Results for “mean-reversion”

MAMBA v2.0 — Range-bound high water + regime protection. A trading strategy config override based on the VIPER skill with three protective gates: BTC regime filter, per-asset cooldown after losses, and hard leverage cap at 10x.

Ponto de entrada principal do Reversa. Orquestra a análise completa de um sistema legado, gerando especificações executáveis por agentes de IA. Use quando o usuário digitar "/reversa", "reversa", "iniciar análise" ou "engenharia reversa". É o primeiro skill a ser chamado em qualquer sessão.

Flip a problem, goal, or decision 180 degrees to find what forward thinking misses. Asks what would guarantee failure, then works backward to what must be avoided or changed. Load when the user says "invert this", "flip this problem", "what would guarantee failure", "think backward", "reverse engineer the goal", "think about it backwards", or when deep-thinking diagnoses an inversion frame. Also triggers on "what's the opposite of success here", "how would we sabotage this". Two methods: Failure Inversion and Opposite Goal. Max 2 clarifying questions before inverting. Always returns forward actions. For broader analysis, deep-thinking calls this.

Predict continuous values from temporal sequences using aeon's time series regressors, covering convolutional, deep learning, distance-based, feature-based, hybrid, interval-based, and shapelet-based approaches.

Conduz a execução do actions.md em código. Atualiza checkboxes para [X], escreve progress.jsonl, gera legacy-impact.md e regression-watch.md. Use quando o usuário digitar "/reversa-coding", "reversa-coding", "executar plano" ou pedir para começar a codar a feature ativa. Último skill do ciclo forward, depois de `/reversa-to-do` (e opcionalmente `/reversa-audit` ou `/reversa-quality`).

Configure fault tolerance, straggler detection, preemption, in-process restart, and re-run state machine for Megatron Bridge training jobs.

Build, optimize, backtest, rebalance, or analyze stock portfolios using NVIDIA-accelerated Mean-CVaR optimization with cuOpt GPU solver.

Reverse-engineers a federal RFP we received — given the SOW/PWS and evaluation criteria already in the Theseus KG, reconstructs the CO's hidden decision tree (upstream `sow-pws-builder` 6 scope blocks + 3 intake answers), surfaces hot buttons, ghost language, discriminator hooks, missing-section signals, and CPFF-form / Section-5 / QASP / Key-Personnel traps. USE WHEN the user asks "what scope decisions did the CO already make?", "reverse engineer this RFP", "what hot buttons are hiding in this PWS?", "where are the discriminator hooks?", "did they pick CPFF completion or term form?", "anything suspiciously missing?", or any variant of decoding CO intent. Pulls `requirement`, `deliverable`, `proposal_instruction`, `evaluation_factor`, `clause`, `performance_standard` from the active workspace KG and emits a JSON envelope feeding `proposal-generator`. DO NOT USE FOR proposal prose (`proposal-generator`), pricing (`price-to-win`), clause audit (`compliance-auditor`), or sub SOW (`subcontractor-sow-builder`).

Computes the Recall metric using torchmetrics, including configuration for binary, multiclass, and multilabel tasks.

Voce e o precificador de features do REVERSA. Sua missao e cruzar o profile de cobranca do usuario com as metricas estruturais da feature ativa e produzir tres cenarios educativos em `_reversa_sdd/_pricing/<feature>/estimate.md` e `estimate.json`.

The relevant axis is not "how do we deploy" but "how fast and how cheaply can we

Use the status-briefing skill to run `pk-reconcile session-start`, then

Reverse shell generation and listener management. Generates platform-specific reverse shell payloads (bash, python, php, powershell, java, ruby, perl, netcat, socat, msfvenom) and sets up listeners in the Kali container. Supports one-liner generation, encoded payloads for WAF/filter bypass, listener setup with session capture, and shell stabilization. Chains from /pentester, /metasploit, or /post-exploit when command execution is confirmed.

Authorized reverse engineering of custom binary protocols, Protobuf/gRPC, WebSocket frames, and PCAP-driven protocol recovery with structured workflow and tooling.

Gera um plano de reconstrução bottom-up a partir das specs do Reversa e executa cada tarefa sob demanda, uma por vez, preservando tokens. Use quando quiser reimplementar o software do zero a partir das especificações geradas. Ativação: /reversa-reconstructor

Evaluates the robustness and alignment with human judgment of reference-based and reference-free evaluation metrics for machine translation and summarization, particularly under adversarial conditions.

Configura e diagnostica Nginx: reverse proxy, TLS, HTTP/2, HTTP/3, cache, compressão, rate limit e load balancing, com verificação obrigatória de configuração antes de recarregar.

Analyze historical downtrend durations and generate interactive HTML histograms showing typical correction lengths by sector and market cap.

Extrai conhecimento de negócio implícito do projeto legado — regras de negócio, ADRs retroativos via Git, máquinas de estado e matriz de permissões. Use na fase de interpretação de uma análise de engenharia reversa.

Explica com analogias o que cada agente do Reversa faz e quando usá-lo. Ative com /reversa-agents-help.

Provides structured reverse engineering techniques for analyzing compiled, obfuscated, packed, or virtualized targets including binaries, APKs, WASM, firmware, and custom VMs using static and dynamic analysis workflows.

`analysis-agent`/`task-agent`/`review-agent`: use for recurrence guards on known defects, incidents, or escaped failures; skip speculative risk without a prior failure mechanism.

当观察到或经历某种极端转化现象，或试图主动促成根本性观念转变时

DeepEval — LLM evaluation framework, RAG metrics, hallucination detection, red-teaming, CI/CD integration

通用多轮迭代改进：对任意研究制品反复调用 /review → 解析反馈 → 修复 → 更新 wiki，直到达标

Standard reviewer for correctness and reproducibility. Use when the user asks to talk to Omen, requests a code review, or needs reproducibility verification.

Beta coefficient reference — CAPM, systematic risk, portfolio sensitivity, regression analysis. Use when measuring stock volatility relative to the market or constructing risk-adjusted portfolios.

Bidirectional conversion between Clojure and Elm. Use when migrating projects between these languages in either direction. Extends meta-convert-dev with Clojure↔Elm specific patterns. Use when migrating Clojure projects to Elm, translating functional patterns from JVM to browser, or building type-safe frontends from Clojure logic. Extends meta-convert-dev with Clojure-to-Elm specific patterns for handling dynamic-to-static typing, REPL-driven to TEA architecture, and side effects to managed effects.

Mede o tamanho estrutural da feature ativa lendo requirements, duvidas, plan e tasks do ciclo forward, e gera size.json mais size.md com T-shirt sizing deterministico baseado em tasks e ajuste de risco. Use quando o usuario digitar "/reversa-pricing-size", "reversa-pricing-size", "dimensionar feature" ou "calcular tamanho da feature". Roda depois de `/reversa-to-do` e antes de `/reversa-pricing-estimate`.

Editor-chefe do Time Reversa Docs. Gera index.html com hero e selo único do projeto, injeta mini-selo nas demais páginas, faz auto-discovery de HTMLs auxiliares produzidos por outros agentes do core, valida links e grava telemetria final. Ative com /reversa-docs-publisher, reversa-docs-publisher, regenerar index, refazer selo, atualizar índice.

Reranking retrieved documents with cross-encoders and LLM rerankers. Cohere Rerank v3, Voyage rerank-2, BGE reranker, ColBERT late interaction, Jina reranker. Cost and latency tradeoffs, top-K in / top-N out strategy. USE WHEN: user mentions "rerank", "reranker", "cross-encoder", "Cohere Rerank", "Voyage rerank", "BGE reranker", "ColBERT", "Jina reranker", "bi-encoder" DO NOT USE FOR: initial retrieval - use `advanced-retrieval` or `hybrid-search`; query rewriting - use `query-transformations`; agent decisions - use `agentic-rag`

heath-no-fluff

Pauses mid-conversation to reassess direction, assumptions, and bias, then recommends whether to continue, pivot, or pause.

Fix PPO training early-stop issues. Trigger when: (1) impossible drawdown values (>100%), (2) training stops too early, (3) need adaptive recovery instead of hard stop.

Re-render a hero image into aspect ratios for Instagram, TikTok, YouTube Shorts, and Twitter/X.