'decomposition' 검색 결과

Batch effect correction for CRISPR screens covering ComBat empirical-Bayes, RUV, SVA, control-sgRNA normalization, and the model-based alternative of including batch as a covariate in MAGeCK MLE or Chronos. Covers screen-specific batch sources (passage cohort, library lot, infection day, sequencing run, Cas9 lot, FBS lot), PCA + variance-decomposition diagnostic to decide if correction is needed, when correction harms biology by over-correcting condition into batch, limma removeBatchEffect for visualization-only correction, and relationship to multi-condition design matrices. Use when combining screens for joint analysis, when passage cohort confounds biology, when DepMap-style panels need Chronos with batch covariates, when picking ComBat vs RUV, or when correction harms biology and should be replaced with explicit covariate modeling.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Manages git worktrees for parallel agent isolation. Creates isolated worktrees for parallel agents on parallel/{name}-{timestamp} branches, merges results with conflict detection, prunes stale metadata, and reports health status. NOT for user-initiated feature branches — use git worktree directly for that.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when refining a draft user prompt before sending it to a coding agent. Decomposes goal/context/constraints/acceptance/output-format, detects ambiguity and model-coupled framing, then emits a model-agnostic rewrite. Supports --analyze, --score, and --deep. NOT for prompts from scratch (mk:brainstorming), plans/reviews (mk:elicit), implementation plans (mk:plan-creator), or general codebase scouting (mk:scout).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when stuck on approach (not debugging). Strategic unsticking via 7 non-default techniques: simplification cascades, collision-zone thinking, meta-pattern recognition, inversion, scale game, first principles, via negativa. Triggers on complexity spiraling, innovation block, recurring patterns across domains, forced-assumption solutions, scale uncertainty, told-it's-impossible, or bloated systems needing subtraction. For evidence-based root-cause debugging, use mk:sequential-thinking instead.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Auto-decompose large tasks into DAG-compatible parallel subtasks

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Decomposition playbook + specialist-roster conventions + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orchestrator role.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert-level linear algebra knowledge. Use when working with vectors, matrices, determinants, eigenvalues, linear transformations, vector spaces, inner products, decompositions, or applications in machine learning and physics. Also use when the user mentions 'matrix', 'determinant', 'eigenvalue', 'eigenvector', 'linear transformation', 'vector space', 'basis', 'orthogonality', 'SVD', 'PCA', 'least squares', 'null space', or 'rank'.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Structured step-by-step problem decomposition and iterative analysis; explicit request only, never for regular coding tasks, and at most once per task.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when staging multi-component or uncertain work — tackle the load-bearing unknown first (risk-first decomposition), not the easy parts first.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Draft or refine IDD-ready GitHub issues, roadmap issues, and sub-issues before the normal IDD execution loop begins. Use when a request is too large or ambiguous for one reviewable change, when work needs decomposition or dependency encoding, or when the user asks for issue drafting, roadmap planning, or parallelizable task breakdown.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Lightweight multi-agent research orchestration using one coordinator, three domain leads, and three lightweight research agents. Use for medium-size research, market scans, competitor comparisons, prior-art style exploration, report planning, and any task that benefits from parallel domain decomposition without running a full high-cost research lab.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Load for behavior-preserving rename, move, decomposition, dead-code removal, dependency cleanup, record/class conversion, or immutable contract migration that needs caller, flow, test, and impact analysis; not for feature work or one-line cleanup.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

LoRA · Hugging Face — We propose Low-Rank Adaptation, or LoRA, which freezes the pre-trained model weights and injects trainable rank decomposition …;

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Econometrics skill for time series analysis. Activates when the user asks about: "time series", "stationarity", "unit root test", "ADF test", "KPSS test", "ARIMA", "ARMA", "autocorrelation", "ACF", "PACF", "VAR model", "VECM", "Granger causality", "cointegration", "impulse response function", "forecast", "seasonal decomposition", "ARCH", "GARCH", "时间序列", "平稳性检验", "单位根", "自回归", "格兰杰因果", "协整", "脉冲响应", "预测", "向量自回归"

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Knowledge base from the GAO Agile Assessment Guide (GAO-24-105506, 2023). Use for assessing and managing Agile software development in federal programs: the Agile Manifesto and framework family (Scrum, Kanban, XP, SAFe, DA, DSDM, Lean, DevOps); the three adoption perspectives (team dynamics, program operations, organization environment); requirements decomposition (epics, features, user stories, INVEST, MoSCoW, definition of done); Agile-aware federal contracting (FAR, modular contracting, SOO/PWS/SOW, product owner vs. COR); program monitoring and control (WBS, cost, schedule, EVM at the feature level); Agile metrics (velocity, lead/cycle time, CFD, burn charts); and the auditor's key-question bank. Oversight- and acquisition-oriented: it tells you how to *assess and govern* Agile programs, not how to code. Thin on hands-on engineering practice, deep cost/schedule checklists (see gao-cost, gao-schedule), and any non-US-federal context.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Remove signs of AI-generated code from a codebase while preserving behavior. Use when editing or reviewing code to make it read like a human engineer on this team wrote it. Works through a test-guarded detect-modify-verify loop: pin down the functional contract and edge cases first, write or run tests as a safety net, then rewrite AI tells (redundant comments, emoji, verbose names, reflexive try/except, defensive null-guards, over-decomposition, speculative abstraction, dead code, non-idiomatic constructs, hallucinated dependencies) and re-verify after every change. The tests decide whether a defensive block is slop or a real safeguard.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when the user asks to "figure out where our direct traffic really comes from", "measure dark social", "add a how-did-you-hear-about-us field", or "show social drives signups without click data"; produces a share-link/UTM hygiene spec for owned share surfaces, a self-reported attribution field design that replaces an existing form field (free-text first, coded later), a GA4 direct-traffic decomposition read (deep-URL directs, mobile-app skew, private-push correlation) with every derived number hard-labeled Estimated/proxy, and a branded-search-lift proxy from GSC plus Wikipedia pageviews — the declared dark-social method behind ECHO O2. Not for paid-channel attribution reconciliation (platform-claimed vs analytics conversions) — use attribution-reconciler. 暗社交归因/直接流量分解/自报来源字段/分享链路UTM

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when platform-reported conversions disagree with GA4/ecommerce, when you suspect Meta and Google are double-counting the same sales, or for a standing (monthly) reconciliation workbook that de-dups stacked credit against an order-ID truth set, normalizes attribution windows and currency, compares attribution models, and reads incrementality from a geo/holdout test. Not for the point-in-time R2 veto or RQS gate — use ad-account-auditor; not for the ROI/ROAS ratio math itself — use roi-calculator; not for organic dark-social share attribution or GA4 direct-traffic decomposition — use dark-social-attributor. 付费广告归因对账/去重/增量

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Agent Orchestrator IA — Expert en orchestration multi-agent (CrewAI, AutoGen, LangGraph, task decomposition, coordination)

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Task decomposition and multi-agent orchestration with retry, checkpoint recovery, and real-time monitoring. Mixed Codex/Claude Code engine. Parallel/sequential execution.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

planner エージェントによるタスク分解。design.md を基に TaskCreate でネイティブタスクに登録。「タスクに分解して」「タスク分解して」「実装計画を立てて」「何から始める？」で発動。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build SwiftUI views with modern MV architecture, state management, and view composition patterns. Covers @Observable ownership rules, @State/@Bindable/@Environment wiring, view decomposition, custom ViewModifiers, environment values, async data loading with .task, iOS 26+ APIs, Writing Tools, and performance guidelines. Use when structuring a SwiftUI app, managing state with @Observable, composing view hierarchies, or applying SwiftUI best practices.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Write Korean job application cover letter drafts from a question, JD, resume.md, and optional company values input. Use when the user asks for 자기소개서, 자소서, 지원동기, 입사 후 포부, 필살기, 3C4P experience decomposition, experience-based application answers, or tailored cover letter text grounded in resume.md evidence.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.