tradermonty/claude-trading-skills

stockbee-20pct-study

Build and maintain a Stockbee-style daily 20% mover study for US equities by scanning +20%/-20% movers, classifying catalysts and setup context, updating forward outcomes, and summarizing cohort patterns.

소스 보기

사용 방법

  1. 설치 명령을 복사하고 자신의 에이전트 환경에 설치하기 전에 소스 패키지를 확인하세요.
  2. 필요한 도구, 인증 정보, 지원 환경은 원본 문서에서 확인하세요.
  3. 입력과 원하는 산출물을 설명하고 출처와 결과를 대조하세요.
npx skills add https://github.com/tradermonty/claude-trading-skills --skill stockbee-20pct-study

시작 전 확인

  • 설치에는 모델 구독, API 한도, 파일 접근 권한이 포함되지 않습니다.
  • 별점 수와 설치 수는 활동 지표이며 독립적인 품질·보안 검증이 아닙니다.
원본 Skill 문서

원본 저장소의 제목, 예시, 코드, 표, 링크, 이미지를 유지해 표시합니다.

Stockbee 20% Study

Build a daily event study of US equities that moved +20% or -20% over a defined window. Convert large movers into structured study records, classify the catalyst and chart context, update forward outcomes, and summarize recurring patterns for research.

This skill is a research, model-book, and setup-fluency workflow. It does not generate buy/sell signals, place orders, or output broker execution instructions.

When to Use

  • User wants to run a Stockbee-style daily 20% mover study
  • User asks which stocks moved +20% or -20% today, this week, or over a configurable lookback window
  • User wants to backfill historical 20% movers and study what happened next
  • User wants to identify continuation, reversal, exhaustion, or theme-cluster patterns
  • User wants to build a model book of explosive winners, major failures, and failed low-quality pops
  • User wants edge hints for downstream strategy research rather than immediate trade signals

Prerequisites

  • Python 3.9+
  • FMP API key for live US universe scans, or offline OHLCV JSON via --prices-json
  • Optional structured news/catalyst JSON for higher-quality catalyst classification
  • Recommended market regime artifact from market-regime-daily
  • Recommended local state path: state/stockbee/20pct_study_events.jsonl

Workflow

Step 1: Scan for 20% Movers

Run after the US market close, or against the latest complete daily bar in an offline OHLCV file.

bash
python3 skills/stockbee-20pct-study/scripts/run_20pct_study.py scan \
  --fmp-universe \
  --max-symbols 300 \
  --as-of 2026-06-28 \
  --lookback-days 5 \
  --min-abs-return-pct 20 \
  --min-price 5 \
  --min-dollar-volume 20000000 \
  --include-down-movers \
  --state-file state/stockbee/20pct_study_events.jsonl \
  --output-dir reports/

Use offline data instead of FMP:

bash
python3 skills/stockbee-20pct-study/scripts/run_20pct_study.py scan \
  --prices-json data/us_daily_ohlcv.json \
  --as-of 2026-06-28 \
  --lookback-days 5 \
  --include-down-movers \
  --state-file state/stockbee/20pct_study_events.jsonl \
  --output-dir reports/

Step 2: Enrich and Classify Events

Use structured catalyst data when available. The enrichment step is best-effort: if no news record is found, the event remains a price-only NO_CLEAR_NEWS study record.

bash
python3 skills/stockbee-20pct-study/scripts/run_20pct_study.py enrich \
  --events-json reports/stockbee_20pct_events_YYYY-MM-DD_HHMMSS.json \
  --news-json data/catalysts_YYYY-MM-DD.json \
  --market-regime reports/market_regime_latest.json \
  --state-file state/stockbee/20pct_study_events.jsonl \
  --output-dir reports/

Step 3: Update Matured Forward Outcomes

Update 1-day, 3-day, 5-day, 10-day, and 20-day forward outcomes after enough future bars exist.

bash
python3 skills/stockbee-20pct-study/scripts/run_20pct_study.py update-outcomes \
  --prices-json data/us_daily_ohlcv.json \
  --state-file state/stockbee/20pct_study_events.jsonl \
  --horizons 1,3,5,10,20 \
  --output-dir reports/

The update records close return, MFE, MAE, direction-adjusted continuation return, and outcome tags.

Step 4: Summarize Cohorts

bash
python3 skills/stockbee-20pct-study/scripts/run_20pct_study.py summarize \
  --state-file state/stockbee/20pct_study_events.jsonl \
  --group-by direction,catalyst.label,technical_context.pattern_label,technical_context.close_quality \
  --min-sample 10 \
  --output-dir reports/

Treat rule_candidates and exported edge hints as research prompts. Require representative chart review, sample-size thresholds, and out-of-sample validation before changing trade rules.

Step 5: Historical Backfill

bash
python3 skills/stockbee-20pct-study/scripts/run_20pct_study.py backfill \
  --from 2020-01-01 \
  --to 2026-06-28 \
  --prices-json data/us_daily_ohlcv.json \
  --min-abs-return-pct 20 \
  --include-down-movers \
  --state-file state/stockbee/20pct_study_events.jsonl \
  --output-dir reports/

Backfill records are marked CURRENT_UNIVERSE_BACKFILL_SURVIVORSHIP_BIAS by default. Add --survivorship-complete only when the supplied OHLCV includes delisted symbols and historical universe coverage.

Output Format

  • stockbee_20pct_events_YYYY-MM-DD_HHMMSS.json — scan metadata and event records
  • stockbee_20pct_daily_report_YYYY-MM-DD_HHMMSS.md — human-readable daily 20% study report
  • stockbee_20pct_enriched_YYYY-MM-DD_HHMMSS.json — enriched event records
  • stockbee_20pct_outcome_update_YYYY-MM-DD_HHMMSS.json/md — matured forward outcome update
  • stockbee_20pct_cohort_summary_YYYY-MM-DD_HHMMSS.json/md — cohort statistics and rule candidates
  • stockbee_20pct_edge_hints_YYYY-MM-DD_HHMMSS.yaml — edge-hint export for downstream research skills
  • state/stockbee/20pct_study_events.jsonl — durable 20% mover model book

Resources

  • references/methodology.md — 20% study methodology and review checklist
  • references/event_schema.md — JSONL event record schema
  • references/catalyst_taxonomy.md — catalyst and risk label definitions
  • references/scoring_system.md — event quality and study priority scoring
  • references/cohort_mining_rules.md — overfitting controls and sample-size rules
  • scripts/run_20pct_study.py — CLI for scan, enrich, update-outcomes, summarize, and backfill

Shared FMP client

Live FMP access uses the bundled generated scripts/fmp_client.py, loaded only when an FMP run starts, so offline modes still work without requests. CLI key/environment precedence, the API-call budget and successful output shapes are preserved. Requests use stable endpoints only; a denied, empty or failed stable request does not fall back to retired v3 URLs. The shared client masks raw and URL-encoded key echoes, retries malformed JSON once, and retries a 429 at most once, after a 60-second wait, before stopping on a repeated rate limit.

같은 저장소의 Skills

더 많은 Skills

모든 Skills
tradermonty
커뮤니티

crypto-regime-analyzer

Quantifies crypto market regime health using free, keyless public data (CoinGecko + Binance funding). Generates a 0-100 composite score across 6 components (100 = risk-on) with a posture recommendation. No API key required. Use when user asks about crypto market conditions, whether it's alt season, BTC dominance, crypto risk-on vs risk-off, funding rates, or whether crypto exposure should be increased or reduced.

1시간 설치 수
4
GitHub Stars
5.3천
업데이트
11월 15일
tradermonty
커뮤니티

drawdown-circuit-breaker

Evaluate account-level drawdown circuit breaker rules from trader-memory-core state and decide whether new trade risk is allowed today. Uses realized P&L, losing-streak cooldowns, and weekly/monthly drawdown limits without any external API.

1시간 설치 수
3
GitHub Stars
5.3천
업데이트
11월 15일
tradermonty
커뮤니티

edge-strategy-designer

Convert abstract edge concepts into strategy draft variants and optional exportable ticket YAMLs for edge-candidate-agent export/validation.

1시간 설치 수
3
GitHub Stars
5.3천
업데이트
11월 15일
tradermonty
커뮤니티

edge-strategy-reviewer

Critically review strategy drafts from edge-strategy-designer for edge plausibility, overfitting risk, sample size adequacy, and execution realism. Use when strategydrafts/.yaml exists and needs quality gate before pipeline export. Outputs PASS/REVISE/REJECT verdicts with confidence scores.

1시간 설치 수
3
GitHub Stars
5.3천
업데이트
11월 15일