← 返回 Skills 市场
buxibuxi

Stock Copilot Pro

作者 dxj · GitHub ↗ · v0.3.0
cross-platform ✓ 安全检测通过
2572
总下载
6
收藏
16
当前安装
14
版本数
在 OpenClaw 中安装
/install stock-copilot-pro
功能描述
OpenClaw stock analysis skill for US/HK/CN markets. Combines QVeris data sources (THS, Caidazi, Alpha Vantage, Finnhub, X sentiment) for quote, fundamentals,...
安全使用建议
This skill appears to do what it says: it routes multi-source market queries through QVeris and needs only the QVERIS_API_KEY. Before installing, confirm you trust QVeris (qveris.ai) because the skill will make outbound requests there and that service in turn may query other provider APIs on your behalf. Provide an API key with the minimum scope possible and monitor its use. Review the infra/qveris-client.mjs (included in the package) if you want to confirm which endpoints are contacted and how the key is attached. Be aware the skill stores a local watchlist and a small evolution state file inside the skill folder; these do not contain credentials per the README, but you may want to place the skill in an isolated environment if you plan to run scheduled/autonomous jobs. Finally, if you want maximum caution, run first-time executions interactively (not as an automated cron) and verify observed network requests match expectations.
功能分析
Type: OpenClaw Skill Name: stock-copilot-pro Version: 0.3.0 The OpenClaw AgentSkills skill bundle 'stock-copilot-pro' is classified as benign. It demonstrates robust security practices, particularly in restricting all outbound network communication to `https://qveris.ai` (enforced by `scripts/lib/infra/qveris-client.mjs` and verified by `tests/architecture-modules.test.mjs`). File system writes are strictly confined to `config/watchlist.json` and `.evolution/tool-evolution.json` within the skill directory, and sensitive data (like API keys) is actively redacted from logs and persisted state. Prompt instructions in `SKILL.md` and `README.md` are benign, guiding the AI agent to generate reports based on the skill's output, with explicit directives for data grounding and transparency, and include XSS prevention for custom report blocks. There is no evidence of intentional harmful behavior or significant vulnerabilities.
能力评估
Purpose & Capability
The skill is a multi-source stock analysis tool that routes queries through the QVeris gateway; requesting a single QVERIS_API_KEY is appropriate. The code files implement quote/fundamentals/technicals/sentiment logic and watchlist/brief/radar features consistent with the description. Minor note: metadata described the package as “instruction-only” but the package contains many code files and a local-skill-execution runtime — this is an implementation detail rather than a security mismatch.
Instruction Scope
SKILL.md and the code instruct the agent to call QVeris tools and to read/write only local skill files (watchlist and evolution state). Runtime behavior (tool discovery, executeTool, resolveToolPayload) is scoped to QVeris calls and content fetches are restricted to qveris.ai. The skill does not instruct reading unrelated system files or additional env vars.
Install Mechanism
No external installers or remote downloads are required; install mechanism is local-skill-execution and code is included in the package. This keeps install risk low. There are no extract-from-URL installs or third-party package downloads in the provided metadata.
Credentials
Only QVERIS_API_KEY is required and is the primary credential, which is proportional to a skill that calls the QVeris MCP/API gateway. The SKILL.md states the key is used in a read-only scope and the code indicates no other credentials are read/persisted. (You should treat the key as sensitive and restrict its scope if possible.)
Persistence & Privilege
The skill persists only to files inside its own directory (config/watchlist.json and .evolution/tool-evolution.json) and does not request always:true or system-wide changes. Auto-invocation is enabled by default but that is the platform default; the skill does include example cron jobs in the repo (informational) which could schedule recurring runs if the user configures them.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install stock-copilot-pro
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /stock-copilot-pro 触发
  4. 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
v0.3.0
Frontmatter: compact inline runtime/install/persistence/security to avoid VirusTotal scan pending; semantics unchanged.
v0.2.9
- Added .evolution/README.md and .evolution/tool-evolution.json files to enable evolution parameter memory and tracking. - Now supports tool evolution v2 parameter-template memory for reduced recurring parameter errors. - Officially tracks skill evolution details in a dedicated .evolution directory for improved maintainability.
v0.2.8
Add standard metadata.openclaw block for ClawHub registry credential/env detection
v0.2.7
Fix ClawHub security scan mismatch by explicitly declaring credentials, runtime, install mechanism, persistence boundaries, and network/full-content host restrictions in SKILL metadata.
v0.2.6
Fix ClawHub security scan mismatch by explicitly declaring credentials, runtime, install mechanism, persistence boundaries, and network/full-content host restrictions in SKILL metadata.
v0.2.5
Improve professional output quality with mandatory data snapshot tables, QVeris source attribution, and structured source summaries for analyze/brief/radar flows.
v0.2.4
Security hardening while preserving full_content_file_url behavior: kept full-content retrieval, added strict host allowlist (qveris.ai + HTTPS), aligned SKILL metadata credential schema, updated README/SKILL security disclosures, added regression tests for blocked non-qveris full_content_file_url, and documented safeguards in CONTEXT.md.
v0.2.3
Unify OpenClaw workflow: structured data output plus LLM-guided analysis. Enhanced single-stock/brief/radar guidance in SKILL.md, improved SEO discoverability with capabilities and data-source sections in docs, and strengthened brief metadata for OpenClaw report generation.
v0.2.2
增强中文公司名动态解析(ths_ifind code_converter),并新增回归测试数据与批量校验脚本。
v0.2.1
- Added `--evidence` flag to enable optional evidence sections in analyst reports. - CN/HK fundamentals workflow now always retrieves company basics for profile backfill (fields like `industry`, `mainBusiness`, `tags`). - Expanded documentation to clarify optional full evidence trace output. - Introduced initial automated test script: `scripts/stock_copilot_pro.test.mjs`.
v0.2.0
- Introduced deterministic tool routing via the new references/tool-chains.json for more reliable analysis flows. - Added sector benchmarks reference data (references/sector-benchmarks.json) to enhance context in reports. - Upgraded evolution system to v2: stores parameter templates and samples to prevent recurring parameter errors. - Analyst reports now include value-investing scorecard, timing classification, safety-margin estimate, and scenario-based suggestions. - SKILL.md and documentation expanded to detail routing logic, evolution changes, and new report components.
v0.1.2
CN/HK upgrade: company-name routing, caidazi news/report sentiment, THS financial statements prioritization, and stronger fundamentals validation.
v0.1.1
Security hardening: aligned credential metadata, minimized evolution persistence, stricter output redaction.
v0.1.0
Initial release of Stock Copilot Pro — a global stock analysis tool powered by QVeris. - Integrates market quote, fundamentals, technicals, news sentiment, and X sentiment. - Automatic symbol normalization for US, HK, CN, and global stocks. - Dynamic tool learning with fallback strategies and report quality checks. - Produces structured markdown or JSON reports for analyst or machine use. - Prioritizes transparency, data integrity, and credential safety. - Command-line interface supports comprehensive single or multi-symbol analysis.
元数据
Slug stock-copilot-pro
版本 0.3.0
许可证
累计安装 18
当前安装数 16
历史版本数 14
常见问题

Stock Copilot Pro 是什么?

OpenClaw stock analysis skill for US/HK/CN markets. Combines QVeris data sources (THS, Caidazi, Alpha Vantage, Finnhub, X sentiment) for quote, fundamentals,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 2572 次。

如何安装 Stock Copilot Pro?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install stock-copilot-pro」即可一键安装,无需额外配置。

Stock Copilot Pro 是免费的吗?

是的,Stock Copilot Pro 完全免费(开源免费),可自由下载、安装和使用。

Stock Copilot Pro 支持哪些平台?

Stock Copilot Pro 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 Copilot Pro?

由 dxj(@buxibuxi)开发并维护,当前版本 v0.3.0。

💬 留言讨论