Description

从 SEC EDGAR 批量抓取上市公司年报（10-K）和季报（10-Q）文件，支持按季度增量更新与本地缓存，适用于美股基本面分析和量化研究数据获取。。

README (SKILL.md)

EDGAR 文件抓取 (edgar-crawler)

Name: Edgar Crawler
Author: tangweigang-jpg

从 SEC EDGAR 批量抓取上市公司年报（10-K）和季报（10-Q）文件，支持按季度增量更新与本地缓存，适用于美股基本面分析和量化研究数据获取。

Pipeline

data_collection -> data_storage -> factor_computation -> target_selection -> trading_execution -> visualization

Top Use Cases (1 total)

SEC EDGAR Filing Extraction (`UC-101`)

Extracts and processes SEC EDGAR filings (10-K annual reports, 10-Q quarterly reports) from compressed ZIP archives for downstream financial analysis Triggers: EDGAR, SEC filings, 10-K extraction

Execute trigger: When user intent matches intent_router.uc_entries[].positive_terms AND user uses action verb (run/execute/跑/执行/backtest/fetch/collect)

What I'll Ask You

Target market: A-share (default), HK, or crypto? (US stocks in ZVT are half-baked — stockus_nasdaq_AAPL exists but coverage is thin)
Data source / provider: eastmoney (free, no account), joinquant (account+paid), baostock (free, good history), akshare, or qmt (broker)?
Strategy type: MACD golden-cross, MA crossover, volume breakout, fundamental screen, or custom factor?
Time range: start_timestamp and end_timestamp for backtest period
Target entity IDs: specific stocks (stock_sh_600000) or index components (SZ1000)?

Semantic Locks (Fatal)

ID	Rule	On Violation
`SL-01`	Execute sell orders before buy orders in every trading cycle	halt
`SL-02`	Trading signals MUST use next-bar execution (no look-ahead)	halt
`SL-03`	Entity IDs MUST follow format entity_type_exchange_code	halt
`SL-04`	DataFrame index MUST be MultiIndex (entity_id, timestamp)	halt
`SL-05`	TradingSignal MUST have EXACTLY ONE of: position_pct, order_money, order_amount	halt
`SL-06`	filter_result column semantics: True=BUY, False=SELL, None/NaN=NO ACTION	halt
`SL-07`	Transformer MUST run BEFORE Accumulator in factor pipeline	halt
`SL-08`	MACD parameters locked: fast=12, slow=26, signal=9	halt

Full lock definitions: references/LOCKS.md

Top Anti-Patterns (14 total)

AP-DATA-SOURCING-001: Missing or invalid User-Agent headers for SEC API requests
AP-DATA-SOURCING-002: Ignoring external API rate limits causing IP blocking
AP-DATA-SOURCING-003: No HTTP timeout configuration causing indefinite hangs

All 14 anti-patterns: references/ANTI_PATTERNS.md

Evidence Quality Notice

[QUALITY NOTICE] This crystal was compiled from blueprint finance-bp-114. Evidence verify ratio = 32.9% and audit fail total = 29. Generated results may have uncaptured requirement gaps. Verify critical decisions against source files (LATEST.yaml / LATEST.jsonl).

Reference Files

File	Contents	When to Load
references/seed.yaml	V6+ 全量权威 (source-of-truth)	有行为/决策争议时必读
references/ANTI_PATTERNS.md	14 条跨项目反模式	开始实现前
references/WISDOM.md	跨项目精华借鉴	架构决策时
references/CONSTRAINTS.md	domain + fatal 约束	规则冲突时
references/USE_CASES.md	全量 KUC-* 业务场景	需要完整示例时
references/LOCKS.md	SL-* + preconditions + hints	生成回测/交易代码前
references/COMPONENTS.md	AST 组件地图（按 module 拆分）	查 API 时

Compiled by Doramagic crystal-compilation-v6.1 from finance-bp-114 blueprint at 2026-04-22T13:00:54.950360+00:00. See human_summary.md for non-technical overview.

Usage Guidance

This skill is internally inconsistent: it advertises an SEC EDGAR batch crawler but most of its references and runtime checks are for a ZVT/A‑share backtesting pipeline and it names Python/zvt as prerequisites without declaring any install steps or required environment variables. Before installing or invoking: 1) Ask the publisher to clarify the primary purpose (EDGAR vs ZVT) and to provide an explicit install spec (which Python version, pip/uv commands, and packages such as zvt). 2) Require a clear list of environment variables and credentials the skill will use (e.g., ZVT_HOME, any API tokens), and do not provide secrets until that list is confirmed. 3) Request that they remove unrelated trading/backtest 'semantic locks' if the package is only intended for EDGAR crawling. 4) Verify network behavior: confirm how it will call EDGAR (User-Agent handling, rate limiting, timeouts) to avoid accidental IP blocks or data exfiltration. If the author cannot clearly explain these mismatches, treat the skill as untrusted and do not run it in a privileged or production environment.

Capability Analysis

Type: OpenClaw Skill Name: edgar-crawler Version: 0.3.3 The edgar-crawler skill bundle is a comprehensive data sourcing tool designed to fetch and parse SEC EDGAR filings (10-K, 10-Q, 8-K) for financial analysis. The bundle contains extensive documentation and instructions (SKILL.md, seed.yaml) that enforce strict data integrity rules, such as mandatory User-Agent identification for SEC compliance (finance-C-006), exponential backoff for rate limiting (SHARED-DS-RL-001), and the prevention of look-ahead bias in trading signals (SL-02). No evidence of malicious intent, unauthorized data exfiltration, or harmful prompt injection was found; all identified behaviors and constraints are consistent with the stated purpose of high-quality financial data procurement and quantitative research.

Capability Tags

cryptorequires-walletrequires-sensitive-credentials

Capability Assessment

⚠ Purpose & Capability

SKILL.md and metadata present the skill as an EDGAR (US 10-K/10-Q) crawler, but the included human_summary, seed.yaml, and many reference files repeatedly refer to ZVT, A‑share, eastmoney/joinquant/akshare, and backtesting/ trading semantics. The skill claims Python 3.12+ with the 'uv' package manager in the compatibility block but the registry shows no required binaries or install spec. This mismatch suggests the bundle is a mashup of two different blueprints (EDGAR vs ZVT) and the declared purpose does not justify the referenced dependencies and domain constraints.

⚠ Instruction Scope

The SKILL.md instructs the agent to re-read seed.yaml, consult references/LOCKS.md and other local reference files, run preconditions (python -c checks that call zvt), and follow an execution_protocol that implies installing recipes and running environment checks. Yet the skill registry declares no required config paths, binaries, or install steps. Instructions also embed trading 'semantic locks' and preconditions unrelated to raw EDGAR crawling (e.g., T+1 rules, MACD parameter locks). The instructions thus go beyond a narrow EDGAR download task and request actions (running Python checks, relying on zvt and ZVT_HOME) that are not declared.

ℹ Install Mechanism

There is no install spec (instruction-only), which is lowest-risk in isolation. However SKILL.md and seed.yaml reference an install_trigger and require Python 3.12+ and the 'uv' package manager and expect 'zvt' to be present. The absence of an explicit install recipe is inconsistent and leaves unclear what, if anything, the agent will attempt to install or require at runtime.

⚠ Credentials

The registry lists no required environment variables, yet SKILL.md/seed.yaml and preconditions reference ZVT_HOME and expect zvt to be initialized. The skill also describes integration with multiple data providers (eastmoney, joinquant, akshare, SEC EDGAR) — some of which require tokens/accounts — but it does not declare any credentials. This mismatch (using env/config values but not declaring them) is an incoherence risk because the runtime behavior may implicitly rely on user credentials or environment settings not surfaced to the installer.

✓ Persistence & Privilege

always is false and disable-model-invocation is false (normal). The skill does instruct the agent to read local packaged reference files and run preconditions, but there is no request for persistent system-wide privileges or an 'always' install. No evidence it tries to modify other skills or system configs.

Version History

v0.3.3

v0.3.3: bilingual metadata injected. H1 shows EDGAR 文件抓取; tagline replaced with skill-specific Chinese hook; tags upgraded to Level 1-4.

v0.3.1

Remove install.sh — knowledge-only bundle. Host AI consumes directly from URL; no user-side installation needed. Fixes ClawHub suspicious flag.

v0.3.0

Doramagic crystal portfolio v0.3.0. Full 5-layer bp-009 standard. github.com/tangweigang-jpg/doramagic-skills

Metadata

Slug edgar-crawler

Version 0.3.3

License MIT-0

All-time Installs 0

Active Installs 0

Total Versions 3

Frequently Asked Questions

What is Edgar Crawler?

从 SEC EDGAR 批量抓取上市公司年报（10-K）和季报（10-Q）文件，支持按季度增量更新与本地缓存，适用于美股基本面分析和量化研究数据获取。。 It is an AI Agent Skill for Claude Code / OpenClaw, with 120 downloads so far.

How do I install Edgar Crawler?

Run "/install edgar-crawler" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Edgar Crawler free?

Yes, Edgar Crawler is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Edgar Crawler support?

Edgar Crawler is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Edgar Crawler?

It is built and maintained by Tang Weigang (@tangweigang-jpg); the current version is v0.3.3.

More Skills

Edgar Crawler