'budget' 검색 결과

Ensure architecture/design docs state traffic assumptions, performance budgets, resource limits, and cost risks for critical paths.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Shared types, SKILL.md renderer, and token budgeting for skillit plugins

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Diagnoses and prevents mobile performance regressions on every stack — Flutter, native Android, native iOS, React Native and Kotlin Multiplatform. Covers startup time, rendering and jank, memory, battery and background work, app size, the profiler and benchmark to use on each platform, and regression detection in CI. Use when an app is slow, janky, heavy or draining the battery, when setting performance budgets, or when a release must not regress.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Define and implement Service Level Indicators (SLIs) and Service Level Objectives (SLOs) with error budgets and alerting. Use when establishing reliability targets, implementing SRE practices, or measuring service performance.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Reduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when working with Apptio — apptio and Cloudability IT financial management and cloud cost optimization. Covers IT cost allocation, cloud cost analysis, benchmarking, budget forecasting, showback/chargeback reports, and technology business management. Use when managing IT financial planning, benchmarking cloud spend, or creating chargeback models.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when working with Azure Cost Management — azure Cost Management cost analysis, budget tracking, Advisor cost recommendations, export management, and spending trend analysis via Azure CLI.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Understand the constraints a design was built under and evaluate quality within that context. Use when reviewing work that had limited time, budget, or team size, or when assessing whether constraints were handled well.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Generates the monthly revenue-accountable marketing report that B2B SaaS marketing leaders deliver to CEOs, CFOs, executive teams, and boards. Use when preparing the monthly CEO report, drafting the marketing section of a board deck, defending budget decisions, diagnosing pipeline gaps, or transitioning marketing from MQL/SQO reporting to revenue, CAC payback, and forward pipeline coverage. Designed for B2B SaaS demand generation leaders who own pipeline targets across segments, geos, and motions, and need to explain marketing's revenue contribution in executive language.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Builds multi-touch pipeline attribution models and generates stakeholder-ready narratives from campaign performance data. Use when analyzing channel contribution to pipeline, preparing monthly/quarterly revenue reports for leadership, diagnosing pipeline misses, modeling budget reallocation scenarios, or translating raw attribution data into board-deck language. Designed for B2B SaaS demand gen teams that report on pipeline and revenue, not leads or MQLs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Turn one reference image into a cleaned, scaled 3D asset: your own image-to-3D ComfyUI workflow makes the mesh, Blender decimates it to a poly budget, fixes scale, origin and material, and exports a .glb. Use for "image to 3D", "make a 3D model from this picture", "photo to glb".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Implement, review, or improve widgets, Live Activities, and controls using WidgetKit and ActivityKit. Use when building home screen, Lock Screen, or StandBy widgets with timeline providers; when creating interactive widgets with Button/Toggle and AppIntent actions; when adding Live Activities with Dynamic Island layouts (compact, minimal, expanded); when building Control Center widgets with ControlWidgetButton/ControlWidgetToggle; when configuring widget families, refresh budgets, deep links, push-based reloads, or Liquid Glass rendering; or when setting up widget extensions, App Groups, and entitlements.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT", "TTR", "Search Match", "exact match", "broad match", "CPP in ads", "ASA bidding", or "Search Ads budget". For Meta/Google UAC/TikTok paid UA, see ua-campaign.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

This skill should be used when the user asks how to "use VibeTags", "add VibeTags annotations", "set up AI guardrails", "protect code from AI", "configure AI platforms", asks about @AILocked, @AIContext, @AIDraft, @AIAudit, @AIIgnore, @AIPrivacy, @AICore, @AIPerformance, @AIContract, @AITestDriven, @AIThreadSafe, @AIImmutable, @AIDeprecated, @AIObservability, @AIRegulation, @AIArchitecture, @AILegacyBridge, @AIStrictClasspath, @AIInternationalized, @AIPublicAPI, @AISchemaSafe, @AIStrictExceptions, @AIStrictTypes, @AIParallelTests, @AIIdempotent, @AIFeatureFlag, @AISecure, @AICallersOnly, @AISandboxOnly, @AIMemoryBudget, @AIPure, @AIDomainModel, @AIExtensible, @AIInputSanitized, @AISecureLogging, @AIExplain, @AIPrototype, @AISunset, @AITemporary annotations, or wants to control how AI tools interact with Java code.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Token budgeting discipline for all agents. Treats tokens as a resource from session start — not just when the buffer hits 60%. Covers prompt compression, context hygiene, handoff packing, and HOT memory pruning.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build, analyze, repair, and audit finance three-statement models and operating forecasts. Use when the user invokes $kelly-finance, asks for 财务三表, 三表模型, income statement, balance sheet, cash flow statement, forecast model, budget model, financial projections, FP&A model, SaaS/unit economics forecast, fundraising model, board finance pack, investor model, model checks, balance-sheet balancing, cash runway, working capital, capex/depreciation schedules, debt schedules, scenario/sensitivity cases, or Excel/Sheets-ready finance outputs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Guides agents through creating and safely sizing a Replay Vision scanner: choosing the scanner type (monitor/classifier/scorer/summarizer), shaping the RecordingsQuery that selects sessions, and — crucially — estimating observation volume and checking the org's monthly quota before creating, so a broad scanner doesn't exhaust the budget on its first scheduled sweep. TRIGGER when: user asks to create, set up, or configure a Replay Vision scanner, OR when you are about to call vision-scanners-create, OR when widening an existing scanner's query or sampling_rate via vision-scanners-update. DO NOT TRIGGER when: only reading scanners or observations, deleting a scanner, or running an existing scanner against a single session on demand (vision-scanners-scan-session).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Review Stellar Community Fund (SCF) Build Award applications. Use when evaluating SCF submissions, covering project fit assessment, technical architecture evaluation, team readiness, traction validation, budget analysis, and funding recommendations.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Simulate the SCF team's manual prescreen on a Build Award submission — a completeness and eligibility check applied to every full submission before panel review. Checks completeness, Stellar integration, eligibility, budget issues, and common disqualifiers. Use when reviewing a draft Build Award submission for readiness before it goes to the SCF round.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Draft Stellar Community Fund Build Award applications interactively. Use when helping teams write their SCF submission — walks through project description, Stellar integration rationale, technical architecture, team section, deliverables, budget, and traction evidence. Produces a complete draft aligned with what funded projects look like.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Autonomous themed tech-debt cleanup. Reads docs/architecture/debt-ledger.yml, rotates to the least-recently-served debt theme, works it for a time budget (default 2h) or until drained, opens one PR, and asks judgment questions inline at the end. Use for daily debt burndown without Peter pointing at a target: grandfathered analyzer rules, architecture-test baselines, obsolete-field reads, cross-section stitching.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Daily per-section review cycle driving a section toward the smallest, clearest form that still does everything it does today. Selects its section live each run (scripted), inventories every file, derives the target shape before any scan, works parallel reading threads into one ranked list and strikes it on a 2-3h budget. One PR per run; each run's report and Needs-Peter queue live in its own docs/health/runs/ file; 'resume' applies Peter's answers later. Use for the morning section-improvement run, 'doctor <section>', or 'run section doctor'.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Writes an autonomous agent for the CARLA Leaderboard — an AutonomousAgent subclass with setup/sensors/run_step/destroy, a sensor suite inside the track's budget, and the right constructor signature for the leaderboard version (1.0 and 2.x differ). Generates a working skeleton, validates the sensor configuration against the real per-track limits offline, and covers the ROS1/ROS2 agent base classes. Use when the user asks to "write a leaderboard agent", "make my agent work with the leaderboard", "add sensors to my agent", "port my agent to 2.1", or hits SensorConfigurationInvalid.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.