快速判断
- 01这个 Skill 是干嘛的
- 提供市场宽度、趋势识别和每周策略分析的可复用交易研究流程。
- 02它能解决什么问题
- 解决宏观市场状态、行业强弱和交易计划之间缺少连续分析框架的问题。
- 03它适合谁来用
- 适合有交易经验、需要定期市场复盘和策略准备的个人投资者。
预览 · README.md
中文为 README 译文；English 保留 GitHub README 原文。
claude-trading-skills
提供市场宽度、趋势与每周交易策略分析所需的可复用流程。
主要能力
This skill should be used when analyzing market breadth charts, specifically the S&P 500 Breadth Index (200-Day MA based) and the US Stock Market Uptrend Stock Ratio charts. Use this skill when the user provides breadth chart images for analysis, requests market breadth assessment, positioning strategy recommendations, or wants to understand medium-term strategic and short-term tactical market outlook based on breadth indicators. All analysis and output are conducted in English.
使用方式
仓库级安装会保留完整目录；本次核验的入口是 examples/weekly-trade-strategy/.claude/skills/breadth-chart-analyst/SKILL.md。使用前先阅读英文 README 与原始 SKILL.md，并按当前 Agent 的目录规范安装。
适用边界
策略示例不代表收益承诺，使用者仍需独立验证数据源与风险敞口。
许可与来源
来源：GitHub 公开仓库。核验许可：MIT。本页是贴近原仓库结构的中文导读，具体参数、依赖和更新记录以英文 README 为准。
Claude Trading Skills
Claude Trading Skills started as a personal project to use AI to improve my own trading process.
Claude Trading Skills is a Claude Skills-based trading workflow toolkit for time-constrained individual investors.
It is designed for investors who use long-term investing, ETFs, and dividend stocks as their core, while using disciplined swing trading as a satellite strategy when market conditions are favorable.
The goal is not to outsource buy/sell decisions to AI. The goal is to structure market review, risk management, trade planning, journaling, and continuous improvement. It is open source because the workflows, checklists, and review habits behind better trading decisions can improve through shared practice.
This is not a signal service or a promise of profitability. It is a toolkit for traders who want to build a better decision process.
The project follows a first for self, open for others stance: it is built first as a practical workflow the author uses, then shared openly for others who face similar constraints.
📖 Documentation site: <https://tradermonty.github.io/claude-trading-skills/>
Project vision: PROJECT_VISION.md
日本語版READMEはREADME.ja.mdをご覧ください。
Disclaimer
This repository is for educational, research, and process-improvement purposes only. It is not financial advice, investment advisory service, tax advice, legal advice, a signal service, or a broker execution platform. Trading and investing involve risk, including loss of principal. Past performance, backtests, screens, reports, and AI-generated analysis do not guarantee future results. All trading decisions, position sizing, tax/regulatory compliance, and broker usage are the user's responsibility.
The project is provided under the MIT License, AS IS, WITHOUT WARRANTY.
Who This Is For
This repository is designed for:
- Time-constrained individual investors
- Long-term investors who also want disciplined swing-trading upside
- Dividend and ETF investors who want structured portfolio review
- Traders who want to manage risk before finding trade candidates
- Investors who want to journal and improve their decision process
It is not designed for fully automated trading, signal outsourcing, or short-term scalping.
Recommended Starting Path
New users should start with one of these operational workflows. Each link points to a machine-readable manifest under workflows/ that names the exact skills, decision gates, and artifacts in order.
| Goal | Workflow | Anchor Skills | API Profile |
|---|---|---|---|
| 15-minute daily market check | market-regime-daily | market-breadth-analyzer, uptrend-analyzer, exposure-coach | No API for basic path |
| Weekly long-term portfolio review | core-portfolio-weekly | portfolio-manager, kanchi-dividend-review-monitor, trader-memory-core | Alpaca required; manual CSV is a degraded fallback |
| Find swing candidates only when risk is allowed | swing-opportunity-daily | vcp-screener, drawdown-circuit-breaker, technical-analyst, position-sizer, trader-memory-core, pre-trade-discipline-gate | FMP for screeners; local state for risk and discipline gates |
| Record and learn from every closed trade | trade-memory-loop | trader-memory-core, signal-postmortem | No API for manual path |
| Review monthly performance and adjust rules | monthly-performance-review | trader-memory-core, signal-postmortem, backtest-expert | No API for manual path |
See workflows/README.md for how to read a manifest and run it manually. For a one-page "which workflow fits my situation?" guide, see Find Your Workflow (日本語).
What This Actually Costs
Claude Skills require a paid Claude plan that supports the Skills feature. FMP, FINVIZ Elite, and Alpaca are optional data or broker integrations for specific workflows; the five-skill starter path below works with public CSVs, chart screenshots, and local files, so it does not require any paid data API subscription beyond your Claude plan.
No API Key Starter Path
If you do not have FMP / FINVIZ / Alpaca subscriptions, start with these five skills and run them manually:
market-breadth-analyzer— public CSV breadth scoring; no API keyuptrend-analyzer— public CSV uptrend participation; no API keyposition-sizer— pure calculation; no I/Otrader-memory-core— local YAML journalingsignal-postmortem— review framework
This path lets you review market conditions, size trades, journal decisions, and review outcomes without paid data APIs. Note: "no API" does not mean "no external data" — these skills still need public CSVs, chart screenshots, or local files. See each skill's integrations: entry in skills-index.yaml for exact input requirements.
Canonical source:
skills-index.yamlis the authoritative index of all skills. If this README,CLAUDE.md, or docs disagree with the index, the index is correct. The same applies to multi-skill workflows —workflows/*.yamlis canonical.
Repository Layout
skills/<skill-name>/– Source folder for each trading skill. ContainsSKILL.md, reference material, and any helper scripts.skills-index.yaml– Canonical metadata index for every skill (id, category, integrations, workflows back-references).workflows/– Operational workflow manifests for the Core + Satellite routines (canonical, validator-enforced via--strict-workflows).skill-packages/– Pre-built.skillarchives ready to upload to Claude's web app Skills tab.docs/– Documentation site content, generated skill pages, anddocs/dev/metadata-and-workflow-schema.md(schema spec).scripts/– Repository-level automation, including the schema validator and one-shot bootstrap helper.skillsets/– Purpose-specific install bundles defining required / recommended / optional skills for major goals (4 core skillsets shipped: market-regime, core-portfolio, swing-opportunity, trade-memory; consumed by the Navigator).
Getting Started
Use with Claude Web App
- Download the
.skillfile that matches the skill you want fromskill-packages/. - Open Claude in your browser, go to Settings → Skills, and upload the ZIP (see Anthropic's Skills launch post for feature overview).
- Enable the skill inside the conversation where you need it.
Use with Claude Code (desktop or CLI)
- Clone or download this repository.
- Copy the desired skill folder (e.g.,
backtest-expert) into your Claude Code Skills directory (open Claude Code → Settings → Skills → Open Skills Folder, per the Claude Code Skills documentation). - Restart or reload Claude Code so the new skill is detected.
Tip:
.skillpackages are built from the source folders with tests and local build artifacts omitted. Edit a source folder if you want to customize a skill, then runpython3 scripts/package_skills.py --skill <skill-name>before uploading to the web app.
Companion Work Package
Want a ready-to-run agent-style workflow? See the companion Hermes Trading Research Agent Work Package.
It packages these skills into a Hermes profile with task-oriented slash-command routines such as /pre-market-routine, /after-close-review, /trade-journal, /weekly-portfolio-review, and /monthly-performance-review.
This is a research, journaling, and risk-review assistant, not an automated trading system. It does not place orders, provide a signal service, or run hidden scheduled jobs; human decision gates remain central.
Core Skill Areas
This repository contains skills across the following areas:
| Area | Example Skills |
|---|---|
| Market Regime | market-breadth-analyzer, uptrend-analyzer, exposure-coach |
| Core Portfolio | portfolio-manager, value-dividend-screener, kanchi-dividend-sop |
| Swing Opportunities | vcp-screener, canslim-screener, breakout-trade-planner |
| Trade Planning | position-sizer, technical-analyst, pre-trade-discipline-gate |
| Trade Memory | trader-memory-core, signal-postmortem |
| Strategy Research | backtest-expert, edge-pipeline-orchestrator |
| Advanced Satellite | parabolic-short-trade-planner, earnings-trade-analyzer, options-strategy-advisor |
The detailed catalog below is auto-generated from skills-index.yaml by scripts/generate_catalog_from_index.py. To update a skill's description, edit its skills-index.yaml entry and re-run the generator (python3 scripts/generate_catalog_from_index.py). For a more navigable version, use the documentation site.
Detailed Skill Catalog
Market Regime
| Skill | Summary | Integrations | Status |
|---|---|---|---|
Breadth Chart Analyst (breadth-chart-analyst) | This skill should be used when analyzing market breadth charts, specifically the S&P 500 Breadth Index (200-Day MA based) and the US Stock Market Uptrend Stock Ratio charts. | chart_image required | production |
COT Contrarian Detector (cot-contrarian-detector) | Detects crowded speculative (large-speculator) positioning in CFTC futures markets using Commitment of Traders data, implementing step 1 of Jason Shapiro's contrarian methodology. | fmp required | production |
Downtrend Duration Analyzer (downtrend-duration-analyzer) | Analyze historical downtrend durations and generate interactive HTML histograms showing typical correction lengths by sector and market cap. | local_calculation — | production |
Exposure Coach (exposure-coach) | Generate a one-page Market Posture summary with net exposure ceiling, growth-vs-value bias, participation breadth, and new-entry-allowed vs cash-priority recommendation by integrating signals from breadth, regime, and flow analysis skills. | local_calculation — | production |
FTD Detector (ftd-detector) | Detects Follow-Through Day (FTD) signals for market bottom confirmation using William O'Neil's methodology. | fmp required | production |
IBD Distribution Day Monitor (ibd-distribution-day-monitor) | Detect IBD-style Distribution Days for QQQ/SPY (close down at least 0.2% on higher volume), track 25-session expiration and 5% invalidation, count d5/d15/d25 clusters, classify market risk (NORMAL/CAUTION/HIGH/SEVERE), and emit TQQQ/QQQ... | fmp required | production |
Macro Regime Detector (macro-regime-detector) | Detect structural macro regime transitions (1-2 year horizon) using cross-asset ratio analysis. | yfinance_or_csv _recommended_ | production |
Market Breadth Analyzer (market-breadth-analyzer) | Quantifies market breadth health using TraderMonty's public CSV data. | public_csv required | production |
Market Environment Analysis (market-environment-analysis) | Comprehensive market environment analysis and reporting tool. | websearch required, chart_image optional | production |
Market News Analyst (market-news-analyst) | This skill should be used when analyzing recent market-moving news events and their impact on equity markets and commodities. | websearch required | production |
Market Top Detector (market-top-detector) | Detects market top probability using O'Neil Distribution Days, Minervini Leading Stock Deterioration, and Monty Defensive Sector Rotation. | public_csv required | production |
News Reaction Failure Analyzer (news-reaction-failure-analyzer) | Judges whether a market failed to react to news favorable to a crowded speculative position, implementing step 2 of Jason Shapiro's contrarian methodology with a Monte-Carlo-verified drift-significance verdict test. | fmp required, websearch required | production |
Sector Analyst (sector-analyst) | This skill should be used when analyzing sector rotation patterns and market cycle positioning. | chart_image required | production |
Uptrend Analyzer (uptrend-analyzer) | Analyzes market breadth using Monty's Uptrend Ratio Dashboard data to diagnose the current market environment. | public_csv required | production |
US Market Bubble Detector (us-market-bubble-detector) | Evaluates market bubble risk through quantitative data-driven analysis using the revised Minsky/Kindleberger framework v2.1. | user_input required | production |
Core Portfolio
| Skill | Summary | Integrations | Status |
|---|---|---|---|
Dividend Growth Pullback Screener (dividend-growth-pullback-screener) | Use this skill to find high-quality dividend growth stocks (12%+ annual dividend growth, 1.5%+ yield) that are experiencing temporary pullbacks, identified by RSI oversold conditions (RSI ≤40). | fmp required, finviz _recommended_ | production |
Kanchi Dividend Review Monitor (kanchi-dividend-review-monitor) | Monitor dividend portfolios with Kanchi-style forced-review triggers (T1-T5) and convert anomalies into OK/WARN/REVIEW states without auto-selling. | fmp _recommended_ | production |
Kanchi Dividend SOP (kanchi-dividend-sop) | Convert Kanchi-style dividend investing into a repeatable US-stock operating procedure. | fmp _recommended_ | production |
Kanchi Dividend US Tax Accounting (kanchi-dividend-us-tax-accounting) | Provide US dividend tax and account-location workflow for Kanchi-style income portfolios. | local_calculation — | production |
Portfolio Manager (portfolio-manager) | Comprehensive portfolio analysis using Alpaca MCP Server integration to fetch holdings and positions, then analyze asset allocation, risk metrics, individual stock positions, diversification, and generate rebalancing recommendations. | alpaca required | production |
Value Dividend Screener (value-dividend-screener) | Screen US stocks for high-quality dividend opportunities combining value characteristics (P/E ratio under 20, P/B ratio under 2), attractive yields (3% or higher), and consistent growth (dividend/revenue/EPS trending up over 3 years). | fmp required, finviz _recommended_ | production |
Swing Opportunity
| Skill | Summary | Integrations | Status |
|---|---|---|---|
Breakout Trade Planner (breakout-trade-planner) | Generate Minervini-style breakout trade plans from VCP screener output with worst-case risk calculation, portfolio heat management, and Alpaca-compatible order templates (stop-limit bracket for pre-placement, limit bracket for post-confi... | local_calculation — | production |
CANSLIM Screener (canslim-screener) | Screen US stocks using William O'Neil's CANSLIM growth stock methodology. | fmp required | production |
Finviz Screener (finviz-screener) | Build and open FinViz screener URLs from natural language requests. | finviz optional | production |
Stockbee Exhaustion Hammer Screener (stockbee-exhaustion-hammer-screener) | Screen US stocks for Stockbee-style selling-exhaustion hammer candidates using quality/liquidity gates, prior momentum, pullback depth, undercut/reclaim, hammer geometry, volume confirmation, market gate, and risk-distance filters. | fmp required, prices_json optional, profiles_json optional, local_calculation — | beta |
Stockbee Momentum Burst Screener (stockbee-momentum-burst-screener) | Screen US stocks for Stockbee-style 3-5 day momentum burst candidates using 4% breakout, dollar breakout, range expansion, volume expansion, setup quality, and risk-distance filters. | fmp required, prices_json optional, local_calculation — | beta |
Theme Detector (theme-detector) | Detect and analyze trending market themes across sectors. | fmp optional, finviz _recommended_ | production |
VCP Screener (vcp-screener) | Screen S&P 500 stocks for Mark Minervini's Volatility Contraction Pattern (VCP). | fmp required | production |
Trade Planning
| Skill | Summary | Integrations | Status |
|---|---|---|---|
Drawdown Circuit Breaker (drawdown-circuit-breaker) | Account-level circuit breaker that reads trader-memory-core state and decides whether new trade risk is allowed today using daily loss limits, losing-streak cooldowns, and weekly/monthly drawdown halts. | local_calculation — | beta |
Position Sizer (position-sizer) | Calculate risk-based position sizes for long stock trades. | local_calculation — | production |
Pre-Trade Discipline Gate (pre-trade-discipline-gate) | Offline manual-execution checklist gate that blocks planless, oversized, revenge-risk, market-regime-blocked, or circuit-breaker-blocked entries and journals the result. | local_calculation — | beta |
Technical Analyst (technical-analyst) | This skill should be used when analyzing weekly price charts for stocks, stock indices, cryptocurrencies, or forex pairs. | chart_image required | production |
US Stock Analysis (us-stock-analysis) | Comprehensive US stock analysis including fundamental analysis (financial metrics, business quality, valuation), technical analysis (indicators, chart patterns, support/resistance), stock comparisons, and investment report generation. | user_input required | production |
Trade Memory
| Skill | Summary | Integrations | Status |
|---|---|---|---|
Signal Postmortem (signal-postmortem) | Record and analyze post-trade outcomes for signals generated by edge pipeline and other skills. | local_calculation — | production |
Stockbee Setup Fluency Trainer (stockbee-setup-fluency-trainer) | Build a Stockbee-style setup model book from momentum-burst screener candidates, then update 3-day and 5-day forward outcomes with MFE/MAE, stop-hit status, outcome tags, and cohort statistics. | prices_json optional, fmp optional, local_calculation — | beta |
Trade Hypothesis Ideator (trade-hypothesis-ideator) | Generate falsifiable trade strategy hypotheses from market data, trade logs, and journal snippets with ranked hypothesis cards and optional strategy.yaml export. | local_calculation — | production |
Trade Performance Coach (trade-performance-coach) | Review closed trades, partial exits, and monthly aggregates for process adherence, risk discipline, execution quality, and evidence-based trading behavior patterns, then produce next-session operating rules. | local_calculation — | beta |
Trader Memory Core (trader-memory-core) | Track investment theses across their lifecycle — from screening idea to closed position with postmortem. | fmp optional | production |
Weekly Performance Digest (weekly-performance-digest) | Generate a weekly performance summary from closed trades with win rate, expectancy, and pattern analysis. | local_calculation — | production |
Strategy Research
| Skill | Summary | Integrations | Status |
|---|---|---|---|
Backtest Expert (backtest-expert) | Expert guidance for systematic backtesting of trading strategies. | user_input required | production |
Edge Candidate Agent (edge-candidate-agent) | Generate and prioritize US equity long-side edge research tickets from EOD observations, then export pipeline-ready candidate specs for trade-strategy-pipeline Phase I. | fmp optional | production |
Edge Concept Synthesizer (edge-concept-synthesizer) | Abstract detector tickets and hints into reusable edge concepts with thesis, invalidation signals, and strategy playbooks before strategy design/export. | local_calculation — | production |
Edge Hint Extractor (edge-hint-extractor) | Extract edge hints from daily market observations and news reactions, with optional LLM ideation, and output canonical hints.yaml for downstream concept synthesis and auto detection. | local_calculation — | production |
Edge Pipeline Orchestrator (edge-pipeline-orchestrator) | Orchestrate the full edge research pipeline from candidate detection through strategy design, review, revision, and export. | local_calculation — | production |
Edge Signal Aggregator (edge-signal-aggregator) | Aggregate and rank signals from multiple edge-finding skills (edge-candidate-agent, theme-detector, sector-analyst, institutional-flow-tracker) into a prioritized conviction dashboard with weighted scoring, deduplication, and contradicti... | local_calculation — | production |
Edge Strategy Designer (edge-strategy-designer) | Convert abstract edge concepts into strategy draft variants and optional exportable ticket YAMLs for edge-candidate-agent export/validation. | local_calculation — | production |
Edge Strategy Reviewer (edge-strategy-reviewer) | Critically review strategy drafts from edge-strategy-designer for edge plausibility, overfitting risk, sample size adequacy, and execution realism. | local_calculation — | production |
Scenario Analyzer (scenario-analyzer) | Analyze 18-month scenarios from news headlines via scenario-analyst agent with strategy-reviewer second opinion; outputs primary/secondary/tertiary impact analysis and stock picks. | websearch required | production |
Stanley Druckenmiller Investment (stanley-druckenmiller-investment) | Druckenmiller Strategy Synthesizer - Integrates 8 upstream skill outputs (Market Breadth, Uptrend Analysis, Market Top, Macro Regime, FTD Detector, VCP Screener, Theme Detector, CANSLIM Screener) into a unified conviction score (0-100),... | local_calculation — | production |
Stockbee 20% Study (stockbee-20pct-study) | Build a daily Stockbee-style +20%/-20% mover event study, classify catalysts and setup context, update forward outcomes, and export evidence-backed edge hints without treating movers as buy/sell signals. | fmp required, prices_json optional, news_events_json optional, websearch optional, local_calculation — | beta |
Strategy Pivot Designer (strategy-pivot-designer) | Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum. | local_calculation — | production |
Advanced Satellite
| Skill | Summary | Integrations | Status |
|---|---|---|---|
Earnings Trade Analyzer (earnings-trade-analyzer) | Analyze recent post-earnings stocks using a 5-factor scoring system (Gap Size, Pre-Earnings Trend, Volume Trend, MA200 Position, MA50 Position). | fmp required | production |
Institutional Flow Tracker (institutional-flow-tracker) | Use this skill to track institutional investor ownership changes and portfolio flows using 13F filings data. | fmp required | production |
Options Strategy Advisor (options-strategy-advisor) | Options trading strategy analysis and simulation tool. | fmp optional | production |
Pair Trade Screener (pair-trade-screener) | Statistical arbitrage tool for identifying and analyzing pair trading opportunities. | fmp required | production |
Parabolic Short Trade Planner (parabolic-short-trade-planner) | Screen US equities for parabolic exhaustion patterns and generate conditional pre-market short plans, then evaluate intraday trigger fires from live 5-min bars. | fmp required, alpaca optional | production |
PEAD Screener (pead-screener) | Screen post-earnings gap-up stocks for PEAD (Post-Earnings Announcement Drift) patterns. | fmp required | production |
Stockbee Episodic Pivot Analyzer (stockbee-episodic-pivot-analyzer) | Analyze Stockbee-style Day 1 Episodic Pivot candidates from earnings, guidance, M&A, FDA, analyst, contract, product, short-squeeze, and story/theme catalysts using catalyst quality, gap/range expansion, volume shock, neglect/revaluation context, liquidity, and EP-day-low risk. | catalyst_events_json required, fmp optional, local_calculation — | beta |
Meta / Development Tooling
| Skill | Summary | Integrations | Status |
|---|---|---|---|
Data Quality Checker (data-quality-checker) | Validate data quality in market analysis documents and blog articles before publication. | local_calculation — | production |
Dual Axis Skill Reviewer (dual-axis-skill-reviewer) | Review skills in any project using a dual-axis method: (1) deterministic code-based checks (structure, scripts, tests, execution safety) and (2) LLM deep review findings. | local_calculation — | production |
Earnings Calendar (earnings-calendar) | This skill retrieves upcoming earnings announcements for US stocks using the Financial Modeling Prep (FMP) API. | fmp required | production |
Economic Calendar Fetcher (economic-calendar-fetcher) | Fetch upcoming economic events and data releases using FMP API. | fmp required | production |
Skill Designer (skill-designer) | Design new Claude skills from structured idea specifications. | local_calculation — | production |
Skill Idea Miner (skill-idea-miner) | Mine Claude Code session logs for skill idea candidates. | local_calculation — | production |
Skill Integration Tester (skill-integration-tester) | Validate multi-skill workflows defined in CLAUDE.md by checking skill existence, inter-skill data contracts (JSON schema compatibility), file naming conventions, and handoff integrity. | local_calculation — | production |
Trading Skills Navigator (trading-skills-navigator) | Recommend the right workflow, skillset, API profile, and setup path from a natural-language trading goal. | local_calculation — | production |
Additional Workflow Examples
The main Core + Satellite starting path is described above. The examples below show additional ways to compose skills, including advanced satellite and contributor workflows.
Daily Market Monitoring
- Use Economic Calendar Fetcher to check today's high-impact events (FOMC, NFP, CPI releases)
- Use Earnings Calendar to identify major companies reporting today
- Use Market News Analyst to review overnight developments and their market impact
- Use Breadth Chart Analyst to assess overall market health and positioning
Weekly Strategy Review
- Use Sector Analyst to fetch CSV data and identify rotation patterns (optionally provide charts)
- Use Technical Analyst on key indices and positions for trend confirmation
- Use Market Environment Analysis for comprehensive macro briefing
- Use US Market Bubble Detector to assess speculative excess and risk levels
Individual Stock Research
- Use US Stock Analysis for comprehensive fundamental and technical review
- Use Earnings Calendar to check upcoming earnings dates
- Use Market News Analyst to review recent company-specific news and sector developments
- Use Backtest Expert to validate entry/exit strategies before position sizing
Strategic Positioning
- Use Stanley Druckenmiller Investment for macro theme identification
- Use Economic Calendar Fetcher to time entries around major data releases
- Use Breadth Chart Analyst and Technical Analyst for confirmation signals
- Use US Market Bubble Detector for risk management and profit-taking guidance
Earnings Momentum Trading
- Use Earnings Trade Analyzer to score recent earnings reactions (gap size, trend, volume, MA position)
- Use PEAD Screener (Mode B) with analyzer output to find PEAD setups (red candle pullbacks → breakout signals)
- Use Technical Analyst to confirm weekly chart patterns and support/resistance levels
- Use Liquidity filters in PEAD Screener to ensure position sizing feasibility
- Monitor SIGNAL_READY stocks for breakout entries with defined stop-loss (red candle low) and 2R targets
Income Portfolio Construction
- Use Value Dividend Screener to identify high-quality dividend stocks with sustainable yields
- Use Dividend Growth Pullback Screener to find growth-focused dividend stocks at attractive technical entry points
- Use US Stock Analysis for deep-dive fundamental analysis on top candidates
- Use Earnings Calendar to track upcoming earnings for portfolio holdings
- Use Market Environment Analysis to assess macro conditions for dividend strategies
- Use Backtest Expert to validate dividend capture or growth strategies
Kanchi Dividend Workflow (US Stocks)
- Use Kanchi Dividend SOP to run Kanchi's 5-step process and create buy plans with invalidation conditions
- Use Kanchi Dividend Review Monitor on a daily/weekly/quarterly cadence to generate
OK/WARN/REVIEWqueues - Use Kanchi Dividend US Tax Accounting to align holdings with qualified-dividend assumptions and account location
- Feed
REVIEWfindings back into Kanchi Dividend SOP before adding to positions
Options Strategy Development
- Use Options Strategy Advisor to simulate and compare options strategies using Black-Scholes pricing
- Use Technical Analyst to identify optimal entry timing and support/resistance levels
- Use Earnings Calendar to plan earnings-based options strategies
- Use US Stock Analysis to validate fundamental thesis before deploying capital
- Review Greeks and P/L scenarios to select optimal strategy (covered calls, spreads, straddles, etc.)
Portfolio Review & Rebalancing
- Use Portfolio Manager to fetch current holdings via Alpaca MCP and analyze portfolio health
- Review asset allocation, sector diversification, and risk metrics (beta, volatility, concentration)
- Review position-level flags (HOLD/ADD/TRIM/SELL candidates) based on thesis validation
- Use Market Environment Analysis and US Market Bubble Detector to assess macro conditions
- Review a rebalancing plan and decide manually which actions, if any, to take
Statistical Arbitrage Opportunities
- Use Pair Trade Screener to identify cointegrated stock pairs within sectors
- Analyze mean-reversion metrics (half-life, z-score) and hedge ratios
- Use Technical Analyst to confirm technical setups for both legs of the pair
- Monitor entry/exit signals based on z-score thresholds
- Track spread convergence and manage market-neutral positions
Skill Quality & Automation
- Data Quality Checker (
data-quality-checker)
- Validates data quality in market analysis documents and blog articles before publication. - 5 check categories: price scale inconsistencies (ETF vs futures digit hints), instrument notation consistency, date/weekday mismatches (English + Japanese), allocation total errors (section-limited), and unit mismatches. - Advisory mode — flags issues as warnings for human review, exit 0 even with findings. - Supports full-width Japanese characters (％, 〜), range notation (50-55%), and year inference for dates without explicit year. - No API key required — works offline on local markdown files.
- Skill Designer (
skill-designer)
- Generates Claude CLI prompts for designing new skills from structured idea specifications. - Embeds repository conventions (structure guide, quality checklist, SKILL.md template) into the prompt. - Lists existing skills to prevent duplication. Used by the skill auto-generation pipeline's daily flow. - No API key required.
- Dual-Axis Skill Reviewer (
dual-axis-skill-reviewer)
- Reviews skill quality using a dual-axis method: deterministic auto scoring (structure, workflow, execution safety, artifacts, tests) and optional LLM deep review. - 5-category auto axis (0-100): Metadata & Use Case (20), Workflow Coverage (25), Execution Safety & Reproducibility (25), Supporting Artifacts (10), Test Health (20). - Detects knowledge_only skills (no scripts, references only) and adjusts scoring expectations to avoid unfair penalties. - Optional LLM axis for qualitative review (correctness, risk, missing logic, maintainability) with configurable weight blending. - Supports --all flag to review every skill at once, --skip-tests for quick triage, and --project-root for cross-project review. - No API key required.
- Skill Idea Miner (
skill-idea-miner)
- Mines Claude Code session logs for skill idea candidates, scores them for novelty/feasibility/trading value, and maintains a prioritized backlog. - Used by the weekly skill auto-generation pipeline. Can also be run manually. - No API key required.
Skill Self-Improvement Loop
This section is contributor-oriented. New users can skip it and start with the Core + Satellite path above.
An automated pipeline that continuously reviews and improves skill quality. A daily launchd job picks one skill, scores it with the dual-axis reviewer, and if the score is below 90/100, invokes claude -p to apply improvements and open a PR.
How It Works
- Round-robin selection — cycles through all skills (excluding the reviewer itself), persisted in
logs/.skill_improvement_state.json. - Auto scoring — runs
run_dual_axis_review.pyto get a deterministic score (0-100). - Improvement gate — if
auto_review.score < 90, Claude CLI applies fixes to SKILL.md and references. - Quality gate — re-scores after improvement (with tests enabled); rolls back if the score didn't improve.
- PR creation — commits changes to a feature branch and opens a GitHub PR for human review.
- Daily summary — writes results to
reports/skill-improvement-log/YYYY-MM-DD_summary.md.
Manual Execution
# Dry-run: score one skill without applying improvements or creating PRs
python3 scripts/run_skill_improvement_loop.py --dry-run
# Review all skills in dry-run mode
python3 scripts/run_skill_improvement_loop.py --dry-run --all
# Full run: score, improve if needed, and open PR
python3 scripts/run_skill_improvement_loop.pylaunchd Setup (macOS)
The loop runs daily at 05:00 local time via macOS launchd:
# Install the agent
cp launchd/com.trade-analysis.skill-improvement.plist ~/Library/LaunchAgents/
launchctl load ~/Library/LaunchAgents/com.trade-analysis.skill-improvement.plist
# Verify
launchctl list | grep skill-improvement
# Manual trigger
launchctl start com.trade-analysis.skill-improvementKey Files
| File | Purpose |
|---|---|
scripts/run_skill_improvement_loop.py | Orchestration script (selection, scoring, improvement, PR) |
scripts/run_skill_improvement.sh | Thin shell wrapper for launchd |
launchd/com.trade-analysis.skill-improvement.plist | macOS launchd agent configuration |
skills/dual-axis-skill-reviewer/ | Reviewer skill (scoring engine) |
logs/.skill_improvement_state.json | Round-robin state and history |
reports/skill-improvement-log/ | Daily summary reports |
Skill Auto-Generation Pipeline
This section is contributor-oriented. It describes repository maintenance automation, not a required trading workflow.
An automated pipeline that mines session logs for skill ideas (weekly) and designs, reviews, and creates new skills as PRs (daily). Works alongside the Self-Improvement Loop to continuously expand the skill catalog.
How It Works
- Weekly mining — scans Claude Code session logs for recurring patterns that could become skills, scores each idea for novelty, feasibility, and trading value.
- Backlog scoring — ranked ideas are stored in
logs/.skill_generation_backlog.yamlwith status tracking (pending,in_progress,completed,design_failed,review_failed,pr_failed). - Daily selection — picks the highest-scoring
pendingidea; retriesdesign_failed/pr_failedonce (butreview_failedis terminal). - Design & review — the Skill Designer builds a complete skill (SKILL.md, references, scripts), then the Dual-Axis Reviewer scores it. If the score is too low, the idea is marked
review_failed. - PR creation — commits the new skill to a feature branch and opens a GitHub PR for human review.
Manual Execution
# Weekly: mine ideas from session logs and score them
python3 scripts/run_skill_generation_pipeline.py --mode weekly --dry-run
# Daily: design a skill from the highest-scoring backlog idea
python3 scripts/run_skill_generation_pipeline.py --mode daily --dry-run
# Full daily run (creates branch, designs skill, opens PR)
python3 scripts/run_skill_generation_pipeline.py --mode dailylaunchd Setup (macOS)
Two launchd agents handle the weekly and daily schedules:
# Install both agents
cp launchd/com.trade-analysis.skill-generation-weekly.plist ~/Library/LaunchAgents/
cp launchd/com.trade-analysis.skill-generation-daily.plist ~/Library/LaunchAgents/
launchctl load ~/Library/LaunchAgents/com.trade-analysis.skill-generation-weekly.plist
launchctl load ~/Library/LaunchAgents/com.trade-analysis.skill-generation-daily.plist
# Verify
launchctl list | grep skill-generation
# Manual trigger
launchctl start com.trade-analysis.skill-generation-weekly
launchctl start com.trade-analysis.skill-generation-dailyKey Files
| File | Purpose |
|---|---|
scripts/run_skill_generation_pipeline.py | Orchestration script (mining, selection, design, review, PR) |
scripts/run_skill_generation.sh | Thin shell wrapper for launchd |
launchd/com.trade-analysis.skill-generation-weekly.plist | Weekly mining schedule (Saturday 06:00) |
launchd/com.trade-analysis.skill-generation-daily.plist | Daily generation schedule (07:00) |
skills/skill-idea-miner/ | Mining and scoring skill |
skills/skill-designer/ | Skill design prompt builder |
logs/.skill_generation_backlog.yaml | Scored idea backlog with status tracking |
logs/.skill_generation_state.json | Run history and state |
reports/skill-generation-log/ | Daily generation summary reports |
Customization & Contribution
- Update
SKILL.mdfiles to tweak trigger descriptions or capability notes; ensure the frontmatter name matches the folder name when zipping. - Extend reference documents or add scripts inside each skill folder to support new workflows.
- When distributing updates, regenerate the matching
.skillfile inskill-packages/so web-app users get the latest version:
``bash python3 scripts/package_skills.py --skill <skill-name> ``
API Requirements
Several skills require API keys for data access:
Skills Requiring APIs
| Skill | FMP API | FINVIZ Elite | Alpaca | Notes |
|---|---|---|---|---|
| Economic Calendar Fetcher | ✅ Required | ❌ Not used | ❌ Not used | Fetches economic events |
| Earnings Calendar | ✅ Required | ❌ Not used | ❌ Not used | Fetches earnings dates |
| Institutional Flow Tracker | ✅ Required | ❌ Not used | ❌ Not used | 13F filings analysis, free tier sufficient |
| Value Dividend Screener | ✅ Required | 🟡 Optional | ❌ Not used | FINVIZ reduces execution time 70-80% |
| Dividend Growth Pullback Screener | ✅ Required | 🟡 Optional | ❌ Not used | FINVIZ for RSI pre-screening |
| Kanchi Dividend SOP | ❌ Not used | ❌ Not used | ❌ Not used | Knowledge workflow; uses outputs from other skills or manual lists |
| Kanchi Dividend Review Monitor | ❌ Not used | ❌ Not used | ❌ Not used | Local rule engine; consumes normalized input JSON |
| Kanchi Dividend US Tax Accounting | ❌ Not used | ❌ Not used | ❌ Not used | Knowledge workflow for classification/account location |
| Pair Trade Screener | ✅ Required | ❌ Not used | ❌ Not used | Statistical arbitrage analysis |
| Options Strategy Advisor | 🟡 Optional | ❌ Not used | ❌ Not used | FMP for stock data; theoretical pricing works without |
| Portfolio Manager | ❌ Not used | ❌ Not used | ✅ Required | Real-time holdings via Alpaca MCP |
| CANSLIM Stock Screener | ✅ Required | ❌ Not used | ❌ Not used | Phase 3.1 (7 components, multi-period RS); free tier sufficient for 35 stocks; Finviz web scraping for institutional data |
| VCP Screener | ✅ Required | ❌ Not used | ❌ Not used | Stage 2 + VCP pattern screening; free tier sufficient |
| Parabolic Short Trade Planner | ✅ Required | ❌ Not used | ✅ Phase 3 / 🟡 Phase 2 | FMP for Phase 1 screener; Alpaca required for Phase 3 intraday bars (paper feed OK), optional for Phase 2 borrow checks. No SDK — requests direct |
| FTD Detector | ✅ Required | ❌ Not used | ❌ Not used | Index price data for rally/FTD detection |
| IBD Distribution Day Monitor | ✅ Required | ❌ Not used | ❌ Not used | Daily QQQ/SPY OHLCV for Distribution Day detection |
| Macro Regime Detector | ✅ Required | ❌ Not used | ❌ Not used | Cross-asset ETF ratio analysis |
| Market Breadth Analyzer | ❌ Not used | ❌ Not used | ❌ Not used | Uses free GitHub CSV data |
| Uptrend Analyzer | ❌ Not used | ❌ Not used | ❌ Not used | Uses free GitHub CSV data |
| Sector Analyst | ❌ Not used | ❌ Not used | ❌ Not used | Uses free GitHub CSV data; optional chart images |
| Theme Detector | 🟡 Optional | 🟡 Optional | ❌ Not used | Core: FINVIZ public + yfinance (free). FMP for ETF holdings, FINVIZ Elite for stock lists |
| FinViz Screener | ❌ Not used | 🟡 Optional | ❌ Not used | Public screener free; FINVIZ Elite auto-detected from $FINVIZ_API_KEY |
| Edge Candidate Agent | ❌ Not used | ❌ Not used | ❌ Not used | Local YAML generation; validates against local pipeline repo |
| Trade Hypothesis Ideator | ❌ Not used | ❌ Not used | ❌ Not used | Local JSON hypothesis pipeline with optional strategy export |
| Edge Strategy Reviewer | ❌ Not used | ❌ Not used | ❌ Not used | Deterministic scoring on local YAML drafts |
| Edge Pipeline Orchestrator | ❌ Not used | ❌ Not used | ❌ Not used | Orchestrates local edge skills via subprocess |
| Edge Signal Aggregator | ❌ Not used | ❌ Not used | ❌ Not used | Aggregates local edge-skill JSON/YAML outputs into weighted ranked signals |
| Trader Memory Core | 🟡 Optional | ❌ Not used | ❌ Not used | FMP only for MAE/MFE in postmortem; core features work offline |
| Exposure Coach | 🟡 Optional | ❌ Not used | ❌ Not used | FMP only when institutional-flow-tracker data is included |
| Signal Postmortem | 🟡 Optional | ❌ Not used | ❌ Not used | FMP for fetching realized returns; manual price entry also supported |
| Dual-Axis Skill Reviewer | ❌ Not used | ❌ Not used | ❌ Not used | Deterministic scoring + optional LLM review |
API Setup
Financial Modeling Prep (FMP) API:
- Free tier: 250 requests/day (sufficient for most use cases)
- Sign up: https://financialmodelingprep.com/developer/docs
- Set environment variable:
export FMP_API_KEY=your_key_here - Or provide key via command-line argument when prompted
FINVIZ Elite API:
- Subscription: $39.50/month or $299.50/year
- Sign up: https://elite.finviz.com/
- Set environment variable:
export FINVIZ_API_KEY=your_key_here - Provides fast pre-screening for dividend screeners
Alpaca Trading API:
- Free paper trading account available
- Sign up: https://alpaca.markets/
- Requires Alpaca MCP Server configuration
- Set environment variables:
``bash export ALPACA_API_KEY="your_api_key_id" export ALPACA_SECRET_KEY="your_secret_key" export ALPACA_PAPER="true" # or "false" for live trading ``
Support & Further Reading
- Claude Skills launch overview: https://www.anthropic.com/news/skills
- Claude Code Skills how-to: https://docs.claude.com/en/docs/claude-code/skills
- Financial Modeling Prep API: https://financialmodelingprep.com/developer/docs
Questions or suggestions? Open an issue or include guidance alongside the relevant skill folder so future users know how to get the most from these trading assistants.
License
All skills and reference materials in this repository are provided for educational and research purposes.