← Back to Skills Marketplace
quant-buddy-skill
by
pseudo-longinus
· GitHub ↗
· v4.14.18
· MIT-0
241
Downloads
0
Stars
0
Active Installs
22
Versions
Install in OpenClaw
/install quant-buddy-skill
Description
查询A股、港股、美股股票及指数的最新收盘价、开盘价、涨跌幅、成交额、成交量、换手率、PE、PB、市值等实时行情与估值数据。 查询最近N个交易日的价格序列、日涨跌幅序列、窗口最高价、最低价、振幅等短期统计。 查询上市公司最近报告期的营业收入、净利润、归母净利润、ROE、总资产、资产负债率等财务指标（A股）。 支持A...
Usage Guidance
This skill appears internally consistent: it is a market-data/quant research tool that legitimately needs a quant-buddy API key (kept in config.json) and an optional Bocha API key for news. Before installing, consider these actions: 1) Review the shipped Python scripts (especially scripts/call.py and scripts/quant_api.py) if you want to confirm the API key is only sent to the declared quantbuddy endpoints and not logged or forwarded elsewhere. 2) Keep the config.json (which will contain your api_key) in a secure location — the key is stored on-disk in the skill directory, so treat that file like a secret. 3) Only paste the sk- API key into the skill when you trust the skill and host; avoid sharing credentials in chat messages. 4) If you do not use the optional event-study news feature, you do not need to set BOCHA_API_KEY. If you want an even stronger assurance, run the skill in a restricted environment or inspect outbound network calls during a controlled test to verify endpoint usage.
Capability Analysis
Type: OpenClaw Skill
Name: quant-buddy-skill
Version: 4.14.18
The skill bundle is a comprehensive quantitative finance tool for analyzing A-share, HK, and US stock markets. The Python scripts (scripts/call.py, scripts/executor.py) act as a standard API wrapper for the quantbuddy.cn platform, using safe subprocess calls and standard libraries for network requests. The extensive documentation and workflow files (SKILL.md, workflows/*.md) contain highly prescriptive instructions for the AI agent to ensure data integrity, 'evidence-only' reporting, and session isolation, which are consistent with a professional financial tool. No evidence of data exfiltration, malicious execution, or unauthorized persistence was found; all network activity is confined to the declared endpoints (quantbuddy.cn and bochaai.com).
Capability Tags
Capability Assessment
Purpose & Capability
Name/description match the requested artifacts: the skill is a quantitative market-data tool and it requires a quant-buddy API key (stored in config.json) and an optional Bocha news API key for an optional feature. The large set of presets/workflows is coherent for a quant research skill.
Instruction Scope
SKILL.md directs the agent to read the skill's config and workflow files, create a local session, and call local Python scripts or native platform tools to fetch data. Those actions are consistent with the stated tasks. The only runtime file the skill asks to read is config.json (declared); it does instruct reading many local presets/workflows (which are part of the skill) — expected for workflow routing and formula lookups.
Install Mechanism
No install spec is provided (instruction + shipped Python scripts). Runtime uses Python 3.8+ and lists optional Python packages (python-dateutil, Pillow). No external download URLs or installers are present in the metadata.
Credentials
The skill requests one primary credential (quant-buddy API Key stored in config.json) and an optional BOCHA_API_KEY for an optional feature — proportional to its functionality. The SKILL.md asserts the API key will only be sent as an Authorization header to the declared quantbuddy endpoints and not logged or forwarded; this is plausible but cannot be independently verified without auditing the shipped scripts (notably scripts/call.py and scripts/quant_api.py).
Persistence & Privilege
always is false (not force-included). The skill stores its API key in config.json within the skill directory (declared). It does not request system-wide or unrelated credential access or try to modify other skills' configuration in the provided docs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install quant-buddy-skill - After installation, invoke the skill by name or use
/quant-buddy-skill - Provide required inputs per the skill's parameter spec and get structured output
Version History
v4.14.18
quant-buddy-skill 4.14.18
- 增加 metadata 字段，丰富了技能元信息，包括类别、标签、依赖等内容
- 无功能和行为变更
- 版本号自 4.14.17 升级至 4.14.18
v4.14.17
Declare Python package dependencies in metadata: python-dateutil (optional, event-study feature) and Pillow (optional, saveChart fallback). Version 4.14.17. No runtime changes.
v4.14.16
quant-buddy-skill v4.14.16
- Clarify credential transport in metadata per review: api_key is transmitted as HTTP Authorization header to the declared networkEndpoints only; removed ambiguous "not transmitted" wording. Also: endpoint migrated from test.quantbuddy.cn to www.quantbuddy.cn. No runtime behavior changes.
v4.14.15
- Enhanced skill metadata to clarify runtime, credential, config, and environment variable requirements.
- Switched credential and environment variable declarations to a more structured YAML format.
- Updated quant-buddy API Key configuration guidance and login URL for accuracy.
- Added explicit fields for runtime Python version and endpoint domains.
- No logic code or workflow changes; documentation alignment only.
v4.14.14
Updated skill metadata for ClawHub review compliance: added primaryEnv and requiredCredentials in SKILL frontmatter, aligned credential declaration with runtime requirement (quant-buddy API key in config.json), and bumped version to 4.14.14. No user-facing behavior changes.
v4.14.13
quant-buddy-skill 4.14.13
- 修正硬规则新建 session 时 user_query 的传参说明，使其仅用于本地 session 初始化标注，完善 trace 分析用途。
- 其他内容无变动。
v4.14.12
quant-buddy-skill v4.14.12
- 投稿新规则：调用 newSession 时，必须传递 user_query 参数以便与用户问题关联
- 其他内容与上一版一致，无功能或接口变更
v4.14.11
quant-buddy-skill 4.14.11
- Updated credential handling: the quant-buddy API Key is now only read from config.json (environment variable support removed), with stricter documentation to reflect this.
- Clarified credential descriptions and storage locations, reducing ambiguity and guiding correct configuration.
- No changes to Python package requirements or tool behavior.
v4.14.10
- Added required and description fields to the environment variable QUANT_BUDDY_API_KEY in requirements, making it explicitly required for all data queries.
- Clarified and described the purpose of both QUANT_BUDDY_API_KEY (required) and BOCHA_API_KEY (optional) in requirements.
- No functional or logic changes to code or workflows—documentation and metadata update only.
v4.14.9
quant-buddy-skill v4.14.9
- Added "slug" and "author" fields to skill metadata for improved identification.
- Reduced and clarified the credentials and requirements sections for easier integration.
- Updated wording in the skill manifest for better readability, without affecting any core logic or user-facing behavior.
- No code or business logic changes—functionality remains the same as previous version.
v4.14.8
- Improved credentials section for clarity: each API key now has a detailed description and source guidance.
- QUANT_BUDDY_API_KEY is now explicitly required; optional fallback to config.local.json remains.
- Clarified requirements on API key presence for data queries.
- No functional or behavioral changes; documentation and metadata only.
v4.14.7
- Expanded API key handling: now supports environment variable QUANT_BUDDY_API_KEY (recommended), with config.json/config.local.json fallback.
- Updated credentials and compatibility docs to clarify recommended and fallback key sources, promoting zero key storage by default.
- Improved security documentation: empty config.json template, guidance not to commit real keys, and preference for env vars or config.local.json.
- Requirements section now documents environment variables and handling for both QUANT_BUDDY_API_KEY and BOCHA_API_KEY.
- No behavior changes to core data queries or workflow logic.
v4.14.6
**Summary: Improved config privacy and optional event-study web search.**
- Added references/scripts-audit.md reference document.
- Updated compatibility section: clarified config.local.json support for api_key (not packaged by default).
- Added optional Bocha web-search integration for event-study; only activates if BOCHA_API_KEY is set.
- Expanded requirements/compatibility sections with details on script behavior, config, and network usage.
- No changes to core query or workflow logic.
v4.14.5
quant-buddy-skill v4.14.5
- Removed all files under scripts/auth/ (auth helpers for API key setup)
- Updated documentation to reflect that only API key from config.json is used for authentication
- Clarified that no phone/SMS/PII collection is required; users obtain API key via website
- Updated compatibility and credentials sections in SKILL.md accordingly
v4.14.4
**quant-buddy-skill 4.14.1 → 4.14.4：新增 API Key 检查与新手引导，强化配置流程**
- 增加硬规则：所有查数类场景，收到新问题必须第一步检查 config.json 中 api_key 是否配置，未配置时输出新用户引导并禁止继续执行其他操作。
- 丰富硬规则说明，明确遇到 API Key 缺失时的处理流程，避免无意义失败调用。
- 现有6条硬规则扩展为7条，新增第0条为 API Key 检查。
- metadata 版本号从 4.14.0 升级到 4.14.4。
- 其余功能、业务场景路由和使用流程未做变更。
v4.14.0
**Summary: Introduces a new "Fast Path" for commonly used workflows, updates compatibility info, and refines routing.**
- Added fast route workflows for snapshot, window series, and recent report period queries (`workflows/fast-snapshot.md`, `fast-window.md`, `fast-report-period.md`).
- Added a fast-load ruleset (`workflows/global-rules-lite.md`) to optimize routing and execution for quick numeric/stat queries.
- Added a tool-call checklist (`recipes/tool-call-checklist.md`) for safe, minimal data tool invocation.
- Updated compatibility section: quant-buddy API key must be from https://test.quantbuddy.cn; clarified API scoping and security.
- Refined execution sequence and global error handling (rate limits, quotas).
- Updated scenario routing tables, specifying when to use fast vs. full workflows.
- config.json ships with an empty api_key field — users must obtain their own key after install. The file contains no sensitive data.
v1.0.5
quant-buddy-skill 1.0.5
- API host in skill description changed from guanzhao12.com to test.guanzhao12.com.
- Data queries now use HTTP instead of HTTPS and reference the test server domain.
- No code changes; SKILL.md metadata and documentation only.
v1.0.4
quant-buddy-skill 1.0.4
- Added interactive authentication scripts under scripts/auth/ for one-time API key setup.
- Included setup, login, registration, and SMS code utilities (not required for normal usage).
- Normal data queries are unchanged and do not invoke or require these scripts.
- Clarified documentation to note authentication scripts are for first-time API key binding only.
v1.0.3
- Removed all interactive authentication and registration scripts (scripts/auth/), including _auth_wizard.py, _login.py, _register.py, _send_code.py, and setup.py.
- Now requires the API key to be manually obtained outside the skill and written into config.json before use; authentication via in-skill interactive flow is no longer supported.
- Updated compatibility and workflow rules to reflect the change: skill never collects, registers, or requests API keys or user authentication details.
- Minor metadata updates to include homepage and source repository information.
v1.0.2
- Removed 7 internal scripts and evaluation files, including core API and evaluation scripts.
- No changes to user-facing workflows or documented interfaces.
- The skill package is now lighter, with only essential execution scripts retained.
- No impact to main functionality or usage; standard quantitative research and data query features remain unchanged.
Metadata
Frequently Asked Questions
What is quant-buddy-skill?
查询A股、港股、美股股票及指数的最新收盘价、开盘价、涨跌幅、成交额、成交量、换手率、PE、PB、市值等实时行情与估值数据。 查询最近N个交易日的价格序列、日涨跌幅序列、窗口最高价、最低价、振幅等短期统计。 查询上市公司最近报告期的营业收入、净利润、归母净利润、ROE、总资产、资产负债率等财务指标（A股）。 支持A... It is an AI Agent Skill for Claude Code / OpenClaw, with 241 downloads so far.
How do I install quant-buddy-skill?
Run "/install quant-buddy-skill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is quant-buddy-skill free?
Yes, quant-buddy-skill is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does quant-buddy-skill support?
quant-buddy-skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created quant-buddy-skill?
It is built and maintained by pseudo-longinus (@pseudo-longinus); the current version is v4.14.18.
More Skills