← 返回 Skills 市场

HK IPO Snapshot Extractor

Name: HK IPO Snapshot Extractor
Author: hackstoic

作者 hackstoic · GitHub ↗ · v0.1.0 · MIT-0

cross-platform ✓ 安全检测通过

总下载

当前安装

版本数

在 OpenClaw 中安装

/install hkipo-snapshot-extractor

功能描述

Extract a structured Hong Kong IPO snapshot with company fields, offer mechanics, timing, source provenance, and field-level quality signals. Use when the us...

使用说明 (SKILL.md)

HK IPO Snapshot Extractor

Use this skill for read-only single-symbol analysis.

Runtime

This publish bundle includes the required CLI runtime under runtime/hkipo-next.

From the skill folder:

cd \x3Cskill_dir>
uv run --directory runtime/hkipo-next hkipo-next ...

Workflow

Run snapshot for the target symbol.
Use --format json when another skill will consume the result.
Check issues, quality.missing_fields, quality.conflicts, and quality.overall_confidence before making strong claims.
Build human summaries from the normalized fields instead of paraphrasing raw upstream pages.

Commands

Machine-readable snapshot:

cd \x3Cskill_dir>
uv run --directory runtime/hkipo-next hkipo-next snapshot 2476 --format json

Readable markdown snapshot:

cd \x3Cskill_dir>
uv run --directory runtime/hkipo-next hkipo-next snapshot 2476 --format markdown

Export a snapshot file:

cd \x3Cskill_dir>
uv run --directory runtime/hkipo-next hkipo-next snapshot 2476 --format markdown --output /tmp/2476-snapshot.md

Output Cues

field_sources shows which upstream source won per field.
quality.conflicts exposes alternate values when sources disagree.
meta.degraded or meta.data_status=partial usually means the snapshot is usable with caveats, not unusable.

Companion Skills

Use $hkipo-parameter-manager before scoring if the user wants to tune rules.
Use $hkipo-decision-engine when the user wants a participation recommendation.

安全使用建议

This skill appears coherent: it bundles a Python CLI that scrapes and normalizes HK IPO data and requires the 'uv' runner. Before installing, be aware it will perform outbound web requests to multiple public endpoints (AAStocks, AiPO, HKEX, Sina/Tencent APIs, etc.) and will write cache/sqlite files under the runtime directory. If you need to limit network access, run it in a sandbox or on a machine where outbound connections are acceptable. Also review the Homebrew 'uv' formula on your platform before installing and confirm that using the upstream data sources complies with your data-use policies.

功能分析

Type: OpenClaw Skill Name: hkipo-snapshot-extractor Version: 0.1.0 The skill is a comprehensive financial analysis tool designed to extract and score Hong Kong IPO data. It fetches information from legitimate public sources such as HKEX, AAStocks, Jisilu, and Yahoo Finance. The codebase includes a refactored CLI (hkipo-next) and legacy scraping scripts, utilizing a local SQLite database for storing scoring parameters and review history, and a local file cache in the user's home directory. No evidence of data exfiltration, malicious execution, or prompt injection was found; the use of environment variables for API tokens and local configuration is consistent with the tool's stated purpose.

能力评估

✓ Purpose & Capability

Name/description match the delivered artifacts: a Python CLI (runtime/hkipo-next) that fetches IPO data from public sources (AAStocks, AiPO, HKEX, Jisilu, Futu, etc.). The only declared binary dependency is 'uv' which is used to run the bundled runtime; no unrelated cloud credentials or system-level access are requested.

ℹ Instruction Scope

Runtime instructions are narrow and read-only from the user's perspective (run the packaged CLI to produce JSON/markdown snapshots). The code does perform many outbound HTTP requests (including token extraction from aipo.myiqdii.com, calls to suggest/sina and qt.gtimg APIs, WebSocket mention for AAStocks), and it can create cache/storage files (sqlite/cache) under the runtime. Those network calls and local caching are expected for this skill but the user should know the skill will contact multiple external services and may persist cached data locally.

✓ Install Mechanism

Install spec only requests a Homebrew formula 'uv' (used as the runtime runner). This is a standard package-manager install rather than an arbitrary archive download. No installers reference shorteners, personal servers, or extraction of unknown archives.

✓ Credentials

The skill declares no required environment variables or credentials. The code performs unauthenticated or site-token-based scraping of public web APIs; no unrelated secrets (AWS, GitHub tokens, etc.) are requested.

ℹ Persistence & Privilege

always:false and normal autonomous-invocation settings. The bundle includes caching and a sqlite storage layer (writes under runtime/hkipo-next), which is proportionate to a data-fetching CLI. It does not request to modify other skills or system-wide agent settings.

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 hkipo-snapshot-extractor
安装完成后，直接呼叫该 Skill 的名称或使用 /hkipo-snapshot-extractor 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

v0.1.0

Initial ClawHub release

元数据

Slug hkipo-snapshot-extractor

版本 0.1.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题