openclaw-skills/sec-filing-reviewer/SKILL.md
Use when reviewing SEC filings, extracting material risk disclosures, scanning 10-K or 10-Q sections, or building a follow-up checklist from filing language.
npx skillsauth add seaworld008/commonly-used-high-value-skills sec-filing-reviewerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
在数百页的冗长文件中,精准捕捉被隐藏的控制风险、流动性危机、法律纠纷及重大会计披露。本技能旨在帮助分析师从 10-K, 10-Q, 8-K 等 SEC 官方文件中提取关键变量,并识别出那些可能被市场忽视的“红旗”信号(Red Flags)。
# 确保已安装 EDGAR 数据处理库
pip install sec-edgar-downloader sec-parser beautifulsoup4
# 下载审计脚本
npx clawhub install sec-filing-reviewer
sec-parser 定位并提取核心章节:
scripts/review_filing.py。Going concern (持续经营能力), Material weakness (重大缺陷), Restatement (重报), Investigation (调查), Qualified opinion (保留意见)。DSO (应收账款周转天数) 变动进行交叉验证。MEMORY.md,供下次业绩电话会或投资者关系(IR)调研使用。{
"cik": "0000320193",
"filing_type": "10-K",
"fiscal_year": 2025,
"sections_to_scan": ["Risk Factors", "Legal", "MD&A"],
"focus_keywords": ["Cybersecurity", "Litigation", "Inventory write-down"]
}
### 🚩 SEC 文件审计报告:[TSLA] 10-Q (2026 Q1)
**1. 重大风险变更 (What's New in Risks)**:
- **新增项**: 明确提及了 X 地区的自动驾驶监管准入风险。
- **变更项**: 删除了关于“供应链已经常态化”的描述。
**2. 财务红旗信号 (Red Flags)**:
- **审计控制**: 🟢 无重大缺陷报告。
- **诉讼更新**: ⚠️ 发现一例涉及专利侵权的新增集体诉讼,金额未披露。
- **流动性**: 现金储备稳健,但存货积压较去年同期上升 15%。
**3. 管理层语气 (MD&A Tone)**:
- 针对资本开支的描述比上季度更显激进,重点强调 AI 算力投入。
**4. 建议跟进问题 (Investor Questions)**:
- 1) 存货积压是否主要来自 X 型号的排产过剩?
- 2) 新增诉讼的拨备计划是否已在当前利润表中体现?
**5. 最终评级**: **中性 (加强监控)**
# 自动抓取并审计最新的 10-K 摘要
python scripts/review_filing.py --cik 320193 --type 10-K --report audit_report.md
sec.gov 直接抓取,而非通过不可靠的第三方采集平台。MEMORY.md。development
Enumerating failure modes via pre-mortem analysis. Systematically identifies failure scenarios for plans, designs, and features, scoring them with RPN/AP. Does not write code.
testing
Orchestrating specialist AI agent teams as a meta-coordinator. Decomposes requests into minimum viable chains, spawns each as an independent session in AUTORUN modes, and drives to final output. Use when a task spans multiple specialist domains, requires parallel agent execution, or needs hub-and-spoke routing across the skill ecosystem.
development
Converting document formats (Markdown/Word/Excel/PDF/HTML). Converts specs from Scribe and reports from Harvest into distributable formats; generates reusable conversion scripts. Use when converting documents, building accessibility-compliant PDFs, or creating Pandoc/LibreOffice pipelines.
testing
Curating cross-agent knowledge and guarding institutional memory. Extracts patterns from agent journals into METAPATTERNS.md, detects knowledge decay, propagates best practices, prevents organizational forgetting. Use when consolidating cross-agent insights, curating memory, or auditing knowledge decay.