Results for “causation”

Causal inference framework for answering "does X cause Y?" beyond correlation. DoWhy (Microsoft Research) provides the identify-estimate-refute loop: define a causal graph (DAG), identify the causal effect using backdoor/frontdoor/instrumental variable criteria, estimate treatment effects with multiple estimators, and validate results with automated refutation tests. Use when: distinguishing causation from correlation, estimating treatment effects (ATE, ATT, CATE), designing and analyzing A/B tests with confounders, using instrumental variables, performing counterfactual reasoning ("what would have happened if..."), validating causal claims with sensitivity analysis, working with observational data where randomization is impossible, or any analysis where the question is "what is the CAUSAL effect of X on Y" rather than just "how do X and Y relate?"

This skill should be used when the user asks to "implement a DiD regression", "write a causal inference pipeline", "set up an event study", "implement instrumental variables", "run a regression discontinuity design", "build a synthetic control model", "implement propensity score matching", "write parallel trends test", "implement Bacon decomposition", or needs code templates for causal inference methods in Python, R, or Stata. Based on Scott Cunningham's Causal Inference: The Mixtape.

Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode

Frame causal questions and estimate treatment effects with assumption checks. Use when: (1) policy impact analysis, (2) A/B interpretation beyond correlation, (3) confounding diagnostics. NOT for: medical/legal conclusions without experts.

Analyze complex systems through stocks, flows, and feedback loops to find high-leverage interventions. For organizational, environmental, social, and technical systems exhibiting circular causality. NOT for linear problems or simple cause-effect chains.

Guide a team through writing a structured, blameless post-mortem after a production incident, covering timeline reconstruction, root cause analysis, impact quantification, and action item generation.

Runs a hypothesis-driven debugging workflow that reproduces failures, forms discriminating tests, proves root cause via toggle, and delivers a fix, regression test, and postmortem.

Use to find the causes behind a complaint population and track whether remediation actually stopped them recurring. Trigger for "root cause analysis on our complaints", "why do we keep getting the same complaints", "complaint themes and remediation", recurring complaint categories, complaint reduction programmes, or a remediation that was signed off and did not work.

Conduz investigação de incidentes com método: triagem, hipóteses, mitigação, RCA e postmortem, priorizando evidências e confirmação humana.

Maneja exibicao de documento ou coisa — contra a PARTE (CPC 396-400: pedido 397, resposta em 5 dias 398, recusa nao admitida 399, presuncao de veracidade se recusa ilegitima 400) ou contra TERCEIRO (CPC 401-404: citacao em 15 dias, audiencia especial 402, deposito/apreensao 403, escusas 404) — e a arguicao de FALSIDADE documental (CPC 430-433: suscitada na contestacao/replica/15 dias da juntada 430, motivos e meios 431, exame pericial 432, coisa julgada se questao principal 433; onus da prova 429). Use quando o operador disser exibicao de documento, obrigar a apresentar documento, incidente de falsidade, documento falso nos autos, parte esconde documento, exibicao de coisa.

Trigger or resolve a PagerDuty incident for on-call escalation

Perform causal interventions on PyTorch models using pyvene's declarative framework for causal tracing, activation patching, and interchange intervention training.

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.

Forces unrelated concepts together to spark novel solutions and emergent properties.

Use to design or audit the executive escalation path for a major account — intake, ownership, communication cadence and follow-through — so escalations are resolved rather than merely attended. Trigger for "design our escalation process for key accounts", "an executive escalation went badly", "customer went to our CEO", red account war rooms, or escalations that get attention and then quietly stall.

Find root causes of bugs, test failures, or unexpected behavior before proposing any fixes.

Multi-tiered memory management (HOT/WARM/COLD) for context compaction. Invoke ONLY for explicit compaction events: post-`/compact` cleanup, MEMORY.md tier promotion, archive batch, or "trim my context". NOT for general recall (use deep-recall) or routine memory writes (use storage-router). Triggers: "compact memory", "promote to durable", "archive old context", "tier this".

Systematic debugging with root cause investigation. (gstack)

Diagnose bugs by establishing a tight feedback loop, tracing root cause, and verifying fixes with regression tests before making changes.

Forces unrelated concepts together to spark novel solutions and uncover emergent properties.

Use to reconstruct what actually happened to one customer across every conversation, channel and handoff, for an escalation, complaint, post-mortem or goodwill decision. Trigger for "build a timeline for this customer", "what happened on this case", "summarize the back-and-forth before I decide", "when were they first told", escalation summaries, complaint investigations, or a case spanning several tickets.

Econometrics skill for machine learning methods in causal inference. Activates when the user asks about: "causal forest", "generalized random forest", "GRF", "double machine learning", "DML", "debiased machine learning", "LASSO for variable selection", "post-LASSO", "heterogeneous treatment effects", "CATE", "conditional average treatment effect", "BLP analysis", "CLAN analysis", "causal tree", "honest estimation", "因果森林", "双重机器学习", "异质性处理效应", "条件平均处理效应", "LASSO变量选择", "机器学习因果推断", "去偏机器学习"

Structured root cause analysis for arriving at a concrete action. Use when something went wrong, a pattern keeps recurring, behavior has drifted, or you catch yourself resolving to "do better" / "remember to X" without a concrete artifact. Five-whys forces behavioral resolutions into file edits, config changes, memory block updates, or scheduled jobs — the action item must produce a diff someone else can verify. Do not use for simple debugging with an obvious cause.

Econometrics skill for machine learning methods in causal inference. Activates when the user asks about: "causal forest", "generalized random forest", "GRF", "double machine learning", "DML", "debiased machine learning", "LASSO for variable selection", "post-LASSO", "heterogeneous treatment effects", "CATE", "conditional average treatment effect", "BLP analysis", "CLAN analysis", "causal tree", "honest estimation", "因果森林", "双重机器学习", "异质性处理效应", "条件平均处理效应", "LASSO变量选择", "机器学习因果推断", "去偏机器学习"

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.

Action (axaz-action)

Provides domain knowledge on the Causal Dynamics Architecture (CDA), an alternative AI computing architecture based on causal graphs and Hamiltonian dynamics, with references for deep dives.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

当需要分析一个观念、文化现象或行为模式为何能广泛传播并被人接受时

Diagnose and mitigate context degradation patterns including lost-in-middle failures, context poisoning, distraction, confusion, and clash in AI agent systems.

Use to audit arrears, collections and financial-difficulty conversations for fair treatment — forbearance offered, pressure absent, vulnerability recognised. Trigger for "audit our collections calls", "are we treating customers in arrears fairly", "did we offer forbearance", financial difficulty handling, payment plan conversations, or a complaint about collections conduct.

Use to clean up sprawling helpdesk tags, categories and custom fields so reporting built on them means something. Trigger for "our tags are a mess", "consolidate our ticket categories", "why don't our tag reports add up", duplicate or near-duplicate tags, tags nobody uses, agents tagging inconsistently, or before building reporting on top of tags.

当需要在写作中与读者建立情感连接、放大问题严重性，并引出后续解决方案时

Understand through recursive decomposition and modular reconstruction of simple operations to reproduce emergent complexity. Use this skill whenever reasoning is required. Framework for [[#parse|parsing]], [[#branch|branching]], [[#reduce|reducing]], [[#ground|grounding]] and [[#emit|emitting]]. Employs metacognitive reasoning epistemology, leveraging first principles through recursive decomposition[^1]. Self-referential and scale-invariant.

Root-cause analysis with hypothesis tracking. Trigger: 'debug', 'broken', 'not working', 'fix this bug', /debug