← 返回 Skills 市场

HK IPO Review Optimizer

Name: HK IPO Review Optimizer
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-review-optimizer

功能描述

Review past Hong Kong IPO decisions, update actual outcomes, export review datasets, and accept or reject tuning suggestions. Use when the user wants to lear...

使用说明 (SKILL.md)

HK IPO Review Optimizer

Use this skill for the post-decision feedback loop.

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 ...

By default review history is stored in ~/.hkipo-next/data/hkipo.db.

Workflow

Use review list to find target records.
Use review show before updating a record.
Use review update to add actual results and variance notes.
Use review export when another tool needs a JSON dataset.
Use apply-suggestions show before accepting or rejecting imported suggestions.

Commands

List recent review records:

cd \x3Cskill_dir>
uv run --directory runtime/hkipo-next hkipo-next review list --limit 20 --format json

Show a record:

cd \x3Cskill_dir>
uv run --directory runtime/hkipo-next hkipo-next review show rvw_123 --format json

Update actual results:

cd \x3Cskill_dir>
uv run --directory runtime/hkipo-next hkipo-next review update rvw_123 \
  --allocated-lots 2 \
  --listing-return-pct 14.2 \
  --exit-return-pct 9.8 \
  --realized-pnl-hkd 1860 \
  --notes "Sold into first-day strength" \
  --variance-note "Grey market was weaker than expected but sponsor demand held" \
  --format json

Export a review dataset:

cd \x3Cskill_dir>
uv run --directory runtime/hkipo-next hkipo-next review export --from 2026-04-01 --to 2026-04-16 --output /tmp/hkipo-review.json --format text

Preview and accept a suggestion:

cd \x3Cskill_dir>
uv run --directory runtime/hkipo-next hkipo-next apply-suggestions show sgg_123 --format json
uv run --directory runtime/hkipo-next hkipo-next apply-suggestions accept sgg_123 --reason "Matches observed listing-day slippage" --format json

Output Cues

Review records preserve the original prediction payload, data status, and source issue count.
Suggestion detail output shows whether a proposed change would create a new parameter version.

Companion Skills

Use $hkipo-parameter-manager when a review conclusion needs manual tuning work.
Use $hkipo-decision-engine to rerun fresh decisions after a rule change.

安全使用建议

This skill bundles an entire CLI runtime and will: (1) write/read a local sqlite DB at ~/.hkipo-next/data/hkipo.db, and (2) make outbound HTTP requests to multiple public IPO data sources (AAStocks, AiPO, HKEX, Tencent APIs, etc.). No credentials are requested, which is proportionate, but you should: verify the skill's source/author (no homepage/source provided), inspect the bundled runtime if you can, and confirm the Homebrew 'uv' formula provenance before installing. If you are cautious, run it in an isolated environment (container or VM), back up or sandbox ~/.hkipo-next/data/hkipo.db, and monitor outbound network connections during first runs.

功能分析

Type: OpenClaw Skill Name: hkipo-review-optimizer Version: 0.1.0 The hkipo-review-optimizer skill is a legitimate tool designed for analyzing Hong Kong IPO data and tracking investment decisions. It fetches financial data from public sources such as HKEX, AAStocks, and Jisilu, and manages a local SQLite database (~/.hkipo-next/data/hkipo.db) to store review history and scoring parameters. The codebase is well-structured, utilizing Pydantic for data validation and standard libraries for networking and storage, with no evidence of data exfiltration, malicious execution, or harmful prompt injection instructions.

能力评估

✓ Purpose & Capability

Name/description (post-decision IPO review, export datasets, accept/reject suggestions) align with the declared requirements: it needs a CLI runner ('uv') and a local DB (~/.hkipo-next/data/hkipo.db) to store review history. The bundled code implements data fetchers, exporters, and review/apply-suggestion commands that match the described functionality.

ℹ Instruction Scope

SKILL.md instructs the agent to run the included CLI (uv run --directory runtime/hkipo-next hkipo-next ...). That runtime reads/writes the configured DB path and makes outbound HTTP(S) requests to public data sources (aipo.myiqdii.com, aastocks.com, hkex, Tencent APIs, etc.). This network activity is expected for the stated purpose, but users should be aware the skill will perform external requests and parse tokens/pages as part of normal operation.

ℹ Install Mechanism

Install spec is a single Homebrew formula 'uv' that creates a 'uv' binary; this is proportional to the runtime instructions which expect 'uv'. Homebrew is a standard distribution channel, but you should verify which 'uv' formula is being installed (provenance) before proceeding.

✓ Credentials

The skill declares no environment variables or secrets and lists only a single config path (~/.hkipo-next/data/hkipo.db). The code does not require unrelated credentials. Network calls are made to public data sources (no embedded secret exfiltration fields).

✓ Persistence & Privilege

always:false and user-invocable: true. The skill stores review history in its own DB path under the user's home directory and does not request elevated or cross-skill privileges. It does not modify other skills' configs according to the bundle.

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

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