Install
$ agentstack add skill-xuboyuebobb-investorskills-marks-cycles ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Howard Marks Cycles
Use this skill to apply Howard Marks-style cycle and risk judgment: identify where markets are in the cycle, compare price to value and risk premium, and decide whether to be defensive or aggressive.
When To Use
Use this skill when the user asks for:
- Market cycle diagnosis
- Credit spread and risk premium review
- Second-level thinking on a crowded view
- Defensive or aggressive portfolio posture
- Whether risk is being rewarded or ignored
Trigger phrases include Howard Marks, cycle, second-level thinking, risk premium, credit cycle, defensive, aggressive, and market psychology.
Do Not Use When
- The user needs a precise technical entry only.
- There is no market, valuation, credit, or sentiment context.
- The user asks for a prediction without uncertainty ranges.
- The setup requires leverage or forced timing.
Inputs Needed
- Asset class or market
- Valuation, yield, spread, or risk premium data
- Credit conditions, liquidity, default risk, and refinancing risk if relevant
- Sentiment, positioning, and consensus view
- Portfolio exposure and drawdown tolerance if posture is requested
Process
- Identify the cycle: early, mid, late, stressed, panic, recovery.
- Separate first-level view from second-level view.
- Compare price, value, and risk premium.
- Assess market psychology: fear, greed, complacency, forced selling.
- Decide posture: defensive, neutral, opportunistic, or aggressive.
- Size by margin for error, not confidence alone.
Output Format
# Marks Cycle View: [Market]
## Verdict
Defensive / Neutral / Opportunistic / Aggressive / Stand Down
## Cycle Position
## First-Level vs Second-Level View
## Risk Premium
## Market Psychology
## Portfolio Posture
## What Would Change The View
## Missing Data
Guardrails
- Do not forecast with false precision.
- Do not treat high returns as low risk.
- Do not become aggressive when risk is underpriced.
- Do not become paralyzed during panic if compensation is attractive.
- Always ask what is already in the price.
Questflow Use
In Questflow, this skill is best used as a portfolio posture and cycle-risk module across Funds, asset classes, and market regimes.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: xuboyuebobb
- Source: xuboyuebobb/investorskills
- License: MIT
- Homepage: https://questflow.ai
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.