القائمة
US SEC EDGAR filings — list 10-K/10-Q/8-K/Form 4/S-1, fetch filing text, parse insider Form 4 transactions.
يُحدَّد Prompt الذي يراجع المصدر أولًا بشكل افتراضي. يمكنك التبديل إلى أمر مباشر أو تنزيل نسخة محلية.
اقرأ SKILL.md وأي ملفات مرافقة يعرضها SkillsMP قبل أن تقرر التثبيت.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
يتجاوز الأمر المباشر Prompt المخصّص للمراجعة. افحص المصدر قبل تشغيله.
npx skills add https://github.com/kansoku-trade/kansoku --skill sec-edgarيبقى الأمر في سطر واحد. مرّر أفقيًا لمراجعته كاملًا قبل النسخ.
تفضّل نسخة محلية؟ نزّل الملفات المتاحة حاليًا لدى SkillsMP.
Render financial charts via the local chart web app (workspace at the repo root — Hono server + React front end, port 1792). Four chart types: intraday capital-flow line (`flow`) and cross-symbol signed-bar comparison (`cohort`) — both Recharts — plus SEPA strategy dashboard (`sepa`) and short-term multi-timeframe prediction dashboard (`intraday`) — both TradingView Lightweight Charts. Multi-timeframe K-line review lives inside `intraday` (the standalone kline chart type was removed). The server fetches Longbridge data itself (kline / capital flow) and computes all indicators (MA, MACD, RS, trend template, volume profile, divergence/beichi detection) in TypeScript; the caller only POSTs `{type, symbol, ...}` to `/api/charts` and gets back `{id, url, technicals?}`. Charts persist as data JSON under `journal/charts/data/`. `url` now points at where the chart actually lives: sepa/intraday land on the symbol page (`http://localhost:1792/symbol/<SYM>?analysis=<id>`), flow/cohort land on the home page for that date
Short-term multi-timeframe (5m/15m/1h) technical read for a single symbol — pulls K-line across three timeframes, reads MACD + swing structure, writes a direction call (long/short/neutral) with an explicit anchor price, a 2–4 scenario forward read, a range-bound playbook (long tactic + short tactic; a neutral call carries a numeric low/high zone instead of an entry plan and is scored on whether the zone held), an entry/stop/target plan with dual-basis R/R (T1 + T2) for directional calls only, position sizing with a nominal cap from the live broker account, an event-risk gate (earnings / FOMC / CPI), and market/sector alignment + relvol volume checks — MACD divergence/背驰, candle patterns like Pin Bar, and 123 structures are auto-detected and drawn server-side — then renders it via the `chart` skill (type `intraday`, POST preview → PATCH prediction) and logs a journal entry. US-only, single-symbol, short horizon (intraday to a few sessions) — a companion to `market-session-tracker`, not a replacement. Triggers:
Cross-context shared trading discipline — output language, independent verification, scenarios not points, noise filtering, intent-attribution guardrails, and execution discipline (trend alignment, R:R floor, exit protection, verifiable reasons). Injected into both the app-side judgment agents (analyst / deepDive / chat) and the bench episode runner. Context-specific chapters live under references/ and are loaded on demand by the caller (app or bench).
استنادا إلى تصنيف SOC المهني
عرض SKILL.md
| name | sec-edgar |
| description | US SEC EDGAR filings — list 10-K/10-Q/8-K/Form 4/S-1, fetch filing text, parse insider Form 4 transactions. |
Response language: match user input.
Trigger phrases:
Not for: 13F holdings analysis (this skill lists 13F filings but does not parse them into holdings — deferred to a future skill).
filings.py <TICKER> (optionally --type 8-K).primary_doc_url from the list output to
filing_text.py. Use --max-chars to cap; --section item1a for risk
factors, --section mda (Item 7) for MD&A.insider.py <TICKER> parses Form 4 XML for the
past --days window.Environment auto-loaded; SEC_USER_AGENT is mandatory.
# Latest 5 NVDA 8-Ks
python3 .claude/skills/sec-edgar/scripts/filings.py NVDA --type 8-K --limit 5
# All recent NVDA filings
python3 .claude/skills/sec-edgar/scripts/filings.py NVDA --limit 20
# Read the most recent 8-K (URL from filings.py)
python3 .claude/skills/sec-edgar/scripts/filing_text.py \
"https://www.sec.gov/Archives/edgar/data/1045810/000104581026000051/nvda-20260520.htm" \
--max-chars 20000
# Pull Item 1A (Risk Factors) from a 10-K
python3 .claude/skills/sec-edgar/scripts/filing_text.py "<10-K URL>" --section item1a
# Save full text to disk, get metadata only
python3 .claude/skills/sec-edgar/scripts/filing_text.py "<URL>" --save-raw /tmp/nvda-10k.txt
# Insider transactions, past 90 days
python3 .claude/skills/sec-edgar/scripts/insider.py NVDA --days 90
# Insider + amendments
python3 .claude/skills/sec-edgar/scripts/insider.py NVDA --include-amendments
| Key | 10-K section |
|---|---|
item1 / business | Item 1. Business |
item1a / risk | Item 1A. Risk Factors |
item7 / mda | Item 7. MD&A |
item7a | Item 7A. Quantitative & Qualitative Disclosures |
item8 | Item 8. Financial Statements |
meta.confidence returned: high (clean heading match), medium (short
slice, may be incomplete), low (heuristic fallback — full text returned
with warning).
filings.py:
{
"data": [
{
"accession": "0001045810-26-000051",
"cik": "0001045810",
"form": "8-K",
"filed_date": "2026-05-20",
"primary_doc_url": "https://www.sec.gov/Archives/edgar/data/1045810/...htm",
"primary_doc_name": "nvda-20260520.htm",
"description": "8-K",
"size": 637530,
"is_xbrl": true
}
],
"meta": { "cik": "0001045810", "name": "NVIDIA CORP", "count_returned":
insider.py:
{
"data": [
{
"accession": "...",
"form": "4",
"filed_date": "2026-05-15",
"reporter": "JEN-HSUN HUANG",
"roles": ["officer:CEO", "director"],
"txn_date": "2026-05-13",
"security_title": "Common Stock",
"code": "S",
"shares": 240000,
"price": 412.5,
"acquire_or_dispose": "D",
"post_holdings": 78000000,
"ownership_kind"
| Exit code | Meaning | LLM action |
|---|---|---|
| 0 | Success | Parse and narrate. |
| 2 | Missing SEC_USER_AGENT | Set in .env at project root. |
| 3 | HTTP 4xx, ticker not found, or unparseable XML | Read hint. Per-filing parse errors collected in meta.parse_errors. |
| 4 | Network | Suggest retry. |
insider.py only scans the recent window of submissions (typically last
~1000 filings); deep history requires submissions/CIK*-N.json paging,
not implemented.filing_text.py uses an HTML-only extractor — XBRL inline tables are
stripped to text, not parsed into structured rows.meta.confidence.*.sec.gov calls.longbridge-financial-report for normalised income / balance / cash flow.longbridge-news for curated equity news (faster than reading 8-Ks).quiver for congressional trades (distinct from corporate insiders).