Results for “activation-recompute”

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

Action (apaz-action)

Retoma uma feature pausada (listada em paused-features de active-requirements.json) e a torna ativa. Use quando o usuário digitar "/reversa-resume", "reversa-resume", "retomar feature pausada" ou pedir para voltar a uma feature anterior. NÃO cria features novas, apenas troca a ativa pela escolhida e (quando faz sentido) move a ativa atual para paused-features.

当需要进入高度专注、高效且愉悦的工作或学习状态时

Performs arbitrary-precision arithmetic calculations including addition, subtraction, multiplication, division, and exponents. Use when the user asks to calculate, compute, or evaluate math expressions, or when precise decimal arithmetic is needed to avoid floating-point errors.

Execute the full AgentHub competition lifecycle in a single command: initialize, capture baseline, spawn agents, evaluate results, and merge the winner.

Regenerates a specific code layer (schemas, services, routes, hooks, ui) or all layers, then runs the corresponding validation checks.

Action (afaz-action)

セッション再開時に最新5件のhandoffを読み込み文脈を復元するスキル。「おはよう」「こんにちは」「こんばんは」「再開」「restart」または /resume-session を呼んだ時にトリガーする。new-session の対（読込側）。

One-shot lifecycle command that chains init → baseline → spawn → eval → merge in a single invocation.

Analyze auto-memory for promotion candidates, stale entries, consolidation opportunities, and health metrics.

Turn "what should we pay reps and what number do we give them" into a defensible comp and quota plan. Reconciles a top-down number against a bottom-up build, sets the OTE mix, lays out accelerators, and names the behaviors the plan will drive and the ones it will break. Built for B2B sales leaders, customizable to your motion and your segments. Trigger on "design the comp plan", "set quotas", "what OTE should I pay", "reconcile top-down and bottom-up", "what will this plan actually incentivize", or any comp or quota build.

One-shot lifecycle command that chains init → baseline → spawn → eval → merge in a single invocation. Use when the user runs /hub:run or asks to execute a full AgentHub competition end-to-end.

Use when code is hard to read, has duplication, is too complex, has grown beyond 300 lines, or needs restructuring without changing behavior. For extracting functions, simplifying nested logic, removing dead code, improving naming, splitting large files, and applying clean code principles. Activate when user says "clean this up", "this is messy", "simplify", "extract", or "improve readability".

Plan and execute a comprehensive red team engagement covering reconnaissance through post-exploitation using MITRE ATT&CK-aligned TTPs to evaluate an organization's detection and response capabilities.

Action (axaz-action)

Resume an interrupted AgenTeam run with verify-first strategy.

Use when tuning RL reward function weights, fixing reward hacking, or addressing P&L gradient issues

Action (acaz-action)

当面对新任务或目标，因过度思考“如何开始”或“需要多久”而陷入拖延、焦虑，迟迟无法行动时

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering.

Analyze auto-memory for promotion candidates, stale entries, consolidation opportunities, and health metrics. Use when the user runs /si:review or asks what has been learned and what should be promoted or pruned.