AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Trading Research Orchestrator

skill-tradermonty-hermes-trading-research-agent-work-package-trading-research-orchestrator · by tradermonty

Front-door skill for selecting and coordinating Claude Trading Skills inside Hermes for market research, earnings triage, risk review, and journaling.

↗ Repository
— No reviews yet
0 installs
12 views
0.0% view→install

Install

$ agentstack add skill-tradermonty-hermes-trading-research-agent-work-package-trading-research-orchestrator

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Trading Research Orchestrator? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Trading Research Orchestrator

Use this skill as the front door for all trading research tasks.

Mission

Select the right trading workflow and coordinate installed skills without making the user remember individual skill names.

First decision

Classify the request into one of these routes:

| User intent | Preferred bundle / skills | |---|---| | "Morning", "pre-market", "before open" | pre-market-routine | | "after close", "EOD", "what changed today" | after-close-review | | "earnings", "gap", "PEAD" | earnings-movers-triage | | "market regime", "risk-on", "breadth" | market-regime-daily | | "find swing candidates", "VCP", "CANSLIM" | swing-opportunity-daily | | "journal", "log trade", "postmortem" | trade-journal | | "weekly portfolio", "dividend", "holdings" | weekly-portfolio-review | | "monthly review", "process improvement" | monthly-performance-review |

If trading-skills-navigator is available, consult it before selecting the route. If it is not available, use the table above.

Skill-selection principles

  1. Start with market regime before candidate generation.
  2. Only generate candidate lists when risk posture is not blocked.
  3. Use earnings-specific skills for post-earnings movers instead of generic stock analysis.
  4. Use trader-memory-core whenever a decision, thesis, or review artifact should persist.
  5. Use position-sizer only for sizing calculations, not to imply a trade should be taken.

Required output discipline

Every research output must include:

  • Skill(s) used or intended.
  • Data freshness / missing data.
  • Degraded-mode caveats if any API or external repo is unavailable.
  • Human decision gate.

For ticker candidates, include:

  • Ticker.
  • Setup type.
  • Thesis.
  • Invalidation condition.
  • Risk notes.
  • Next human action.

Forbidden behavior

Do not output commands such as "Buy", "Sell", "Short", "Enter now", or "Place this order" as direct instructions. Use watchlist/research language.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Finance & Payments