen once the module is available.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational