Real Skill packageSource verifiedClawHub registry

股票投资价值评分 / Stock Portfolio Investment Scoring

分析A股自选与持仓，获取行情、财报、风险与新闻，按行业计算价值评分和独立交易环境分，输出基本面情景估值、数据缺口及受用户风险政策约束的配置参考，并生成离线HTML报告。适用于股票诊断、持仓复盘、投资价值评分和组合配置请求；不自动下单。 English — Deterministic value scoring and allocation for China A-share watchlists and holdings; sector-routed scoring, separate trading-environment score, scenario-based fundamental valuation, explicit data-gap reporting and constrained allocation reference; renders an offline HTML report. Pure Python stdlib, 77 unit tests. Not investment advice.

Identity and source

Publisher attributionHoLauvregistry owner unverified by skillvetai
Functional categoryData, Spreadsheets & Analyticsautomatically inferred · 63% rule confidence
Package forminstruction with code29 recorded files
Canonical sourceClawHub registryclawhub:holauv:stock-portfolio-advisor
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 9/15/2026.claude/skills/stock-portfolio-advisor

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 9/15/2026.agents/skills/stock-portfolio-advisor

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 9/15/2026skills/stock-portfolio-advisor

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @holauv/stock-portfolio-advisor
clawhub inspect @holauv/stock-portfolio-advisor --version 2.4.0

Security evidence

SkillVetAI static result: no findings detected

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
28 / 29 inspected as text
Checked
9/15/2026, 5:09:15 PM
Scanner
0.1.3
Policy
1.0.3
3 inferred permission indicators
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
6 dependency and API indicators
  • api: clawhub.ai
  • api: github.com
  • api: img.shields.io
  • api: pages.stern.nyu.edu
  • api: www.sse.com.cn
  • api: www.w3.org
External clawhub result: suspicious

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
9/14/2026, 3:46:21 PM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:7a7b7f47c236f536f53441d7db4757be0e100e97c3b99bd24e5229a8c78bf4c4
Show up to 29 recorded paths
  • assets/icon.png
  • assets/icon.prompt.md
  • assets/report.css
  • CHANGELOG.md
  • config/backtest_strategy.json
  • config/calibration.json
  • config/weights.json
  • LICENSE
  • README.md
  • references/backtesting.md
  • references/data-playbook.md
  • references/indicator-mapping.md
  • references/scoring-model.md
  • references/valuation-review-2026-09-05.md
  • scripts/backtest.py
  • scripts/build_backtest_dataset.py
  • scripts/build_report.py
  • scripts/calibrate_weights.py
  • scripts/make_demo_data.py
  • scripts/package_skill.py
  • scripts/portfolio_ledger.py
  • scripts/run_calibration.py
  • scripts/score_engine.py
  • scripts/test_backtest.py
  • scripts/test_value_model.py
  • scripts/value_model.py
  • scripts/weight_registry.py
  • skill-card.md
  • SKILL.md

Source changelog

v2.4.0 缺失数据不再"一缺全灭"：大盘温度 3 项即可出分 + 个股观测项缺失给中性兜底 【大盘温度：≥3 项即可出分，按可用项权重归一】 此前 market_temperature() 要求「均线 / 成交额 / 涨跌广度 / 破净比例」四项全齐才输出温度， 缺任意一项整个温度分就变成 null（"数据不足"）——等于让缺一个指标掩盖掉另外三个已有信息。 现改为拿到 ≥3 项即出分，分母改用可用项的权重和归一；不足 3 项才仍为"数据不足"。 输出新增 coverage（可用权重占比）、used / missing（用上 / 缺失的项）、min_items（门槛=3）， notes 写明"温度分由 N/4 项按权重归一得出（可用权重 …，覆盖率 …%）"。 示例：故意只给 3/4 项 → 旧口径"数据不足"，新口径按 82.4% 覆盖率归一给出 70.0 分（偏热）。 【个股观测项缺失：不再一律计 0，改为中性默认分 60 兜底】 此前 score_dimension() 对缺失项直接计 0，即"缺一项 = 该项得 0 分"， 数据完整度不同的标的分数无法比较——而本技能的核心用法恰恰是跨快照跟踪评分变化。 现把缺失处置拆成固定优先级的四层： 1. 补数据：按取数手册把字段取回来（首选）； 2. 派生：能从原始数据算的就自己算，本版新增 np_yoy 由净利润TTM / 去年同期利润派生 （两侧 period_end 需相差约一年，防拿错窗口硬算）； 3. 结构性缺失（IMPUTE 白名单：forecast / industry_boom）按总体期望分插补（沿用 2.2.0）； 4. 观测项缺失（公司应披露的财务 / 资金 / 技术项）按 MISSING_FILL 兜底， 默认 'neutral'：给中性默认分 60（NEUTRAL_FALLBACK=60），仍留在计分分母里。 两个分母是分开的：all_weight（适用项权重）只算 coverage，used_weight（实际计分权重）只算 score。 neutral 下两者相等，所以兜底不抬高覆盖率，…

Release security diff

mediumCompared fixed releases 0.1.0 and 2.4.0; 0 finding and 0 permission indicators were added.

Both fixed releases were scanned under the current scanner and policy, so finding, permission and dependency changes are available.

Change reasons and limitations
  • file surface changed
  • content hash changed

Observed release history

These older immutable releases were observed by prior successful syncs. They remain recorded when a newer release becomes current.

0.1.09/7/2026sha256:263209499a85cffd261d274a42bbc631ddc594834baa8f4c6093626b7b4c018e