← Back to Skills Marketplace
1054
Downloads
2
Stars
1
Active Installs
31
Versions
Install in OpenClaw
/install 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 Revie...
Usage Guidance
This skill appears coherent for producing macro morning briefs and related modes. Before installing or running it: 1) be aware it performs outbound network requests to public data providers (Yahoo, Stooq, FRED proxies, optional finshare/akshare); ensure that network access is acceptable for your environment. 2) The skill writes cache files by default into the skill directory (.runtime/market-snapshots); do not set STANLEY_RUNTIME_DIR to a sensitive system path. 3) Optional dependencies (finshare, akshare) can be installed to improve coverage; review those third-party packages and their auth requirements before installing. 4) If you supply a FRED API key, limit its scope and treat it as a secret. 5) Run the skill in a sandbox or with limited privileges if you want to audit its network behavior first. Overall, the skill implements what it claims and does not request unrelated credentials or hidden privileges.
Capability Analysis
Type: OpenClaw Skill
Name: stanley-druckenmiller-workflow
Version: 1.1.11
The 'stanley-druckenmiller-workflow' skill bundle is a legitimate financial analysis tool designed to generate market briefs and regime assessments. The core logic in `scripts/market_panels.py` fetches macro and equity data from public sources (Yahoo Finance, FRED, Stooq, and AkShare) using standard HTTP requests and implements a localized caching system in a `.runtime` directory. The instructions in `SKILL.md` define a complex analytical persona and workflow without any evidence of malicious prompt injection, data exfiltration, or unauthorized system access.
Capability Assessment
Purpose & Capability
The skill claims to be a macro-to-execution market workflow and the included code (market_panels.py), README, and reference docs implement data fetching, panel construction, and evidence protocols for U.S. and A-share markets. Data sources and libraries (Yahoo, Stooq, FRED proxies, AkShare, optional finshare) align with the stated purpose; nothing requested or present appears unrelated to producing market briefs.
Instruction Scope
SKILL.md constrains output style and evidence rules and does not instruct the agent to read unrelated system files. The code will perform network requests to public data endpoints and may write cache files under the skill directory (.runtime/market-snapshots). SKILL.md and README reference optional environment variables (FINSHARE_MODE, FRED_API_KEY, STANLEY_RUNTIME_DIR) and the code honors them; these are reasonable for data-source selection and runtime path override but should be noted (see guidance).
Install Mechanism
There is no install spec bundled with the skill. README suggests optional pip installs (finshare, akshare) for additional data coverage; that is a normal, low-risk developer instruction. The skill itself does not download or execute arbitrary archives or external installers.
Credentials
The skill declares no required env vars or credentials. The README and SKILL.md reference optional env vars (FINSHARE_MODE, FRED_API_KEY, STANLEY_RUNTIME_DIR). Requiring a FRED API key is proportional to improved macro-series quality; FINSHARE_MODE toggles optional behavior. The runtime-dir override allows writing cache anywhere if the user sets STANLEY_RUNTIME_DIR — reasonable but worth caution. No unrelated secrets or cross-service tokens are requested.
Persistence & Privilege
always:false and no platform-level persistence is requested. The code writes runtime cache inside the skill folder by default; that is scoped and reversible. The only elevated behavior is the ability to change the runtime path via STANLEY_RUNTIME_DIR if explicitly set by the user—this is a user-controlled option, not automatic.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install stanley-druckenmiller-workflow - After installation, invoke the skill by name or use
/stanley-druckenmiller-workflow - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.11
Aligned output granularity with the latest structure: replaced the old CAR block with fixed Consensus Decomposition, hardened U.S. Internal Structure into a checklist-style required section, and made Sector Expression explicitly require top/bottom sector ranking plus confirmation from key leading baskets.
v1.1.10
Added explicit U.S. leading market-internal basket (Russell 2000, homebuilders, transports, retail, regional banks, industrial metals/copper) as required inspection set for U.S. internal structure. These baskets are now treated as economic telltales, not optional side notes.
v1.1.9
Expanded the U.S. internal structure layer with equal-weight, small-cap, high-beta, sector leadership, and breadth confirmation rules so U.S. briefs now carry the same tape/structure depth as the upgraded A-share version.
v1.1.8
Expanded the A-share internal structure layer with breadth, limit-up/limit-down, new highs/lows, median-stock-return proxies, turnover change, and explicit top/bottom industry expression requirements so daily briefs read more like real A-share tape and sector structure work.
v1.1.7
Replaced CAR Snapshot anti-consensus with Open Attack Surface and aligned the base skill to work alongside a separate challenger layer instead of forcing fake contrarian takes.
v1.1.6
Tightened Morning Brief opening logic into three hard rules: event selection, market interpretation, and headline-driven ordering, making briefs less vacuum-sealed and more responsive to obvious market-moving events.
v1.1.5
Removed stale hardcoded macro-event examples from the opening-layer rules and tightened Big Events logic so daily briefs stay fresh, implication-first, and market-relevant for both A-share and U.S. outputs.
v1.1.4
Added visible published-version line to SKILL.md for markdown-only clients and refined Big Events rules so stale macro headlines move into background regime context unless the market is actively repricing them again.
v1.1.2
Refined Big Events opening layer to rank overnight developments by actual market transmission relevance; A-share briefs no longer default to a fixed U.S. macro trio and now explicitly include China policy, ECB/BOJ, RMB, HK, and commodity relevance when they matter.
v1.1.1
Added Big Events / Main Theme / Underpriced Risks opening layer for A-share and U.S. briefs, improved event-first framing, and fixed framework numbering.
v1.1.0
Promote to v1.1.0: adopt the new PM-note morning brief structure with Macro Position Snapshot, Primary Drivers Today, CAR Snapshot, Top Breakouts / Key Moves, and Sizing Ladder for both A-share and U.S. workflows, with clearer section responsibilities and cleaner daily hierarchy.
v1.0.19
Adopt the latest PM-note structure: add Macro Position Snapshot and Primary Drivers Today for both A-share and U.S. briefs, tighten role separation between Regime / Drivers / CAR, and add a Sizing Ladder to both markets for more explicit conviction scaling.
v1.0.18
Refine daily PM-note structure: add Macro Position Snapshot, move CAR Snapshot and Top Breakouts to the front for both A-share and U.S. briefs, enforce one dominant thesis, and keep breakout ordering stable by decision relevance.
v1.0.17
Refine daily memo structure to feel more like a PM morning note: enforce one dominant thesis, move CAR Snapshot and Top Breakouts to the front, compress slow-moving nowcast layers by default, and require natural judgment language instead of raw proxy labels in final output.
v1.0.16
Refine A-share domestic-demand layer for daily use: compress 5.4 into a default status-based nowcast with one-line composite read, and only expand sub-blocks when data updates, the thesis changes, or the market is actively trading that layer.
v1.0.15
Simplify safety-footer rule: keep one standard disclaimer rendered in the resolved user language instead of duplicating separate Chinese and English variants.
v1.0.14
Complete English-only cleanup across all visible skill files, including the remaining A-share tape reference and human-facing script labels/output fields, while preserving parser compatibility for Chinese upstream data sources.
v1.0.13
English-only documentation cleanup: convert SKILL.md, README.md, and core-panels-and-sources reference fully to English while preserving multilingual output behavior and trigger logic.
v1.0.12
Add formal language-resolution policy: explicit instruction > account preference > current-session habit > platform locale > message-language detection, with persistence and conflict rules for multilingual users.
v1.0.11
Add formal News Validation module for both A-share and U.S. workflows, with source priority, lightweight verification rules, and explicit supports/conflicts/noise guidance.
Metadata
Frequently Asked Questions
What is 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... It is an AI Agent Skill for Claude Code / OpenClaw, with 1054 downloads so far.
How do I install Stanley Druckenmiller Workflow?
Run "/install stanley-druckenmiller-workflow" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Stanley Druckenmiller Workflow free?
Yes, Stanley Druckenmiller Workflow is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Stanley Druckenmiller Workflow support?
Stanley Druckenmiller Workflow is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Stanley Druckenmiller Workflow?
It is built and maintained by luckycatL (@luckycatl); the current version is v1.1.11.
More Skills