{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"tool_trading-literacy","slug":"trading-literacy","name":"Trading Literacy","type":"product","url":"https://tradingliteracy.com","page_url":"https://unfragile.ai/trading-literacy","categories":["data-analysis"],"tags":[],"pricing":{"model":"paid","free":false,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"tool_trading-literacy__cap_0","uri":"capability://text.generation.language.conversational.portfolio.data.analysis","name":"conversational portfolio data analysis","description":"Accepts natural language questions about trading activity and portfolio performance, processing them through an LLM-based conversational interface that interprets trader intent and generates contextual responses. The system maintains conversation state across multiple turns, allowing follow-up questions and drill-downs into specific trades or time periods without requiring users to re-upload or re-specify their data context. This differs from traditional dashboard analytics by treating the portfolio as a conversational subject rather than a static visualization.","intents":["Ask questions about my trading performance without learning SQL or dashboard navigation","Get follow-up insights on specific trades or patterns I'm curious about in natural language","Understand why certain trades underperformed without manually calculating metrics"],"best_for":["Self-directed traders with limited quantitative background","Investors who prefer narrative explanations over charts and tables","Portfolio managers seeking behavioral coaching rather than algorithmic signals"],"limitations":["Conversational context window is finite — very large portfolios (10k+ trades) may require data filtering or summarization before analysis","LLM hallucination risk on edge-case calculations; users must verify critical financial conclusions independently","No real-time market data integration — analysis is retrospective only, based on uploaded historical data"],"requires":["Trading activity data in CSV, JSON, or broker statement format","Internet connection for cloud-based LLM inference","Account with Trading Literacy (paid subscription)"],"input_types":["natural language questions","structured trading data (CSV/JSON with trade timestamps, symbols, entry/exit prices, quantities)"],"output_types":["natural language explanations","calculated metrics (win rate, average trade duration, profit factor)","narrative insights about trading patterns"],"categories":["text-generation-language","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_trading-literacy__cap_1","uri":"capability://data.processing.analysis.behavioral.pattern.extraction.from.trade.history","name":"behavioral pattern extraction from trade history","description":"Analyzes sequences of trades to identify recurring behavioral patterns — such as revenge trading after losses, overtrading in specific market conditions, or systematic bias toward certain asset classes. The system likely uses statistical aggregation and LLM-based narrative synthesis to surface patterns that would require manual review across hundreds of trades. This capability bridges quantitative metrics (win rate, drawdown) with qualitative behavioral insights (emotional decision-making, discipline lapses).","intents":["Identify my recurring trading mistakes or emotional patterns without manual trade review","Understand if I trade differently after losses or wins","Discover systematic biases in my asset selection or position sizing"],"best_for":["Traders focused on self-improvement and behavioral accountability","Investors who recognize emotion as a performance factor","Coaches or mentors analyzing client trading behavior"],"limitations":["Pattern detection requires sufficient trade history (minimum ~50-100 trades recommended) to be statistically meaningful","Behavioral insights are correlative, not causal — cannot definitively prove emotional causation without trader self-reporting","Patterns may be artifacts of market regime rather than trader behavior (e.g., overtrading during volatile periods)"],"requires":["Complete trade history with timestamps, entry/exit prices, and outcomes","Minimum 30+ trades for meaningful pattern detection","Optional: trader notes or journal entries for context enrichment"],"input_types":["structured trade data (timestamps, symbols, P&L, duration)","optional narrative trader notes or journal entries"],"output_types":["behavioral pattern summaries (e.g., 'revenge trading detected after 3+ consecutive losses')","statistical correlations (e.g., 'win rate drops 15% on Mondays')","narrative coaching feedback"],"categories":["data-processing-analysis","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_trading-literacy__cap_2","uri":"capability://data.processing.analysis.manual.trading.data.ingestion.and.normalization","name":"manual trading data ingestion and normalization","description":"Accepts trading data uploads in multiple formats (CSV, JSON, broker statements) and normalizes them into a standardized internal schema for analysis. The system likely performs format detection, field mapping, and data validation to handle variations in how different brokers export trade records. This is a critical integration point that avoids the friction of direct broker API connections but requires users to manually export and upload their data.","intents":["Upload my trading history from my broker without needing API credentials or technical setup","Analyze trades across multiple brokers by consolidating exports into a single dataset","Start using the tool immediately without waiting for broker API integration"],"best_for":["Traders using brokers without native API support or with restrictive API policies","Users who prefer not to grant API access to third-party tools","Multi-broker traders who need consolidated analysis"],"limitations":["Manual upload creates friction and staleness — data is not automatically refreshed as new trades execute","Requires users to understand their broker's export format and manually download files","No support for real-time trade monitoring or intraday analysis","Data validation errors may require users to manually clean or reformat exports"],"requires":["Access to broker's trade export functionality (CSV or statement download)","File size limit (likely 10-100MB based on typical SaaS constraints)","Supported formats: CSV, JSON, or common broker statement formats"],"input_types":["CSV files with trade records","JSON structured trade data","Broker-specific statement formats (PDF or text exports)"],"output_types":["normalized trade records in internal schema","validation report with errors or warnings","data quality summary"],"categories":["data-processing-analysis","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_trading-literacy__cap_3","uri":"capability://data.processing.analysis.performance.metrics.calculation.and.contextualization","name":"performance metrics calculation and contextualization","description":"Computes standard trading performance metrics (win rate, profit factor, Sharpe ratio, maximum drawdown, average trade duration) from uploaded trade data and contextualizes them through conversational explanation. Rather than displaying raw numbers, the system explains what each metric means, how the trader's performance compares to benchmarks, and what the metrics reveal about trading style. This bridges the gap between quantitative rigor and accessibility for non-technical traders.","intents":["Understand what my trading metrics actually mean and whether they're good or bad","Compare my performance to realistic benchmarks without needing to research industry standards","Get plain-English explanations of technical metrics like Sharpe ratio or profit factor"],"best_for":["Retail traders without quantitative finance background","Traders seeking educational context alongside performance data","Coaches or mentors explaining performance to clients"],"limitations":["Benchmark comparisons are generic and may not account for trader's specific market, timeframe, or strategy","Metrics assume complete and accurate trade data — missing trades or incorrect entry/exit prices skew results","No risk-adjusted performance attribution (cannot isolate alpha from beta or market exposure)","Historical metrics are backward-looking and do not predict future performance"],"requires":["Complete trade history with entry/exit prices, quantities, and timestamps","Accurate P&L calculation (entry price × quantity vs. exit price × quantity)","Optional: risk-free rate or benchmark index for Sharpe ratio calculation"],"input_types":["structured trade data with OHLC prices and execution timestamps"],"output_types":["calculated metrics (win rate %, profit factor, Sharpe ratio, max drawdown %)","narrative explanations of metric meaning and implications","benchmark comparisons and performance context"],"categories":["data-processing-analysis","text-generation-language"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_trading-literacy__cap_4","uri":"capability://data.processing.analysis.trade.by.trade.performance.review.and.feedback","name":"trade-by-trade performance review and feedback","description":"Enables users to ask questions about specific individual trades or trade sequences, receiving detailed analysis of entry/exit decisions, timing, position sizing, and outcomes. The system retrieves relevant trade data from the portfolio context and generates explanations of what happened, why it happened, and what could have been done differently. This capability supports iterative learning by allowing traders to drill down from high-level patterns to specific trade decisions.","intents":["Understand why a specific trade failed and what I could have done differently","Review my best trades to identify what I did right and replicate it","Analyze a sequence of related trades to understand cumulative impact"],"best_for":["Traders committed to detailed post-trade analysis and learning","Coaches reviewing client trades for educational feedback","Traders with moderate portfolio size (100-1000 trades) where individual review is feasible"],"limitations":["Detailed review of very large portfolios (10k+ trades) becomes impractical without filtering or summarization","Hindsight bias — analysis of 'what could have been' is inherently backward-looking and may not reflect realistic decision-making at trade time","No access to trader's real-time market data or news context at time of trade — analysis is based on price data alone","LLM may generate plausible-sounding but incorrect explanations of trade mechanics"],"requires":["Specific trade identifier (date, symbol, entry/exit prices) or natural language trade description","Complete trade record with entry/exit prices, quantities, timestamps, and P&L","Optional: trader notes or journal entries from time of trade for context"],"input_types":["natural language trade queries (e.g., 'Why did my AAPL trade on March 15 lose money?')","structured trade identifiers (symbol, date, entry/exit price)"],"output_types":["trade analysis narrative (entry/exit timing, position sizing, risk/reward)","outcome explanation (why the trade succeeded or failed)","alternative scenarios or lessons learned"],"categories":["data-processing-analysis","text-generation-language","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_trading-literacy__cap_5","uri":"capability://data.processing.analysis.time.period.and.market.condition.filtering.for.comparative.analysis","name":"time-period and market-condition filtering for comparative analysis","description":"Allows users to ask questions that implicitly or explicitly filter trades by time period, market condition, or asset class (e.g., 'How did I trade during the March 2023 rally?' or 'Compare my performance in bull vs. bear markets'). The system interprets these natural language filters, applies them to the portfolio data, and generates comparative analysis. This capability enables traders to understand how their behavior and performance vary across different market regimes without requiring manual data slicing.","intents":["Understand how my trading performance differs between bull and bear markets","Analyze my behavior during specific market events or time periods","Compare my performance across different asset classes or trading styles"],"best_for":["Traders seeking to understand regime-dependent performance","Investors analyzing how their strategy adapts to market conditions","Coaches identifying when traders struggle most"],"limitations":["Market regime classification is heuristic-based (e.g., bull/bear defined by index returns) and may not match trader's actual market perception","Requires sufficient trades in each filtered subset for meaningful comparison (minimum ~10-20 trades per group)","Natural language filter interpretation may be ambiguous (e.g., 'volatile markets' could mean VIX > 20 or daily swings > 2%)","No integration with external market data — regime classification is based on portfolio returns alone"],"requires":["Trade history with timestamps spanning multiple market periods","Optional: external market data (index returns, VIX, volatility metrics) for regime classification","Minimum 50+ trades for meaningful comparative analysis"],"input_types":["natural language queries with implicit or explicit time/condition filters","structured trade data with timestamps and asset classes"],"output_types":["filtered trade subsets with performance metrics","comparative analysis across conditions (e.g., 'win rate 60% in bull markets vs. 40% in bear markets')","narrative insights about regime-dependent behavior"],"categories":["data-processing-analysis","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_trading-literacy__cap_6","uri":"capability://data.processing.analysis.risk.and.position.sizing.analysis.with.feedback","name":"risk and position-sizing analysis with feedback","description":"Analyzes position sizing decisions across the portfolio and identifies patterns in risk management — such as oversized positions, inconsistent stop-loss placement, or risk-per-trade variance. The system calculates metrics like risk-per-trade percentage, position size relative to account, and maximum exposure, then generates coaching feedback on whether sizing is appropriate for the trader's stated risk tolerance. This addresses a critical gap in trader education where position sizing discipline directly impacts long-term survival.","intents":["Understand if my position sizes are appropriate for my account size and risk tolerance","Identify if I'm taking inconsistent risks across different trades","Get feedback on whether my stop-loss placement is disciplined or emotional"],"best_for":["Traders focused on risk management and capital preservation","Traders with inconsistent position sizing who want to improve discipline","Coaches teaching position sizing principles to clients"],"limitations":["Risk analysis assumes fixed account size — does not account for dynamic account growth or drawdown","Stop-loss analysis is based on executed trades; does not evaluate mental stops or intended stops that were not placed","No integration with broker margin requirements or leverage limits — analysis is position-sizing only","Feedback is educational, not prescriptive — system cannot enforce position sizing rules"],"requires":["Trade data with entry/exit prices, quantities, and account size at time of trade","Optional: stated risk tolerance or risk-per-trade target for comparison","Optional: stop-loss prices or risk amounts for each trade"],"input_types":["structured trade data with position sizes, entry/exit prices, and account balance","optional trader-specified risk targets or risk tolerance"],"output_types":["position sizing metrics (risk per trade %, max exposure, position size relative to account)","variance analysis (consistency of risk across trades)","coaching feedback on sizing discipline"],"categories":["data-processing-analysis","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_trading-literacy__cap_7","uri":"capability://memory.knowledge.multi.turn.conversational.context.persistence.across.sessions","name":"multi-turn conversational context persistence across sessions","description":"Maintains conversation state and portfolio context across multiple user sessions, allowing traders to return to previous analyses and continue drilling down into patterns without re-uploading data or re-specifying context. The system stores conversation history, portfolio snapshots, and analysis state in a user-specific knowledge base, enabling continuity and reference to previous insights. This differs from stateless chatbots by treating the portfolio as persistent context that accumulates insights over time.","intents":["Return to my portfolio analysis days or weeks later and continue where I left off","Reference previous insights or patterns I discovered in earlier conversations","Build on previous analyses without re-uploading data or re-explaining my trading style"],"best_for":["Traders using the tool over weeks or months for ongoing learning","Coaches conducting iterative client reviews across multiple sessions","Traders who want to track how their insights and patterns evolve over time"],"limitations":["Conversation history storage requires backend persistence — increases infrastructure cost and data privacy considerations","Context window size is finite — very long conversations may require summarization or pruning of old context","Portfolio snapshots become stale as new trades execute — system must handle incremental data updates","No explicit version control — users cannot easily compare analyses from different time periods"],"requires":["User account with persistent storage backend","Session management and authentication","Conversation history database with sufficient retention policy"],"input_types":["natural language queries in new sessions","optional: new trade data uploads for incremental updates"],"output_types":["conversation history and previous insights","updated analyses incorporating new trades","references to previous patterns or conclusions"],"categories":["memory-knowledge","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_trading-literacy__cap_8","uri":"capability://text.generation.language.educational.coaching.and.trading.principle.explanation","name":"educational coaching and trading principle explanation","description":"Generates educational explanations of trading principles, risk management concepts, and behavioral finance insights based on the trader's specific portfolio and performance data. Rather than generic trading education, the system contextualizes lessons to the trader's actual trades and patterns, making principles concrete and relevant. This capability positions the tool as a coach that teaches through example rather than a signal generator that predicts market moves.","intents":["Learn trading principles and best practices through analysis of my own trades","Understand behavioral finance concepts and how they apply to my specific trading mistakes","Get personalized coaching that addresses my actual weaknesses rather than generic advice"],"best_for":["Traders committed to self-improvement and learning","Traders new to trading who need foundational education","Coaches or mentors seeking to personalize education for clients"],"limitations":["Educational content is generated by LLM and may contain inaccuracies or oversimplifications","Coaching is reactive (based on past trades) rather than proactive (preventing future mistakes)","No structured curriculum — learning is ad-hoc based on trader questions rather than systematic progression","Cannot replace formal financial education or professional advisory services"],"requires":["Sufficient trade history to ground lessons in concrete examples","Trader willingness to reflect on mistakes and learn from them","No specific technical prerequisites"],"input_types":["natural language questions about trading principles or behavioral finance","implicit context from trader's portfolio and performance data"],"output_types":["educational explanations of trading principles","behavioral finance insights contextualized to trader's trades","coaching feedback and improvement suggestions"],"categories":["text-generation-language","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":37,"verified":false,"data_access_risk":"high","permissions":["Trading activity data in CSV, JSON, or broker statement format","Internet connection for cloud-based LLM inference","Account with Trading Literacy (paid subscription)","Complete trade history with timestamps, entry/exit prices, and outcomes","Minimum 30+ trades for meaningful pattern detection","Optional: trader notes or journal entries for context enrichment","Access to broker's trade export functionality (CSV or statement download)","File size limit (likely 10-100MB based on typical SaaS constraints)","Supported formats: CSV, JSON, or common broker statement formats","Complete trade history with entry/exit prices, quantities, and timestamps"],"failure_modes":["Conversational context window is finite — very large portfolios (10k+ trades) may require data filtering or summarization before analysis","LLM hallucination risk on edge-case calculations; users must verify critical financial conclusions independently","No real-time market data integration — analysis is retrospective only, based on uploaded historical data","Pattern detection requires sufficient trade history (minimum ~50-100 trades recommended) to be statistically meaningful","Behavioral insights are correlative, not causal — cannot definitively prove emotional causation without trader self-reporting","Patterns may be artifacts of market regime rather than trader behavior (e.g., overtrading during volatile periods)","Manual upload creates friction and staleness — data is not automatically refreshed as new trades execute","Requires users to understand their broker's export format and manually download files","No support for real-time trade monitoring or intraday analysis","Data validation errors may require users to manually clean or reformat exports","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.2833333333333333,"quality":0.63,"ecosystem":0.2,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.1,"match_graph":0.35,"freshness":0.05}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:33.648Z","last_scraped_at":"2026-04-05T13:23:42.562Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=trading-literacy","compare_url":"https://unfragile.ai/compare?artifact=trading-literacy"}},"signature":"EsVXlpJLKqC1ogMxby2LcKFJchiTD6raUGVVbP6Lyd/X96KDp88IClYiktuGEz0LHOTY+3tidnCfRHfHJ1INAQ==","signedAt":"2026-06-22T11:21:08.888Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/trading-literacy","artifact":"https://unfragile.ai/trading-literacy","verify":"https://unfragile.ai/api/v1/verify?slug=trading-literacy","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}