← 返回 Skills 市场
uwillberich
作者
huangrichao2020
· GitHub ↗
· v0.1.12
· MIT-0
254
总下载
0
收藏
0
当前安装
13
版本数
在 OpenClaw 中安装
/install a-share-decision-desk
功能描述
Build next-session A-share game plans from market structure, overnight macro shocks, policy timing, and watchlist leadership. Use when the user asks what A-s...
使用说明 (SKILL.md)
uwillberich
Author: 超超
Contact: [email protected]
Overview
Use this skill for decision-oriented A-share analysis. The goal is not to explain the market mechanically, but to convert today’s tape and overnight developments into a concrete next-session plan.
Best fit:
- next-session A-share outlook
- likely repair sectors after a selloff
- opening checklist for
09:00,09:25, and09:30-10:00 - first-30-minute observation template for distinguishing true repair from defensive concentration
- watchlist-based decision notes
- distinguishing defensive leadership from true market repair
- persistent message iteration that maps high-attention news into watchlist overlays
- automatic event-driven stock pools that feed directly into desk reports
- main-force capital-flow confirmation for watchlists and market-wide risk tone
- industry-chain expansion that turns event themes into fresh stock pools
- sentiment scoring built from breadth, sector dispersion, and capital flow
Core Workflow
- Gather market structure first.
- Confirm
EM_API_KEYis configured before running any script. - Run
scripts/fetch_market_snapshot.pyfor indices, breadth, and sector leaders/laggards. - Run
scripts/fetch_quotes.pyorscripts/morning_brief.pyfor the watchlist.
- Confirm
- Confirm the overnight and policy layer.
- Use primary sources first for
PBOC,Federal Reserve, and other central-bank decisions. - Use high-quality news sources for geopolitics, oil, and global risk sentiment.
- Use primary sources first for
- Classify the market through three layers.
- External shock: oil, rates, U.S. equities, geopolitics
- Domestic policy/liquidity:
LPR, PBOC posture, macro support - Internal structure: breadth, leadership, relative strength, style rotation
- Build a scenario tree.
- Provide
Base / Bull / Bearpaths with explicit triggers and invalidations.
- Provide
- Turn the view into an execution checklist.
- Include
09:00,09:20-09:25,09:30-10:00, and14:00-14:30.
- Include
Workflow Shortcuts
Step 1: overnight and policyscripts/mx_toolkit.py preset --name preopen_policyscripts/mx_toolkit.py preset --name preopen_global_risk
Step 2: board resonancescripts/fetch_market_snapshot.pyscripts/capital_flow.pyscripts/market_sentiment.pyscripts/mx_toolkit.py preset --name board_optical_modulescripts/mx_toolkit.py preset --name board_compute_power
Step 3: single-name validationscripts/fetch_quotes.pyscripts/mx_toolkit.py preset --name validate_inspurscripts/mx_toolkit.py preset --name validate_luxshare
Step 4: event-to-chain expansionscripts/industry_chain.pyscripts/news_iterator.py
Source benchmarkscripts/benchmark_sources.py
Decision Heuristics
- Prefer sectors that resisted best in a weak tape over sectors that merely fell the most.
- Treat defensive leadership as separate from broad market repair.
- On monthly
LPRdays, use the09:00release as a hard branch in the plan. - A repair thesis is stronger when leadership broadens from core growth names into secondary names and brokers.
- A rebound without breadth is usually just a technical bounce.
Scripts
Use these scripts before writing the decision note:
scripts/fetch_market_snapshot.py- Pulls Eastmoney index and sector breadth data.
scripts/fetch_quotes.py- Pulls Tencent quote snapshots for user-specified names.
scripts/morning_brief.py- Builds a markdown brief from the default watchlists in
assets/default_watchlists.json.
- Builds a markdown brief from the default watchlists in
scripts/capital_flow.py- Pulls the whole-market main-force snapshot plus top inflow/outflow names and intersects them with watchlists.
scripts/market_sentiment.py- Scores the tape as
抱团行情,科技修复,修复扩散, or分化偏弱using breadth, sector dispersion, and capital flow.
- Scores the tape as
scripts/opening_window_checklist.py- Builds a first-30-minute observation sheet with time gates, group scoreboards, and watchlist signal tables.
scripts/industry_chain.py- Uses event summaries and desk groups to expand into industry-chain stock pools through live MX stock screens.
scripts/news_iterator.py- Continuously polls public RSS feeds, classifies high-attention events, maps them into watchlist overlays, and writes dynamic event-driven stock pools.
scripts/runtime_config.py- Loads local runtime credentials, enforces the required
EM_API_KEY, and prints the Eastmoney application URL when it is missing.
- Loads local runtime credentials, enforces the required
scripts/mx_toolkit.py- Calls the live Meixiang / Eastmoney APIs for news search, stock screening, structured data queries, and preset desk workflows.
scripts/benchmark_sources.py- Benchmarks public and MX-enhanced sources before you decide what to trust as the primary feed.
scripts/install_news_iterator_launchd.py- Installs the news iterator as a
launchdjob on macOS for long-running local polling.
- Installs the news iterator as a
scripts/smoke_test.py- Verifies that the bundled scripts and public endpoints are working.
References
Read only what you need:
references/methodology.md- Trading philosophy, decision tree, and timing gates.
references/data-sources.md- Source map for official and market data endpoints.
references/persona-prompt.md- Decision-maker persona for desk-style answers.
references/trading-mode-prompt.md- Time-boxed opening workflow for the next A-share session.
references/opening-window-template.md- A reusable first-30-minute decision template.
references/cross-cycle-watchlist.md- How to use the cross-cycle core stock pool without turning it into an unfocused mega-list.
references/event-regime-watchlists.md- How to use war-shock and energy-spike watchlists as temporary overlays.
references/message-iterator.md- How to run the persistent RSS iterator, generate event-driven stock pools, and feed them into the desk workflow.
assets/mx_presets.json- Preset MX workflows for policy scan, global-risk scan, board resonance, and single-name validation.
assets/industry_chains.json- Theme-to-chain map for optical module, compute power, semiconductors, robotics, oil and coal, and IDC/power-cost overlays.
Output Standard
Default to a compact desk-style answer:
- one-paragraph decision summary
Base / Bull / Bearpath- most likely repair sectors
- defensive-only sectors
- opening checklist
do / avoid
Required Credential
EM_API_KEYis mandatory for this skill.- Apply here:
https://ai.eastmoney.com/mxClaw - After opening the link, click download and you will see the key.
- Official site:
https://ai.eastmoney.com/nlink/ - Store it in
~/.uwillberich/runtime.env
安全使用建议
This skill appears to do what it claims (A-share pre-open research) and uses expected APIs (Eastmoney, Tencent, MX, public RSS), but note two red flags: 1) the registry metadata omitted the required EM_API_KEY while SKILL.md/README say it is mandatory — confirm the key requirement before installing; 2) the package can persist locally (writes ~/.uwillberich/, creates SQLite/jsonl, and can install a launchd job). Before installing or running scripts: - Inspect scripts/runtime_config.py to see how it stores/reads your API key and whether it transmits it only to the documented endpoints. - Check any code that calls mkapi2.dfcfs.com (MX endpoint) to confirm the exact requests and whether your key is used only for intended queries. - If you don't want persistent polling, do not run install_news_iterator_launchd.py or the news_iterator loop; run one-off scripts only. - Avoid running install scripts as root; restrict runtime file permissions (store runtime.env with 600). - If you have operational or regulatory concerns about sending data to third-party endpoints, test the scripts in a network-controlled environment or review network calls in detail. If you want, I can inspect specific script files (runtime_config.py, mx_toolkit.py, news_iterator.py, install_news_iterator_launchd.py) and summarize exactly what HTTP requests they make and what they store locally.
功能分析
Type: OpenClaw Skill
Name: a-share-decision-desk
Version: 0.1.12
The 'uwillberich' skill bundle is a comprehensive financial analysis tool designed for A-share market decision-making. It utilizes legitimate data sources including Tencent (qt.gtimg.cn), Eastmoney (push2.eastmoney.com), and the Meixiang API (mkapi2.dfcfs.com) to provide market snapshots, capital flow analysis, and sentiment scoring. While the bundle includes a persistence mechanism for macOS via `scripts/install_news_iterator_launchd.py` to poll RSS feeds in the background, this behavior is explicitly documented and serves the stated purpose of continuous news monitoring. The handling of sensitive credentials (EM_API_KEY) is managed locally through `scripts/runtime_config.py` without evidence of exfiltration. No malicious code, obfuscation, or harmful prompt injection attempts were detected.
能力评估
Purpose & Capability
The skill’s stated purpose (A-share pre-open analysis) matches the included scripts and assets (Eastmoney/Tencent data pulls, watchlists, RSS iterator). However the registry metadata claims 'Required env vars: none' while SKILL.md and README repeatedly state the skill hard-requires an EM_API_KEY (maps to MX_APIKEY). That metadata mismatch is incoherent and could mislead users about credential needs.
Instruction Scope
SKILL.md instructs the agent/user to run many local Python scripts that: call Eastmoney (push2.eastmoney.com), Tencent quote endpoints (qt.gtimg.cn), MX endpoints (mkapi2.dfcfs.com), and public RSS feeds; write outputs (markdown/jsonl/SQLite) under ~/.uwillberich/; and can install a long-running news iterator. Those actions are consistent with the stated purpose but they read and persist local runtime credentials (~/.uwillberich/runtime.env) and create local state files — review those scripts before running.
Install Mechanism
No remote install spec is included in the registry entry (instruction-only). The repo bundles Python scripts (standard-library oriented) rather than providing an automatic remote download. Risk is lower than packages that fetch arbitrary binaries, but running bundled scripts still executes code on your machine — inspect before running.
Credentials
The skill legitimately needs an Eastmoney/MX API key (EM_API_KEY / MX_APIKEY) to access market and MX endpoints — that single credential is proportionate to its function. The concern is that the registry metadata omitted this requirement, and the scripts suggest writing the key to ~/.uwillberich/runtime.env and mapping it to MX_APIKEY automatically. Confirming what runtime_config.py does (read/write behavior, permissions, storage format) is advised.
Persistence & Privilege
The skill includes scripts to run a persistent news iterator and a macOS launchd installer for scheduled polling; it writes state under ~/.uwillberich/news-iterator/ and can run background processes. It does not request 'always: true' or system-wide privilege changes in the metadata, but installing a background job is a non-trivial persistence action — the user should opt in explicitly and inspect launchd install code before use.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install a-share-decision-desk - 安装完成后，直接呼叫该 Skill 的名称或使用
/a-share-decision-desk触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v0.1.12
- Updated the project homepage URL in metadata to the new repository location.
- No user-facing functional or workflow changes.
v0.1.11
- Skill renamed from "a-share-decision-desk" to "uwillberich."
- All documentation and references updated to reflect the new name, including credential path (`~/.uwillberich/runtime.env`).
- No functional changes to core features or workflow.
- Maintains A-share pre-open decision toolkit and its script suite.
v0.1.10
- Added author and contact information to documentation.
- Improved and clarified documentation in SKILL.md and README.md.
- No functional code changes were made to core scripts.
- General polishing of descriptive and reference sections for better usability.
v0.1.9
**Major expansion: Adds capital flow, industry-chain, and sentiment features.**
- NEW: Added scripts for market capital flow, industry chain expansion, and sentiment scoring.
- ENHANCED: Workflow now covers main-force capital-flow checks, theme/industry-chain pool generation, and sentiment scoring.
- UPDATED: Documentation and shortcuts to reflect new features and scripts.
- NEW: Added `assets/industry_chains.json` for event-to-industry chain mapping.
- FIXED: Improved required credential instructions and updated script coverage.
v0.1.8
Version 0.1.8 of a-share-decision-desk introduces a more capable and credential-aware workflow.
- Added new scripts: `benchmark_sources.py`, `mx_api.py`, `mx_toolkit.py`, and `runtime_config.py` for MX/Eastmoney API integration, benchmarking, and credential enforcement.
- Introduced `assets/mx_presets.json` for preset policy/news/board/single-name workflow shortcuts.
- Updated documentation to require `EM_API_KEY`, with setup instructions in the README and SKILL.md.
- Expanded workflow overview and added a new "Workflow Shortcuts" section for operational efficiency.
- Updated script explanations and references for new MX and benchmarking utilities.
v0.1.7
Auto-build event-driven stock pools from news alerts and append them to the morning brief and opening checklist.
v0.1.6
Added a persistent RSS message iterator with local SQLite state, rolling markdown reports, and launchd deployment support.
v0.1.5
Added war_shock_core12, a compact 12-name wartime overlay for oil, coal, compute, IDC, and power.
v0.1.4
Added war-shock overlay watchlists for oil and coal beneficiaries plus compute and power headwind groups.
v0.1.3
Added cross-cycle core stock pools, anchor12 daily watchlist, themed rotation buckets, and usage guidance.
v0.1.2
Added a first-30-minute opening checklist workflow, time-gate template, and watchlist signal matrix.
v0.1.1
Polished listing text, added smoke test, and excluded cache files from publish payloads.
v0.1.0
A-share-decision-desk 0.1.0 – Initial Release
- Introduces a structured workflow to analyze and plan for the next A-share session using real-time index, breadth, sector, and policy data.
- Provides integrated scripts for market snapshot, watchlist updates, and morning briefs.
- Emphasizes scenario planning: Base/Bull/Bear paths with clear triggers and invalidations.
- Includes heuristics for sector selection and repair-thesis development.
- Offers a reusable checklist format for pre-market and intraday decision making.
元数据
常见问题
uwillberich 是什么？
Build next-session A-share game plans from market structure, overnight macro shocks, policy timing, and watchlist leadership. Use when the user asks what A-s... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 254 次。
如何安装 uwillberich？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install a-share-decision-desk」即可一键安装，无需额外配置。
uwillberich 是免费的吗？
是的，uwillberich 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
uwillberich 支持哪些平台？
uwillberich 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 uwillberich？
由 huangrichao2020（@huangrichao2020）开发并维护，当前版本 v0.1.12。
推荐 Skills