'foundation' 검색 결과

16 evidence-graded behavioral-economics primitives. Use when asking will this nudge work, is a pricing decoy or dark pattern lawful, or what effect size to expect.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

PID/MPC/Kalman/anti-windup control primitives for feedback loops. Use when an autoscaler flaps, a controller overshoots after saturation, or budget pacing overspends at peak.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Formulates LP, MILP, CP-SAT models; diagnoses infeasibility and gaps. Use when a MILP is infeasible, shifts need scheduling under capacity, or choosing a solver.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Designs consensus, quorums, leases, idempotency, and CRDTs. Use when facing split brain, fencing tokens, exactly-once claims, duplicate retries, stale reads, or leader flapping.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Team-theory primitives for cooperative agents: what each subagent sees, when to communicate, aggregation, Shapley credit, coalition topology. Use when organizing subagents.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Computes availability for redundant and series designs, failover, SPOFs, fault trees, FMEA, Weibull, and error budgets. Use when asking what uptime a design gives.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Tests whether changes caused a metric move without a clean A/B test: DiD, synthetic control, IV, RDD. Use when asking did a launch cause lift.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Tests whether data supports a claim: A/B significance, peeking, sample size, eval error bars, multiple comparisons. Use when deciding if results are significant.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Audits whether scores, benchmarks, LLM judges, or surveys measure what we think. Use when a benchmark is saturated, a score unreliable, or judge agreement untrustworthy.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Proves protocols and agent workflows with TLA+, P, Alloy, Z3, Dafny, or Lean. Use when proving protocols correct, writing TLA+ specs, or verifying LLM proofs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Analyzes hazards in systems or AI agents: STPA, guardrails, safety cases, incident analysis. Use when an agent can take actions or send payments.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Evaluates neuromarketing studies and neural-data law. Use when judging EEG, fMRI, eye-tracking, or GSR ad study or vendor, or if signals are regulated neural data.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Game-theory primitives for divergent incentives: Nash equilibrium, auctions, mechanism design, collusion, bargaining, reputation. Use when modeling strategic play.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Theory of Constraints primitives for focusing steps, drum-buffer-rope, throughput accounting, critical chain, and policy constraints. Use when sequencing by bottleneck.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Measures entropy, mutual information, KL/JS, bits-per-byte. Use when picking KL direction, comparing cross-tokenizer perplexity, trusting MI estimates, or semantic-entropy gating.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Applies planning/search theory (A*, CSP, MCTS, PDDL, HTN) to agents. Use when ordering tool calls, enforcing preconditions before side effects, or validating a plan.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Builds and backtests demand and revenue forecasts: rolling-origin backtests, prediction intervals, reconciliation, zero-shot foundation models. Use when forecasting time series.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Foundational voice authority and AI humanizer — writes content in the user's authentic voice with built-in AI detection, and supports stealth / anti- attribution writing (forum personas, anonymous posts, "write as not-me"). Use when asked to write/draft/generate content, invoke /voice, /write-as-me, or /humanize, run voice calibration, check "does this sound like me?", "make this sound human" / "de-AI this", "write a forum post as [persona]", or run AI detection ("does this sound like AI?", "check for AI patterns", "anti-slop check"). Do NOT use this skill for code, technical docs, or any output the user has not asked to be written in their voice — code styling defers to the separate code-voice skill.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Defining and managing design tokens, applying token systems to existing codebases, building design system foundations. Use for spacing, color, typography, dark mode, cross-platform output.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

When the user wants to create or update their product marketing context document. Also use when the user mentions 'product context,' 'marketing context,' 'set up context,' 'positioning,' 'who is my target audience,' 'describe my product,' 'ICP,' 'ideal customer profile,' or wants to avoid repeating foundational information across marketing tasks. Use this at the start of any new project before using other marketing skills — it creates `.agents/product-marketing.md` that all other skills reference for product, audience, and positioning context.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Apply evidence-first engineering discipline to any agent-built software project: fact discovery before action, evidence-calibrated status reporting, explicit change boundaries and stage gates, controlled confirmation for risky or external actions, sensitive-information redaction for anything shared publicly, and resumable continuity after interruptions. Use when users ask an agent to take over an existing codebase, deliver a feature across stages, verify whether work is actually complete, judge release readiness, or keep conclusions honest about what is proven versus assumed. This foundation skill is domain-neutral; vertical suites (for example mini-program engineering) build on it by adding domain facts and platform rules.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Establish project context - foundation for all design work

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Orchestrator skill that takes a warp-apply receipts directory and proposes each batch to its corresponding multisig signer — Safe Transaction Service via `safes/propose-warp-batch.ts` for EVM batches (auto-detects governance context: AW / Foundation / Regular / etc. per filename), Squads via `squads/propose-warp-batch.ts` for SVM batches. Persists a per-ticket proposal summary at `~/.hyperlane/proposals/ticket-id.yaml` so the human can track signing progress in Heimdall or Squads.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Foundation skill for warp-route updates. Reads the current on-chain config of a warp route via `hyperlane warp read`, enumerates every artifact (router, ProxyAdmin, ISM, hook, fee contracts) per chain, classifies each artifact's owner (auto-detects Safe / ICA / EOA; asks the user for everything else — Turnkey, Privy, MPC, custom multisig, timelock, etc.), and persists a per-artifact owner table that downstream update skills consume to know which signing path each batch needs. Read-only — no signing, no on-chain mutations.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.