Loading...
Loading...
Found 126 Skills
Defines a testable hypothesis with clear success metrics and validation approach. Use when forming assumptions to test, designing experiments, or aligning team on what success looks like.
Quantitative statistics framework for time-series analysis using Longbridge price data — ADF unit root test (stationarity), cointegration (Engle-Granger / Johansen), GARCH volatility modelling (conditional heteroskedasticity), regression diagnostics (Durbin-Watson / Breusch-Pagan), bootstrap confidence intervals, hypothesis tests (t-test / F-test). Requires statsmodels and scipy. Triggers: "量化统计", "ADF检验", "单位根", "协整检验", "GARCH", "自相关", "异方差", "Bootstrap", "假设检验", "量化統計", "ADF檢驗", "單位根", "協整檢驗", "異方差", "假設檢驗", "quantitative statistics", "ADF test", "unit root", "cointegration", "GARCH", "autocorrelation", "heteroskedasticity", "bootstrap", "hypothesis test", "statsmodels".
Investment thesis tracker — maintains and updates the investment thesis for portfolio holdings and watchlist names by continuously tracking key data points (revenue growth, gross margin, user metrics), catalyst progress (new products, expansion, policy), and risk milestones, then renders a verdict on whether the thesis still holds. Triggers: "投资逻辑", "Thesis追踪", "投资假设", "逻辑验证", "跟踪持仓", "买入逻辑", "持仓理由", "投資邏輯", "Thesis追蹤", "投資假設", "邏輯驗證", "追蹤持倉", "investment thesis", "thesis tracking", "investment hypothesis", "thesis validation", "thesis check", "investment rationale", "position monitoring", "thesis intact", "is my thesis still valid".
Guides agents through the 3-step experiment creation flow: defining the hypothesis, configuring rollout, and setting up analytics. Delegates rollout decisions to configuring-experiment-rollout and metric setup to configuring-experiment-analytics. TRIGGER when: user asks to create a new experiment or A/B test, OR when you are about to call experiment-create. DO NOT TRIGGER when: user is updating an existing experiment, managing lifecycle, or only browsing experiments.
Wide before deep. Fans out N parallel divergent thoughts under structurally different cognitive frames (regulator, biology, speedrunner, 10 year old, $0 budget), then scores, clusters, prunes traps, and deepens only the top survivors. The isolated parallel branches and the separated generator/critic phases are load-bearing. Do not collapse them into a single linear thought. Use when the user asks to brainstorm, ideate, generate options, design an architecture, name something, pick between approaches, plan a refactor, design an API or SDK surface, generate hypothesis classes for a fuzzy bug, or any prompt of the shape "give me a few ways to". Also use when the obvious answer feels obvious and wrong, or when the user explicitly invokes /adhd or asks for "ADHD mode".
Use when developing or documenting trading strategies - guides edge hypothesis formation, validates statistical significance, documents strategy rules systematically (entry, exit, risk management). Activates when user says "research this strategy", "document my approach", "test this idea", mentions "trading strategy", "edge", or uses /trading:research command.
Improve activation, retention, and engagement through hypothesis-driven growth experiments.
Scientific method expert for systematic bug investigation and root cause analysis. Use when users report bugs, crashes, unexpected behavior, or debugging requests. Applies hypothesis-driven investigation, controlled experiments, and rigorous validation across any programming language or platform.
Generate falsifiable trade strategy hypotheses from market data, trade logs, and journal snippets. Use when you have a structured input bundle and want ranked hypothesis cards with experiment designs, kill criteria, and optional strategy.yaml export compatible with edge-finder-candidate/v1.
Debug a broken Zoom integration by isolating the failure point and routing into the right Zoom references. Use when auth, API, webhook, SDK, or MCP behavior is failing and you need a ranked hypothesis list plus verification steps.
Conduct statistical hypothesis testing including null/alternative hypothesis formulation, p-values, Type I/II errors, and test statistic selection. Use this skill when the user needs to determine whether a result is statistically significant, choose the right statistical test, interpret p-values correctly, or evaluate research findings — even if they say 'is this result significant', 'which statistical test should I use', or 'what does this p-value mean'.
Use when hunting for threats in an environment, analyzing IOCs, or detecting behavioral anomalies in telemetry. Covers hypothesis-driven threat hunting, IOC sweep generation, z-score anomaly detection, and MITRE ATT&CK-mapped signal prioritization.