← 返回 Skills 市场
Stock Picker Orchestrator
作者
Nguyễn Đức Thành
· GitHub ↗
· v1.0.2
700
总下载
1
收藏
6
当前安装
3
版本数
在 OpenClaw 中安装
/install stock-picker-orchestrator
功能描述
Acts as a meta-orchestrator that routes stock-analysis requests across data, macro/news, and valuation skills under explicit budget controls; used when users...
安全使用建议
This skill is an instruction-only orchestrator and appears coherent with its purpose, but it delegates all network access and credential use to the downstream skills it names (vnstock-free-expert, news/macro monitors, equity-valuation-framework, etc.). Before installing or invoking it: 1) verify those dependent skills are trustworthy and review their required env vars/API keys; 2) test the orchestrator in a safe environment to confirm budget limits behave as expected; 3) if you need tighter control, restrict autonomous invocation or require explicit user approval before running high-budget/deep pipelines; and 4) note that absence of code meant the static scanner had nothing to analyze — that reduces installer risk but also means you should inspect the workspace for the named skills' behavior and endpoints.
功能分析
Type: OpenClaw Skill
Name: stock-picker-orchestrator
Version: 1.0.2
The skill bundle is benign. Both `SKILL.md` and `agents/openai.yaml` consistently instruct the AI agent to operate with transparency, strict budget controls (e.g., API call limits, free-tier pacing), and responsible reporting (mandatory output contract, confidence rubric). It explicitly warns against presenting uncertain outputs as facts, self-modifying user data, or providing absolute buy/sell instructions. There is no evidence of prompt injection attempts to subvert the agent's behavior, exfiltrate data, execute arbitrary commands, or establish persistence. The instructions actively promote ethical and cautious AI behavior.
能力评估
Purpose & Capability
The name/description (meta-orchestrator for stock analysis) aligns with the SKILL.md: it routes requests to other specialized skills and enforces budget/pacing. It does not request unrelated binaries, credentials, or config paths. The fact that dependencies are named in the markdown rather than formally declared is a bookkeeping issue but not a functional mismatch.
Instruction Scope
The SKILL.md stays on-scope: it classifies intent, selects pipelines, enforces vnstock/news/valuation budgets, and mandates a structured output. It does not instruct reading local files or harvesting unrelated env vars. Note: it delegates network/API work to downstream skills — those skills (not this orchestrator) will perform the actual data fetches, so the security posture depends on them as well.
Install Mechanism
No install spec or code is included (instruction-only), so nothing is downloaded or written to disk by this skill itself. That minimizes installation risk.
Credentials
This skill declares no required environment variables or credentials, which is appropriate because it orchestrates other skills that will hold their own API keys. The SKILL.md references vnstock rate limits and 'community API key' only as policy guidance — not as required secrets for this skill itself.
Persistence & Privilege
always is false and model invocation is allowed (platform default). The skill does not request persistent system-wide changes or modify other skills' configs. Autonomous invocation will let it call downstream skills, which is expected for an orchestrator.
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 stock-picker-orchestrator - 安装完成后，直接呼叫该 Skill 的名称或使用
/stock-picker-orchestrator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
v1.0.2
**Expanded portfolio risk management and governance in orchestration logic**
- Added `portfolio-risk-manager` as a required skill dependency.
- Enhanced the "Portfolio Refresh" workflow to include running risk manager for IPS mini, position sizing, and ticker-level triggers.
- Added rule: when user provides holdings/watchlist, only propose drafts—do not self-modify.
- Updated governance section to clarify single source of truth behavior for user holdings.
- Other clarifications to ensure risk controls and output trustworthiness.
v1.0.1
**Expanded documentation and scope note, plus added compatibility section and trigger examples.**
- Clarified that this skill coordinates other skills and does not replace their domain logic.
- Added a new compatibility section specifying required dependencies in the workspace.
- Reorganized workflow into an explicit 7-step execution process.
- Included new trigger example queries for clarity.
- No changes to core orchestration logic or routing policies.
v1.0.0
- Initial release of the Stock Picker Orchestrator skill.
- Supports end-to-end stock analysis by selecting and sequencing relevant data, macro, news, and valuation skills.
- Enforces API and news data budgets based on user tier and preset risk levels.
- Classifies user intent into distinct modes (deep dive, screening, macro/news investigation, portfolio refresh) and orchestrates appropriate analysis pipelines.
- Standardizes outputs with clear sections: data fetched, pipeline choice, assumptions, results, confidence/gaps, risk flags, and next steps.
- Applies consistent confidence scoring, conflict resolution, and governance to ensure transparent, reproducible recommendations.
元数据
常见问题
Stock Picker Orchestrator 是什么？
Acts as a meta-orchestrator that routes stock-analysis requests across data, macro/news, and valuation skills under explicit budget controls; used when users... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 700 次。
如何安装 Stock Picker Orchestrator？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install stock-picker-orchestrator」即可一键安装，无需额外配置。
Stock Picker Orchestrator 是免费的吗？
是的，Stock Picker Orchestrator 完全免费（开源免费），可自由下载、安装和使用。
Stock Picker Orchestrator 支持哪些平台？
Stock Picker Orchestrator 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 Stock Picker Orchestrator？
由 Nguyễn Đức Thành（@ndtchan）开发并维护，当前版本 v1.0.2。
推荐 Skills