Stockbee Episodic Pivot Analyzer Agent Skill
Analyze Stockbee-style Day 1 Episodic Pivot candidates from earnings, guidance raises, M&A, FDA/regulatory approvals, analyst actions, major contracts, product launches, short-squeeze catalysts, or theme/story events. Scores catalyst quality together with gap/range expansion, volume shock, neglect/revaluation context, liquidity, and risk to the EP-day low. Use when the user asks for EP candidates, episodic pivots, Day 1 catalyst trades, game-changing news reactions, delayed EP watchlists, or handoffs into PEAD monitoring.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/BaggaT236/AI-Trading-Skills --skill stockbee-episodic-pivot-analyzerWhat comes with it
56 470 bytes besides the instructionThe instruction itself
10 sections, as written by the authorStockbee Episodic Pivot Analyzer
Classify Day 1 Episodic Pivot (EP) candidates using both catalyst quality and price/volume confirmation. The skill is a candidate-quality analyzer, not an execution engine.
When to Use
- The user asks for Pradeep Bonde / Stockbee style EP candidates
- The user provides earnings, guidance, M&A, FDA, analyst, contract, product, short-squeeze, or theme/news events
- The user wants to separate
ACTIONABLE_DAY1candidates fromDELAYED_EP_WATCHnames - The user wants to hand strong earnings/guidance EPs into
pead-screener - The user wants to combine catalyst analysis with
stockbee-momentum-burst-screenerprice/volume output
Prerequisites
- Python 3.10+
- Optional: FMP API key for OHLCV/profile enrichment
- One of:
- Catalyst/events JSON
earnings-trade-analyzerJSON output- Catalyst JSON plus
stockbee-momentum-burst-screenerJSON enrichment - This skill does not fetch or discover news by itself. If the catalyst is not supplied, first gather the event/news context using the user's preferred news or research process.
Workflow
Step 1: Prepare Candidate Inputs
Use one or more of these input modes.
Mode A — Catalyst/event JSON:
{
"events": [
{
"symbol": "ABC",
"event_date": "2026-04-25",
"catalyst_type": "guidance_raise",
"headline": "ABC raises FY guidance after record demand",
"summary": "Management raised revenue and EPS guidance."
}
]
}
Mode B — Earnings pipeline:
Use the JSON produced by earnings-trade-analyzer.
Mode C — Price/volume enrichment:
Pass a stockbee-momentum-burst-screener JSON report to reuse day-gain, volume, close-location, and risk-distance fields.
Step 2: Run the Analyzer
# Catalyst JSON + offline OHLCV
python3 skills/stockbee-episodic-pivot-analyzer/scripts/analyze_ep.py \
--events-json data/catalysts.json \
--prices-json data/daily_ohlcv.json \
--output-dir reports/
# Earnings pipeline input
python3 skills/stockbee-episodic-pivot-analyzer/scripts/analyze_ep.py \
--earnings-json reports/earnings_trade_analyzer_YYYY-MM-DD_HHMMSS.json \
--output-dir reports/
# Catalyst JSON + Stockbee momentum enrichment
python3 skills/stockbee-episodic-pivot-analyzer/scripts/analyze_ep.py \
--events-json data/catalysts.json \
--momentum-json reports/stockbee_momentum_burst_YYYY-MM-DD_HHMMSS.json \
--output-dir reports/
Optional FMP enrichment:
export FMP_API_KEY=your_key
python3 skills/stockbee-episodic-pivot-analyzer/scripts/analyze_ep.py \
--events-json data/catalysts.json \
--max-api-calls 200 \
--output-dir reports/
Step 3: Review the Output
For each candidate, present:
state:ACTIONABLE_DAY1,DAY1_WATCH,DELAYED_EP_WATCH,CATALYST_WATCH, orREJECTep_type:EARNINGS_EP,GUIDANCE_EP,FDA_EP,M_AND_A_EP,STORY_EP, etc.- Catalyst quality score and reasons
- Price/range expansion, volume shock, and close-location quality
- Risk to EP-day low
pead_handoffanddelayed_ep_watchflags
Step 4: Handoff Rules
ACTIONABLE_DAY1: Send totechnical-analystandposition-sizerbefore any trade decision.DAY1_WATCH: Keep on the intraday/next-day watchlist; require chart confirmation.DELAYED_EP_WATCH: Do not chase Day 1; monitor for a controlled pullback or new range.CATALYST_WATCH: Catalyst may be important, but price/volume confirmation is not yet sufficient.REJECT: Do not trade from this candidate source.- Earnings/guidance EPs with
pead_handoff=truecan be sent topead-screenerfor weekly red-candle / delayed reaction monitoring.
Output
stockbee_episodic_pivot_YYYY-MM-DD_HHMMSS.json— structured EP scoring reportstockbee_episodic_pivot_YYYY-MM-DD_HHMMSS.md— human-readable candidate report
Resources
references/ep_methodology.md— Stockbee EP interpretation and setup taxonomyreferences/catalyst_quality.md— catalyst classification and quality scoringreferences/handoff_rules.md— downstream workflow handoffs and review rules
Other skills for the same job
different authors, same section of the catalogue
Maps architectural components in a codebase and measures their size to identify what should be extracted first. Use when asking "how big is each module?", "what components do I have?", "which service is too large?", "analyze codebase structure", "size my monolith", or planning where to start decomposing. Do NOT use for runtime performance sizing or infrastructure capacity planning.
Understand and adhere to the project's technology stack including Laravel, PHP, React, PostgreSQL, Pest, Tailwind CSS, and all configured tools and services. Use this skill when making architectural decisions, when choosing libraries or packages, when configuring development tools, when setting up testing frameworks, when implementing authentication, when integrating third-party services, when configuring CI/CD pipelines, when setting up local development environments, or when ensuring consistency with the established tech stack across all parts of the application.
Use when the user requests diagrams, flowcharts, architecture diagrams, ER diagrams, UML / sequence / class diagrams, SysML / MBSE diagrams (block definition, internal block, requirement, parametric), BPMN business process diagrams, swimlane / cross-functional flowcharts, network topology, cloud architecture from Terraform or Kubernetes manifests, ML/DL model figures (Transformer/CNN/LSTM), mind maps, or any visualization. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that benefit from visual representation. Best suited when the diagram needs custom styling, rich shape vocabulary, swimlanes, or exportable images (PNG/SVG/PDF/JPG). Generates .drawio XML and exports locally via the native draw.io desktop CLI.
When the user wants to plan product distribution via marketplaces, app stores, or third-party platforms. Also use when the user mentions "distribution channels," "marketplace listing," "app store listing," "Figma plugin," "Chrome extension marketplace," "AWS Marketplace," "Shopify app," "GPTs store," "app distribution," or "third-party marketplace." For channel mix, use integrated-marketing.
网页设计与部署。生成精美的单页 HTML 网页（报告、落地页、数据可视化等），支持一键部署到 Cloudflare Pages。使用 Tailwind CSS + Chart.js + Font Awesome 技术栈。当用户要求制作网页、生成报告页面、创建落地页、数据可视化展示、部署网页到线上时使用。
Use when the user asks for a Databricks lakehouse architecture diagram — medallion architecture (Bronze/Silver/Gold), Delta Lake, Unity Catalog, workspace deployment, data-plane/control-plane, or any diagram built with Databricks icons. Builds with the declarative layout engine using ground-truth stencils, validates (stencils/colors/nesting/geometry), runs a render-based vision self-check. Default output is .drawio; PNG/SVG only on request.
Generate ActivityKit Live Activity infrastructure with Dynamic Island layouts, Lock Screen presentation, and push-to-update support. Use when adding Live Activities to an iOS app.
架构文档生成 — 生成架构设计说明书、技术方案文档、API设计文档、部署架构文档
How to use it
Take baggat236/stockbee-episodic-pivot-analyzer from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.