What makes Stanley Druckenmiller Workflow notable?

2.1K downloads. Trust evidence available

How should Stanley Druckenmiller Workflow be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Stanley Druckenmiller Workflow

Thesis-driven macro-to-execution market workflow in natural Chinese or English. Generate A-share and U.S. equity Morning Briefs, Intraday Alerts, Close Revie... Skill: Stanley Druckenmiller Workflow Owner: luckycatl Summary: Thesis-driven macro-to-execution market workflow in natural Chinese or English. Generate A-share and U.S. equity Morning Briefs, Intraday Alerts, Close Revie... Tags: latest:1.1.11 Version history: v1.1.11 | 2026-03-27T01:11:25.751Z | user Aligned output granularity with the latest structure: replaced the old CAR block with fixed Consensus Decomposition,

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

2.1k

Updated

Oct 9, 2026

Version

1.1.11

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2.1K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 2.1K downloadsadoption · observed Oct 9, 2026
Latest release: 1.1.11release · observed Mar 27, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17dvq0hzneqxs5n9qbmjybz4h83grk0:stanley-druckenmiller-workflow

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-luckycatl-stanley-druckenmiller-workflow/snapshot"

Documentation

CLAWHUB

151,267 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: stanley-druckenmiller-workflow
description: Thesis-driven macro-to-execution market workflow in natural Chinese or English. Generate A-share and U.S. equity Morning Briefs, Intraday Alerts, Close Reviews, Weekly Regime Resets, and pre-trade sanity checks. Use when the user asks for an A-share morning brief, a U.S. morning brief, a pre-market view, an intraday state update, an end-of-day review, a weekly regime reset, a market-location read, portfolio-bias guidance, falsification conditions, market priority, industry priority, or a translation from liquidity, rates, credit, real-economy demand, price, structure, sector expression, fundamentals, and reflexivity into Regime, Best Expression, Position Bias, Kill-switch, and Watchlist.
---

# Stanley Druckenmiller Workflow

> Published version: **1.1.11**

## 1) Positioning

Use a public-data process that approximates a Druckenmiller-style workflow.
Do not claim private access or exact replication of the real person.
Do not present inference as quoted fact.

This skill is a **macro-to-execution decision engine**, not a generic news summarizer.

Its job is to:
- identify the current regime
- form a thesis first, then test it against tape
- trace transmission from upstream conditions to downstream market expression
- translate that into executable positioning language
- define falsification clearly

Its job is not to:
- issue individual stock buy/sell calls
- promise prediction accuracy
- replace human execution judgment
- dump raw data without synthesis

### Product boundary
- Strongest use: first-layer macro environment judgment
- Human-owned layer: exact asset, exact entry, exact size, exact risk budget
- Honest framing: AI watches the environment; the human decides how to bet

When extending or maintaining the skill, read:
- `references/core-panels-and-sources.md`
- `references/a-share-tape-v1_1.md`

---

## 2) Output Style (Strict)

- Output in the resolved user language.
- Voice should feel like a live PM memo: direct, conditional, concise, human.
- Depth parity rule: Chinese and English outputs should have equivalent analytical depth for the same request type.
- Do not output JSON, YAML, code blocks, key-value dumps, or tool logs unless the user explicitly asks for machine format.
- Markdown headings and bullets are allowed.
- On first mention, explain each ticker or series in the user's language when that helps readability.
- Facts and interpretation must be distinguishable.

### Language Policy
Resolve output language in this order:
1. explicit user instruction
2. account-level preference
3. current-session language habit
4. platform locale / Accept-Language
5. message-language detection

Rules:
- explicit instruction overrides everything
- current-session language habit should not silently overwrite account-level preference unless the user explicitly confirms a long-term change
- if account preference and session habit conflict for multiple turns, ask once and persist the answer at t

README.md

# Stanley Druckenmiller Workflow

Thesis-driven market analysis skill for OpenClaw.

This skill is designed for Druckenmiller-inspired macro/equity thinking with a live PM memo voice:
- Liquidity and rates first
- Consensus vs variant explicitly separated
- D1/D2 (first derivative / second derivative) regime logic
- Evidence anchors and safety disclaimers

Current product framing:
- Goal: hand most repetitive monitoring work to the machine and leave the highest-value judgment to the human.
- V1 scope: US-led macro engine + China / A-share transmission layer.
- Honest limitation: the skill can help with first-layer macro judgment, not fully replace second-layer execution judgment.
- Core panels and source reference: `references/core-panels-and-sources.md`
- A-share tape design reference: `references/a-share-tape-v1_1.md`

## What This Skill Produces

Depending on trigger, it can generate:
- AM morning brief (thesis + validation)
- EOD wrap
- Weekly review
- Monthly regime review
- Pre-trade thesis collision check
- Asset divergence monitor

All outputs are narrative and decision-oriented (not raw JSON dumps).

## Folder Structure

```text
stanley-druckenmiller-workflow/
  SKILL.md
  README.md
  references/
    core-panels-and-sources.md
    a-share-tape-v1_1.md
  scripts/
    market_panels.py
```

## Data Source Fallback (updated)

`market_panels.py` now has two layers:

### Global / cross-asset layer
Per symbol, the default order is:
1. finshare (default `first` mode)
2. Yahoo chart API
3. Stooq CSV
4. FRED proxy mapping
5. Local cache

### A-share structure layer
A-share internal structure now uses **AkShare** when available, mainly for:
- northbound flow
- Shibor / China government bond yields
- margin financing and securities lending
- property-chain, transport, consumer-tiering, and credit-sensitive proxy baskets

### Runtime cache scope (security fix)
By default, `market_panels.py` now writes cache files only inside the skill directory:
- `stanley-druckenmiller-workflow/.runtime/market-snapshots/`

It no longer writes to a workspace-level `memory/` directory by default.

If you explicitly want a different runtime/cache directory, set:

```bash
export STANLEY_RUNTIME_DIR=/your/explicit/runtime/path
```

If unset, the script stays confined to the skill-local runtime folder.

### Minimal finshare integration (optional)

Default mode is `first`:
- try finshare first
- if finshare fails, fall back to Yahoo / Stooq / FRED / Cache
- use `auto` to switch back to “Yahoo first, finshare as fallback”

#### 1) Install optional dependencies

```bash
pip install finshare akshare
```

#### 2) Enable / disable modes

- CLI arguments (single run)

```bash
python3 scripts/market_panels.py --finshare-mode first
python3 scripts/market_panels.py --finshare-mode auto
python3 scripts/market_panels.py --finshare-mode off
```

- Environment variables (default global behavior)

```bash
export FINSHARE_MODE=first  # default: prefer finshare
export FINSHARE_MODE=auto

_meta.json

{
  "ownerId": "kn7d3hfagfaks9xk7natxyg2w981hqsy",
  "slug": "stanley-druckenmiller-workflow",
  "version": "1.1.11",
  "publishedAt": 1774573885751
}

references/a-share-tape-v1_1.md

# A-share Tape V1.1

Goal: build a Stan-style A-share tape using mostly free and reasonably stable data.

Principles:
- Keep the daily tape focused on what changes the regime read.
- Separate hard anchors from noisy confirmation signals.
- Prefer data that is free, repeatable, and can survive source changes with fallback.

## Tiering
- Core = should be in the V1 daily tape
- Confirm = useful confirmation layer
- Optional = helpful but noisy or fragile
- Avoid as core = do not let this drive the main thesis in V1

---

## 1) Internal Structure (Most Important)

| Indicator | Tier | Why it matters in Stan terms | Free source feasibility | Recommended sources | Notes |
|---|---|---|---|---|---|
| CSI300 vs CSI1000 | Core | China version of IWM/SPY; large vs small cap risk appetite | High | Tencent / Eastmoney / Yahoo proxies | Core breadth / risk-expansion read |
| ChiNext vs CSI300 | Core | Growth vs core-beta proxy | High | Tencent / Eastmoney / Yahoo | Use for duration / growth appetite |
| STAR50 vs CSI300 | Confirm | Higher-beta innovation-board confirmation | Medium | Eastmoney / Tencent / AkShare proxies | Useful, not strictly required in V1 |
| Up/down stocks count | Core | Most direct breadth signal | Medium-High | Eastmoney / AkShare market breadth pages | Critical for diagnosing “index up but tape weak” |
| Total turnover (Shanghai + Shenzhen combined turnover) | Core | Shows whether repair has real participation | High | Eastmoney / Tencent / AkShare | Pair with breadth, not alone |
| Limit-up / limit-down counts | Optional | A-share emotion extreme gauge | Medium | Eastmoney / AkShare | Emotion layer only |

---

## 2) Flow / Who Is Buying

| Indicator | Tier | Why it matters | Free source feasibility | Recommended sources | Notes |
|---|---|---|---|---|---|
| Northbound net flow (single day) | Core | Best free foreign-flow proxy | High | Eastmoney / AkShare HSGT endpoints | Must be read with continuity, not as a single print |
| Northbound 3-day / 5-day continuity | Core | More Stan-like than one-day flow | High | Derived from the same northbound source | Prefer over raw daily number |
| Northbound sector destination | Confirm | Shows whether foreign money is buying banks / consumer / tech | Medium | Eastmoney / AkShare summaries | Great when available, not mandatory |
| Margin financing balance change | Confirm | Retail leverage temperature | Medium | Eastmoney / AkShare | Better as weekly / daily confirmation, not thesis anchor |
| Credit-risk proxy basket (property developers / brokers / small-cap beta) | Confirm | A-share substitute for weak-credit tape; shows whether risk capital is willing to own fragile balance sheets | Medium | Eastmoney sector quotes + selected names | Prefer basket or spread-style read over one stock |
| ETF subscriptions / redemptions | Confirm | Institutional demand for style buckets | Medium-Low | Fund issuer pages / Eastmoney | Good to add later |
| Main-force net inflow | Optional | Can help with sector

references/core-panels-and-sources.md

# Core Panels and Sources

Purpose: keep one compact reference for the V1/VNext panel hierarchy, key indicators, and practical source mapping.

Use this file when maintaining the skill, refining the data layer, or checking whether a panel belongs in the daily engine, weekly engine, or monthly background layer.

## 1) Product scope

This workflow is a first-layer macro environment engine.
It helps with:
- liquidity
- rates
- credit
- FX
- breadth / internal structure
- A-share transmission
- U.S. and China macro-to-execution translation

It does not replace second-layer execution judgment:
- exact asset
- exact level
- exact size
- discretionary trading nuance

## 2) Daily engine: required layers

### U.S. core
Use these as the default P0 daily stack:
- Fed net liquidity
- ON RRP balance
- 2s10s
- 3m10y
- 10Y TIPS real yield
- HY OAS
- DXY / dollar proxy
- USDJPY
- WTI
- VIX
- 10Y nominal yield
- IWM / SPY
- RSP / SPY
- KRE / SPY
- SPHB / SPLV

### A-share core
Use these as the default P0 daily stack:
- USDCNY or USDCNH
- northbound flow or valid proxy
- CSI300 vs CSI1000
- ChiNext vs CSI300
- breadth and turnover
- China liquidity anchor (DR007 or Shibor)
- China rates curve proxy
- property leader basket
- joint-stock banks vs big state banks
- HK / offshore China confirmation

## 3) Weekly / monthly extensions

### Weekly U.S.
Useful confirmation layer:
- initial jobless claims
- 5Y5Y or breakeven inflation
- EPS revision momentum
- broader breadth metrics
- housing / consumer high-frequency set
- thematic ETF flow proxies
- IG / CCC / EMB stress proxies

### Weekly China
Useful confirmation layer:
- DR007 / Shibor persistence
- China 10Y-1Y curve proxy
- credit impulse proxy
- property high-frequency sales
- HK China assets confirmation

### Monthly background
Use for slower regime calibration:
- QT progress
- financial conditions index
- ISM / PMI decomposition
- NFIB / business confidence
- China monthly credit impulse
- China property investment and sales
- global PMI split
- SLOOS

## 4) A-share transmission additions

### Internal structure
Most important A-share daily reads:
- CSI300 vs CSI1000
- ChiNext vs CSI300
- breadth
- turnover
- northbound continuity

### Flow / who is buying
Prefer:
- northbound day + continuity
- margin financing change
- style / sector destination when available
- ETF style flow as confirm, not thesis anchor

Daily stabilization rule:
- if northbound truth is unavailable or upstream values are clearly invalid, replace it with a northbound proxy built from Stock Connect breadth, style relative strength, and offshore China-beta confirmation
- do not keep northbound truth as a routine daily hard gap if the proxy is available

### Sector / single-name baskets
Use baskets, not isolated names:
- property
- joint-stock banks vs big state banks
- brokers
- machinery
- transport / logistics
- heavy-truck proxy
- premium consumer vs mass consumer
- credit-sensitive basket

Daily proxy policy:
- use these baskets to buil

Github ReposUpdated 8h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.