'ttl' 검색 결과

One-question-at-a-time design interrogation. Use when: 'grill me', 'interrogate this', 'one question at a time', 'brainstorm', 'let's brainstorm', 'let's discuss', 'lets discuss', 'discuss', 'walk me through', or design review start. Produces ADRs and glossary as decisions settle. Use for unsettled designs; for settled designs go straight to architecture-mode. When the design is unsettled and also has high ambiguity, several technical approaches, or security/data risk, load architecture-mode alongside.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

공장의 설비, 인력, 자재, 납기를 고려해 생산 순서를 검토합니다. 작업 전환과 공정별 부하를 조정하고 설비 고장이나 자재 부족 시 계획 수정을 돕습니다.

• 제한된 설비에서 생산 순서 검토
• 설비 고장 후 계획 재수립
• 생산 묶음 크기와 전환 비용 비교

Find CSS and JavaScript that delay a page’s first visible content. Confirm the bottleneck with browser tools or performance data, then adjust loading behavior and inline essential styles to help the page start rendering sooner.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating a blank screen during page loading
• Reviewing CSS and JavaScript loading behavior
• Inlining styles needed for the initial display

Work through project decisions one question at a time, with a recommended answer and a short explanation. Record settled choices in project documentation, including scope, completion criteria, constraints, risks, and unresolved questions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clarify project goals through a decision interview
• Agree on deliverables and completion criteria
• Record settled decisions in project documentation

Optimize scientific Python workloads for NVIDIA GPUs by choosing suitable libraries and reducing bottlenecks. Compare outputs with the CPU version and measure complete processing time, including data transfers, to determine whether the GPU implementation provides a useful improvement.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Assess whether slow Python processing would benefit from a GPU
• Move NumPy or pandas workloads to suitable GPU libraries
• Validate GPU results against CPU outputs

Implement controlled retries and request throttling for external APIs. Covers retryable errors, provider-specified waiting times, increasing delays with random variation, retry limits, and checks that repeating a request will not cause unintended duplicate changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Handle 429 and temporary server errors
• Respect Retry-After waiting times
• Limit outgoing API request frequency

Design systems where multiple AI agents share work, generate tool schemas that define tool inputs for Anthropic and OpenAI, and analyze execution logs. Outputs include role assignments, communication diagrams, and recommendations for addressing cost, latency, and failures.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing agent roles for research automation
• Choosing how multiple agents coordinate work
• Generating and validating tool schemas

Track competitors’ products, pricing, and customer wins or losses, then turn findings into sales comparison sheets, market positioning updates, and feature gap summaries that inform product planning and leadership decisions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Mapping direct, indirect, and emerging competitors
• Preparing competitor comparison sheets for sales calls
• Analyzing why deals were won or lost

Turn company strategy into operational plans through process design, OKRs—objectives paired with measurable results—and regular reviews. Produce bottleneck analyses, efficiency scorecards, meeting schedules, and readiness reports for teams preparing to grow.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Connecting company goals to department and team OKRs
• Finding process bottlenecks and planning improvements
• Assessing operational readiness for team growth

Review game code for likely performance bottlenecks in processing, memory, rendering, and data loading. Compare available estimates with configured limits and produce ranked optimization recommendations, including expected impact, effort, risks, and areas needing runtime measurement.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding performance bottleneck candidates in one game system
• Reviewing performance across the whole game
• Comparing available estimates with configured performance limits

Maintain personal goals and beliefs with timestamped backups, or analyze project documents to connect problems, goals, strategies, and projects. Turn findings about progress, bottlenecks, and alignment into reports, presentation points, or interactive dashboards.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Update personal goals while preserving history
• Find project dependencies and bottlenecks
• Prepare key points for a presentation

Set up application monitoring with structured logs, performance metrics, and traces that follow requests across services. Build dashboards and alerts, run load tests, investigate CPU and memory bottlenecks, and estimate future infrastructure capacity.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set up application dashboards and alerts
• Investigate production issues using logs, metrics, and traces
• Run load tests before traffic increases

Record dated developments in litigation matters and update the corresponding matter log. Capture status, risk, deadlines, and settlement developments, with proposed history entries and field changes shown for review before saving.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recording hearings, orders, and new deadlines
• Updating risk assessments after new facts emerge
• Logging settlement offers and authority changes

Maintain data retention in ClawHub's Convex tables by classifying each table, defining expiration fields, and bounding cleanup jobs. Guide changes to temporary data and expired authentication records, with focused tests and runtime verification.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Classify retention policies for new tables
• Add expiration fields and indexed cleanup
• Update scheduled jobs with bounded deletion batches

Build a concise sales card for competing against one rival using public evidence. Organize talking points, questions, pricing, and claims to avoid, with sources, dates, and labels distinguishing facts, inferences, and assumptions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prepare for sales conversations against a recurring competitor
• Rebuild an outdated sales comparison card with sources
• Develop questions backed by documented competitor limitations

Create and manage prediction markets on Solana, where participants trade YES or NO outcome tokens. Support includes direct peer bets, social media metrics, custom result authorities, market settlement, and redemption of winning positions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a prediction market around social media metrics
• Build direct peer-to-peer betting markets
• Let an AI agent determine market outcomes

Assess login and verification code protections, identify response differences that reveal registered accounts, and distinguish visible blocks from silent throttling. The skill guides evidence gathering to verify weaknesses and assess their practical impact.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review login attempt limits
• Assess OTP and password reset protections
• Check whether responses reveal registered accounts

Guide cache implementation and code reviews by choosing expiration times, update rules, keys, and storage layers. Address stale data and bursts of requests when cached entries expire, with examples for Redis, HTTP headers, and TanStack Query.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing cache expiration and invalidation rules
• Reviewing cache keys for missing parameters
• Investigating stale data and request bursts

Use when the user asks to "build battle cards", "prep the sales team for launch", or "write the internal launch FAQ"; produces the internal enablement kit for a sales-led launch — battle cards vs each named alternative (where we win / where they win / trap questions, every fact traceable), a sales talk track derived from the PR-FAQ spine, an objection-handling table (objection → response → evidence), internal FAQ + CS macros, and an internal launch announcement with embargo discipline. Not for the external message house — use message-house-builder; not for competitor tracking itself — use competitor-tracker or competitor-analysis; not for outbound sequences — use cold-outbound-sequencer. 销售赋能/battle card/销售叙事/异议处理/内部FAQ

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Generate intense fight scene and action sequence video prompts for Seedance 2.0 on Higgsfield. Use whenever the user wants fight scenes, combat, martial arts, battles, action choreography, sword fights, hand-to-hand combat, chase scenes, superhero action, or any high-energy action video. Triggers on: fight, combat, battle, martial arts, action scene, choreography, duel, sword fight, kung fu, chase, brawl, punch, kick, weapon combat, superhero fight, or any action/fight request. Use even for "make an intense action video" or "epic battle.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert blueprint for Battle Royale games including shrinking zone/storm mechanics (phase-based, damage scaling), large-scale networking (relevancy, tick rate optimization), deployment systems (plane, freefall, parachute), loot spawning (weighted tables, rarity), and performance optimization (LOD, occlusion culling, object pooling). Use for multiplayer survival games or last-one-standing formats. Trigger keywords: battle_royale, zone_shrink, storm_damage, deployment_system, loot_spawn, networking_optimization, relevancy_system, snapshot_interpolation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert blueprint for Battle Royale games including shrinking zone/storm mechanics (phase-based, damage scaling), large-scale networking (relevancy, tick rate optimization), deployment systems (plane, freefall, parachute), loot spawning (weighted tables, rarity), and performance optimization (LOD, occlusion culling, object pooling). Use for multiplayer survival games or last-one-standing formats. Trigger keywords: battle_royale, zone_shrink, storm_damage, deployment_system, loot_spawn, networking_optimization, relevancy_system, snapshot_interpolation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build sales battlecards with feature comparisons, objection handling scripts, positioning statements, and win themes for competitive deal scenarios. Use when the user requests competitive battlecard creation or provides relevant inputs for this workflow.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

World-class caching strategies - cache invalidation, Redis patterns, CDN caching, and the battle scars from cache bugs that served stale data for hoursUse when "cache, caching, redis, memcached, cdn, ttl, invalidation, stale, cache aside, write through, cache stampede, thundering herd, cache warming, etag, cache-control, caching, redis, memcached, cdn, performance, http-cache, ttl, invalidation" mentioned.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.