89건 · 관련도순
Benchmark multi-agent coordination systems with experiment design, power analysis, human rating protocols, bootstrap confidence intervals, and reproducible reporting. Use for salvage latency, recovery fidelity, coordination overhead, and protocol comparison studies. NOT for ML model benchmarking, web-product A/B testing, survey design, or general-purpose data science.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Low-ceremony workflow for trivial, low-risk changes: typos, comments, CSS/styling tweaks, string changes, single-line fixes with no logic impact. Use to avoid the overhead of the full feature workflow when the change cannot break anything. If during the fix the change turns out to touch logic, security, config, or schema, stop and escalate to the feature-workflow skill.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Read-only audit of the project's agent-tree structural overhead vs the context window. NOT for cost tracking (budget skill); NOT for read/compact decisions (mk:context-engineering).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Runtime router for context decisions: read-more/stop/ask/assume/delegate, minimal read-set, compaction timing. Model: Write/Select/Compress/Isolate. NOT for agent-tree overhead audit (context-audit).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Read-only audit of .codex/ structural overhead: 'remove X save Y tokens' vs the context window. NOT for cost tracking (budget skill); NOT for runtime read/compact decisions (mk:context-engineering).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Runtime router for context decisions: read-more/stop/ask/assume/delegate, minimal read-set, compaction timing. Model: Write/Select/Compress/Isolate. NOT for .codex/ overhead audit (mk:context-audit).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Runtime router for context decisions during a task — decide read-more / stop / ask / assume / delegate, pick a minimal read-set, and time compaction. Front-page mental model is Write / Select / Compress / Isolate; a lazy pattern index routes to 25 context-engineering patterns, one reference per decision. Use when context is near budget, a long session is degrading, you must choose what to read for a task, or you are deciding /compact vs /clear vs a sub-agent. NOT for structural .claude/ overhead audits (see mk:context-audit); NOT for owning persistence (see mk:memory); NOT for USD cost (see mk:budget).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Audit one or all supported agent harnesses (claude, codex, opencode, pi, omp, antigravity, cursor, grok) for config efficiency, hook overhead, permission friction, plugin and MCP cost, skill metadata portability, dead config, and measured session friction. Use when invoked as `$optimize-harness [harness ...] [focus]`, or when the user asks to optimize or compare agent harness configuration.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Marketing operations manager handling budget planning, financial reporting, meeting preparation and follow-up, vendor management, and administrative workflows for marketing and communications departments. Designed for SME leaders who need to minimize time spent on operational overhead.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Expert-level guidance for Flutter production applications: architecture decisions (Clean/Layered/Hexagonal/Feature-First), advanced state management (BLoC/Riverpod/GetX), performance optimization (eliminating jank, memory profiling, reducing rebuild overhead), code review with design pattern enforcement, scalability assessments, native platform integration (MethodChannel/EventChannel/FFI), complex UI challenges (custom render objects, slivers), testing strategies (unit/widget/integration/golden), CI/CD pipeline architecture, build optimization, and accessibility compliance. Triggers: 'architecture decision', 'design pattern', 'performance issue', 'code review', 'production problem', 'scaling concerns', 'best practices', 'technical debt', 'refactoring strategy'. Essential for complex enterprise apps, critical production debugging, architectural refactors, or when choosing between competing technical approaches.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Hive CE (Community Edition v2.19.x) NoSQL object database for Flutter providing blazing-fast key-value and object storage with TypeAdapters. Use this skill when implementing offline-first architecture, high-performance local data caching, NoSQL document-style object stores, custom TypeAdapter serialization for complex objects, lazy loading boxes for memory efficiency, encrypted boxes (HiveAES encryption), database compaction for size optimization, storing large datasets without SQL schema overhead, implementing local-first sync patterns, or migrating from SQLite to NoSQL. Supports primitive types, custom objects, lists, and maps. Ideal for apps requiring ultra-fast read/write operations (microsecond latency), object persistence without ORM complexity, or local-first data architecture.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
SharedPreferences (v2.5.5) for Flutter providing simple persistent key-value storage for non-sensitive user settings and app preferences. Use this skill when storing user preferences (theme mode, language selection, font size), app settings and configuration, feature flags or A/B test assignments, simple cache data, onboarding completion status, last selected values (filters, sort options), user consent flags, or any non-sensitive data that survives app restarts. Supports String, int, double, bool, and StringList types. NOT suitable for storing tokens, passwords, API keys, or any sensitive/encrypted data (use flutter_secure_storage instead). Ideal for quick persistent storage without database overhead.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Design finalization: generates production-quality Pretext-native HTML/CSS. Works with approved mockups from /design-shotgun, CEO plans from /plan-ceo-review, design review context from /plan-design-review, or from scratch with a user description. Text actually reflows, heights are computed, layouts are dynamic. 30KB overhead, zero deps. Smart API routing: picks the right Pretext patterns for each design type. Use when: "finalize this design", "turn this into HTML", "build me a page", "implement this design", or after any planning skill. Proactively suggest when user has approved a design or has a plan ready. (gstack) Voice triggers (speech-to-text aliases): "build the design", "code the mockup", "make it real".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Append structured execution traces across operational, cognitive, and contextual surfaces with minimal overhead. Load when inspecting agent runs, logging tool calls and observations, enabling post-run debugging, or pairing with structured-planning step IDs. Also triggers on "trace this run", "log execution", "agent observability", "run log", or when fault-localize needs evidence. Default-on during multi-step plans. Traces live at .agent-loom/traces/ — git-ignored by default.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when a carrier asks how to calculate cost-per-mile (CPM) at the fleet, truck, lane, or driver level — separating fixed vs variable costs, allocating overhead, accounting for empty miles, and using CPM to negotiate rates, build pricing tiers, or evaluate lane profitability.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Runs an iterative, conversational product-discovery process with a founder/stakeholder: structured interview, live low-fi wireframing, a linked feature/page node-graph built up as you go, a founder-confirmed lock-in checkpoint, then a generated PRD, a Mermaid-rendered sitemap, and a mockup with a full design system (palette, typography, dark mode). Use when building or operating an AI product-discovery chatbot, or when running founder/stakeholder discovery by hand and you need the structure (interview script, node-graph schema, PRD template, design-system handoff order). NOT for implementing the spec'd product once locked — hand off to feature-specific skills (ideal-web-app-builder, tailwind-v4-expert, color-theory-palette-harmony-expert, typography-expert, dark-mode-design-expert) for that. NOT for one-shot PRD generation without an interview loop — if the founder already has a written spec, this process is unnecessary overhead.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Execute a trivial task inline — no subagents, no planning overhead
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.