Borrowing it
Nothing to install: this file belongs to lowtidebuild/public-equity-research. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lowtidebuild/public-equity-research/main/.claude/skills/earnings-window-detector/SKILL.mdgit clone --depth 1 https://github.com/lowtidebuild/public-equity-researchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lowtidebuild/public-equity-research/earnings-window-detector)<a href="https://agentmods.dev/skills/lowtidebuild/public-equity-research/earnings-window-detector"><img src="https://agentmods.dev/badge/skills/lowtidebuild/public-equity-research/earnings-window-detector/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lowtidebuild/public-equity-research/earnings-window-detector"><img src="https://agentmods.dev/badge/skills/lowtidebuild/public-equity-research/earnings-window-detector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.02739 |
| Opus 5 | $0.00000 | $0.01370 |
| Sonnet 5 | $0.00000 | $0.00548 |
| Haiku 4.5 | $0.00000 | $0.00274 |
Grade A, and why
earnings-window-detector scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Earnings Window Detector — SKILL.md
Role: Mode E 진입 자동 감지 — 티커 + 오늘 날짜로부터 실적 발표 윈도우 (preview / review / none) 분류.
Triggered by: CLAUDE.md Workflow 1 Step 0 직후 (Chunk 5에서 staleness-checker와 함께 호출). 또는 사용자가 --earnings-mode preview|review 강제 지정 시 검증 용도.
Reads: yfinance.Ticker(t).calendar (1차) → yfinance.Ticker(t).earnings_dates (2차).
Writes: output/runs/{run_id}/earnings-window/{ticker}.json per ticker.
References: .claude/skills/earnings-window-detector/scripts/window-classifier.py
목적 (Purpose)
Mode E (Earnings Preview/Review)는 실적 발표 D-7 ~ D+3 윈도우에서만 의미가 있다. 이 skill은 그 윈도우 안인지 밖인지를 결정해서 orchestrator의 모드 분기 결정을 돕는다. Stateless 분류기이며 캐시 레이어를 가지지 않는다 (orchestrator가 Mode E 재진입 시점에 1h TTL 정책을 처리).
호출 시점 (When to Invoke)
- Mode E 자동 감지 — Workflow 1 진입 시 staleness-checker 직후.
window != "none"이면 Mode E 자동 제안 (Chunk 5에서 wiring). - 수동 검증 — 사용자가
--earnings-mode preview|review를 강제 지정한 경우, 실제 윈도우와 일치하는지 sanity-check 용도. - 워치리스트 스캔 — 워치리스트 전체를 스캔할 때 어떤 종목이 곧 실적 발표를 앞두고 있는지 식별 (멀티 티커 CLI).
호출하지 않는 경우:
- Mode A/B/C/D 명시적 요청 시 (단, Mode E 후보임을 알리는 informational 호출은 가능)
- 유럽/홍콩 티커 (yfinance 데이터 품질 낮음 — 향후 별도 source 필요)
입력 (Inputs)
CLI
python .claude/skills/earnings-window-detector/scripts/window-classifier.py \
--ticker GOOGL AAPL MSFT \
--output-dir output/runs/{run_id}/earnings-window/ \
--today-date 2026-05-07 \
--timeout 30
| 인자 | 필수 | 기본값 | 설명 |
|---|---|---|---|
--ticker |
✅ | — | 1개 이상 ticker 심볼 (공백 구분) |
--output-dir |
✅ | — | 출력 디렉토리 (per-ticker JSON 작성 위치) |
--today-date |
❌ | UTC 오늘 | 분류 기준 날짜 (YYYY-MM-DD) — 테스트/재현 용도 |
--timeout |
❌ | 30 | 티커당 yfinance 호출 timeout (초) |
프로그래매틱
from window_classifier import classify_window, classify_windows
# 단일 티커
record = classify_window(ticker="GOOGL", today_date="2026-05-07", timeout=30)
# 멀티 티커 + 디스크 작성
results = classify_windows(
tickers=["GOOGL", "AAPL"],
output_dir="output/runs/RUN/earnings-window/",
today_date="2026-05-07",
timeout=30,
)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 251 lines · 0 tokens per session scan A a2420a08c648
earnings-window-detector is a skill published in the GitHub repository lowtidebuild/public-equity-research (46 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,739 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
tradingagents-analysis
A multi-agent analysis tool for stocks listed on China's Shanghai and Shenzhen exchanges, known as A-shares. It combines technical, company, market-sentiment, money-flow, economic, and game-theory analysis into a structured trading view.
dcf-model
DCF valuation: free cash flow projections, WACC, terminal value, sensitivity analysis.
initiating-coverage
Full equity research initiation: company research, financial model, valuation, charts, 30-50 page report.
comps-analysis
Comparable company analysis: operating metrics, valuation multiples, peer benchmarking.
ui-design
Design-quality reference for financial-research visual output: typography, color, composition, and avoiding generic AI aesthetics.
onboarding
First-time user onboarding to set up investment profile, watchlists, portfolio, and preferences.