'guard' 검색 결과

OpenAI API (developers.openai.com) の Agents SDK (Python / TypeScript)・Agents API (beta)。 Agent, Runner, handoffs, guardrails, tracing, SandboxAgent、 client.beta.agents の sessions / environments / vaults / plugins、 built-in tools（web search, file search, computer use, code interpreter, image generation）、 function tools, vector stores, MCP (Model Context Protocol) connectors, background mode, multi-agent orchestration。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Android アプリ開発 (Kotlin) の Gradle ビルドシステムリファレンス。 Android Gradle Plugin (AGP), Kotlin DSL (build.gradle.kts), version catalog, KSP, R8/ProGuard, App Bundle, baseline profile。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Identifies differential m6A methylation between conditions from MeRIP-seq paired IP/input data using exomePeak2 with `bam_ip` + `bam_input` (control arm) and `bam_treated_ip` + `bam_treated_input` (treatment arm) for integrated GC-bias-aware differential calling (Liu 2022 *NAR Genom Bioinform* 4:lqac046), QNB beta-binomial test (Liu 2017 *BMC Bioinformatics* 18:387), MeTDiff HMM-based differential bundled with MeTPeak, RADAR (Zhang 2019 *Genome Biol* 20:294) with its `filterBins -> diffIP -> reportResult` workflow, and the defensible paired-symmetric case of edgeR / DESeq2 on featureCounts-on-peaks matrices when batch / lot covariates need explicit fixed-effect handling (exomePeak2's top-level API does NOT accept arbitrary covariates). Covers paired vs unpaired vs interaction designs, batch confounding (antibody lot, RNA prep, sequencing run) and the per-lot meta-analysis strategy when exomePeak2 is the primary caller, the stoichiometry-vs-expression-vs-IP-efficiency confound that all MeRIP differential methods inherit, normalisation choice (size factor on IP, on input, on per-sample IP/input ratio), the McIntyre 2020 reproducibility caveat, effect-size filtering as a guardrail against under-powered N=2 designs, and orthogonal-validation routes for absolute stoichiometry (GLORI / SAC-seq / m6Anet `mod_ratio`). Use when comparing m6A levels across two or more conditions, choosing between exomePeak2 / QNB / RADAR / MeTDiff for a given design, handling batch confounding when exomePeak2's API is too rigid, normalising against input properly, distinguishing real hyper- / hypo-methylation from expression-level shifts, applying effect-size thresholds, interpreting volcano plots of differential peaks, or planning a follow-up orthogonal stoichiometry validation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Autonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s compliance.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design spec with 98 rules for building CLI tools that AI agents can safely use. Covers structured JSON output, error handling, input contracts, safety guardrails, exit codes, and agent self-description.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Core context and guardrails for Openrind Desktop native app

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Run a bounded, provider-neutral SDD Composy correction loop on one approved task (EXECUTE, QA, EVIDENCE, REVIEW, VERIFY; at most 3 iterations) with explicit approval, safe-stop guards, and fresh verification. Use to continue an approved TASK autonomously — 'rodar o loop na TASK-003', 'continuar a task até passar', 'start a loop on task 4'. Do NOT use for the host's recurring loop runner, for fleets (sdd-fleet), or for a task without human approval.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Implement exactly one SDD Composy task in the ready state with dependency preflight, TDD RED evidence, allowed paths, real verification commands, and the guarded transition to qa_required. Use when a ready task should be executed — 'executar a TASK-003', 'implementar a próxima tarefa', 'run task 4'. Do NOT use for changes without an approved task (sdd-quick), for autonomous multi-stage correction (sdd-loop), or for QA, review, or verification.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Generate and safely advance the SDD Composy task projection from approved PRD, stories, and TechSpec: import contracts, list/next/show, and guarded start/block/transition/verify. Use when work must be decomposed or a task's state inspected or moved — 'quebrar a spec em tarefas', 'listar as tarefas', 'qual a próxima task', 'mark TASK-003 blocked'. Do NOT use to implement a task (sdd- execute), reconcile Markdown and JSON (sdd-sync), or for a status overview (sdd- status).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Delegate a bounded repository task to an allowlisted external coding CLI through the guarded Flow runner. Use for automatic provider selection or explicit Codex, OpenCode, Kimi, Gemini, or Kiro delegation that requires timeout handling and independent local review.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Arquitetura e diagnóstico AWS — VPC, EC2, ECS, EKS, ALB, NLB, RDS, ElastiCache, S3, CloudFront, Route53, IAM, WAF, GuardDuty. Use quando o usuário disser "AWS", "VPC", "ALB", "RDS", "revisar a arquitetura", "Well-Architected", "subnet", "security group", "IAM", ou citar qualquer serviço AWS. Leitura livre; qualquer mudança passa pelo portão de confirmação.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Write type-safe TypeScript code with strict mode enabled, comprehensive type definitions, proper error handling, and elimination of any types. Use when enabling TypeScript strict mode, adding types to existing JavaScript, fixing type errors, creating type definitions, using utility types, implementing type guards, avoiding any types, creating generic types, or ensuring complete type safety across the codebase.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful mode". (gstack)

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AEM as a Cloud Service Java/OSGi best practices, guardrails, and legacy-to-cloud pattern transformations. Use for Cloud Service–correct bundles, deprecated APIs, schedulers, ResourceChangeListener, replication, Replicator, JCR observation (javax.jcr.observation.EventListener), OSGi Event Admin (org.osgi.service.event.EventHandler), DAM AssetManager, BPA-style fixes, HTL (Sightly) Cloud SDK lint warnings (data-sly-test redundant constant value comparison), or any time you need the detailed pattern reference modules under this skill.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

HTML -> UCUF (Cocos Creator UI) conversion skill. Use for turning a complete HTML source package with ui-design-tokens.json and colors_and_type.css into Cocos usable layout/skin/screen JSON, then validating with rule guard, visual fidelity risk, runtime interaction smoke, Cocos Editor final gate, and regression evidence.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

快速編碼防災工作流。USE FOR：任何會修改 .md / .json / .ts / .js / .ps1 等文字檔的工作。目標是在每次編輯後立即檢查 touched files 是否出現 UTF-8 BOM、U+FFFD 或 mojibake，並在收工前再檢查一次，避免中文檔被整檔寫壞後才在 pre-commit 才發現。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Strict routing mode for prompts prefixed with `(best)`. USE FOR: any turn where the user explicitly wants the safest, smallest-context, highest-discipline execution path. This skill must route into context-budget-guard first, then continue into the task-specific workflow.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

HTML -> UCUF (Cocos Creator UI) conversion skill. Use for turning a complete HTML source package with ui-design-tokens.json and colors_and_type.css into Cocos usable layout/skin/screen JSON, then validating with Plan5 final fidelity gates: stale-rule audit, rule guard, visual fidelity risk, runtime interaction smoke, Cocos Editor final gate, and 95% regression matrix.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Measure, profile, and fix performance bottlenecks — Core Web Vitals, backend latency, bundle size, and database queries. Load when performance requirements exist, users report slowness, profiling reveals bottlenecks, or the user asks to optimize load time, LCP, INP, CLS, or response time. Not for premature optimization without evidence. Pairs with browser-testing-with-devtools and ci-cd-and-automation for regression guards.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Capture actionable learnings that emerge during conversation — when the agent or user discovers that a skill, a set of skills, or a process needs to be updated based on what's happening in the current chat. Sub-skill of the learn-from orchestrator. Load when the user says "we should update the skill for this", "this should be a skill rule", "add this as a gotcha", "the skill should know about this", "update the process for this", "remember this for next time", "this is important for the skill". Also triggers when the agent notices a skill's guidance was wrong or incomplete, a process step failed or was unnecessary, a new pattern emerged, a guardrail was missing, a workaround became a pattern, or a debugging session reveals a gap.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Author the project's non-negotiable engineering rules — the constitution that every feature spec, plan, and implementation must satisfy. Load when the user asks to write a constitution, define project rules, set engineering invariants, write project standards, define non-negotiables, capture agent guardrails as policy, or when spec-driven-development orchestrator routes here. Also triggers on "project constitution", "engineering invariants", "non-negotiable rules", "project policy", "set our standards", "/constitution". Output: docs/constitution.md. The third strategic artifact alongside AGENTS.md (agent behavior) and product-soul (strategy).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Run a structured retrospective after development-phase runs of your product's agents — interview the owner in plain language about what went well and poorly, draft ranked improvement hypotheses, then design and run small n=1/n=2 experiments with pre-declared success criteria, guardrails, stop conditions, and a cost/ROI kill-switch. Load when the user says how did that run go, retro this run, the agent output was bad, what should we improve, draft hypotheses, run a small experiment, or after repeated dev runs of an agentic system produce uneven quality. Priority: output quality over performance over cost, each with diminishing-returns stops. NOT a product A/B test (experimentation), NOT coding-agent harness repair (harness-evolution), NOT production-scale learning (runtime-learning-loop).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Write a rigorous, decision-grade experiment spec — falsifiable hypothesis, primary metric, guardrails, randomisation unit, exposure definition, method (A/B, holdout, switchback, quasi-experiment, MAB), MDE/duration plan, peek policy, validity threats, and pre-committed decision rule. Platform-agnostic. Load when the user has a candidate experiment and needs to spec it before launch, or says "spec this experiment", "write the test plan", "design this A/B test", "what's the hypothesis", "how big a sample do we need", "how long should we run this", "define the metrics for this test", or when the experimentation orchestrator routes here.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.