1.5만건 · 관련도순
Build or improve a Coval dashboard with metric visualizations backed by real data. Creates new dashboards from scratch or rebuilds existing ones by analyzing usage patterns, metric frequency, and data density. Use when user says "create a dashboard", "build a dashboard", "improve my dashboard", "add widgets", "visualize my metrics", "make a performance dashboard", or "dashboard for my runs".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
End-to-end Coval adversarial / red-team testing workflow. Builds one adversarial test set (12 core attack vectors plus legitimate controls, each with an expected-behavior checklist), creates a persistent "Adversarial User" persona and a Composite Evaluation metric that scores each scenario against its own expected behaviors, launches a multi-iteration run against the agent (voice or chat), polls for completion, builds a per-scenario pass/fail scorecard, and creates a saved report grouped by Test Case. Use when a user wants to follow the Adversarial & Red-Team Testing cookbook (https://docs.coval.dev/guides/adversarial-red-team-testing) without doing each step by hand. Triggers: "adversarial test set", "red team my agent", "jailbreak / prompt-injection testing", "test my agent against bad actors".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Configure an AI agent to send OpenTelemetry traces to Coval. Use when a user wants to add Coval tracing, instrument an agent for simulations or conversation monitoring, make traces show up in Coval, handle SIP/PSTN/WebSocket trace correlation, or replace the one-command wizard with a security-reviewable manual setup.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Analyze development-set disagreements between human annotations and one Coval text LLM judge, then propose a focused prompt revision. Use coval-calibrate-metric for independent trust measurements.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Analyze existing XML sitemaps or generate new ones with industry templates. Validates format, URLs, and structure. Use when user says "sitemap", "generate sitemap", "sitemap issues", or "XML sitemap".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Recipe for creating or changing a floating window. Use when adding a window, deleting, killing or retiring a window or overlay ('kill this panel', 'remove the X window', consolidating X into Y and deleting X), editing a window component, declaring restore or ephemeral behavior, wiring a ?panels= link or the Tools grid, or a window fails to restore after reload. NOT for drag/resize/tray internals (use window-panels) or for opening an overlay (use overlay-system).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Orchestrator that runs one UI brief through all four ui-* posture skills in parallel, then picks and merges a winner. Use when a screen matters enough to explore several directions, or the user says 'build it a few ways', 'design options', 'bake-off', 'show me variations', or 'compare approaches'.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
The TTS/STT/audio-playback system behind the one `speak()` entry point. Use when working on read-aloud, the Listen panel, voice/speed settings, transcription, mic capture, SpeakerButton, iOS playing silence, audio API routes, or files in features/audio/, features/tts/, hooks/tts/, app/api/audio/.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Dense UI posture — maximum information density with clear hierarchy. Use when building or reworking admin dashboards, data tables and grids, ops or monitoring views, settings-heavy panels, debug inspectors, state or log viewers, and multi-pane tool UIs someone drives all day.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
THE full UI surface checklist (S1–S18) run on one assigned surface. Use for a named surface check, `/surface-check <surface>`, or a claimed `surface-certification` Work Loop item. NOT for fleet selection or claims (use surface-certification-loop).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Pipeline that turns a big system idea into briefs for an agent fleet. Use when Arman says 'let's plan out X', 'build or overhaul the X system', 'create the vision and plan for X', 'do the full discovery process', 'get this ready for a fleet', or 'do what we did for education', or when carrying forward a VISION, COMPETITIVE_INSIGHTS, roadmap, or briefs doc. NOT for one feature in a live system (use build-sub-feature).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Pre-ship safety proof for replacing a live implementation with a canonical one. Use when repointing nodes, tools, or services to a new contract, superseding a schema, retiring a legacy or parallel system, or any 'new way replaces the old way' change. NOT for greenfield or unconsumed additive work.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Coordinator for the fleet that repairs and independently certifies registered UI surfaces through Work Loop claims. Use for pilot batches, recurring certification, repair rounds, or retroactive rechecks after surface-check rules change. NOT for one assigned surface (use surface-check).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Audit-and-fix method for one user setting area across every repo. Use when a setting seems ignored, duplicated or confusing, on 'audit the X settings' or 'why doesn't my X setting apply', or as a lane of the settings sweep. NOT for adding a new setting (use build-sub-feature).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Recipe for building one focused UI section out for every consumer. Use when asked to 'make this section canonical', 'productize this widget', give it 'the full treatment', or set it up 'like the SEO metadata system', or when building a new analyzer, preview, or calculator section.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
One-route pattern: public marketing landing plus signed-in workspace. Use when creating or fixing a landing page or a feature's front door, guests see an error, 'make /X work signed out', signed-in users land on a pitch, or ModuleLanding / AuthedWorkspaceCTA. NOT for (public) share viewers or free tools.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
react-resizable-panels v4 rules for this SSR codebase. Use when importing react-resizable-panels (PanelGroup and PanelResizeHandle are v3 names), editing components/ui/resizable* or features/code/layout/, building a split-pane, sidebar, or drag-handle layout, or persisting or toggling panel sizes.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Rules for SKILL.md files that trigger, fit, and are proven. Use when creating a SKILL.md, rewriting its description, splitting an oversized SKILL.md, or editing one because an agent ignored, misread, or never fired it.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Lifecycle for AI Matrx agent-aware UI surfaces. Use when creating a surface in features/surfaces/manifests/, or completing or repairing one that is partial, stubbed, unregistered, missing runtime context or context menus, or not agent-wired. NOT for certifying a surface (use surface-check).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Delegating work down to subagents: briefs, report statuses, independent review. Use when writing an implementer or verifier brief, dispatching a subagent to build, fix, or verify work you own, or a subagent reports DONE, blocked, or concerns. NOT for campaign-scale doctrine (use campaign-pattern).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Runbook for creating or majorly growing an @ai-matrx TypeScript npm package. Use when invoked as /new-package <name or capability>, or for a new @ai-matrx/* package, extracting code into one, or a major growth wave. NOT for a routine fix inside an existing package (THE SAME-SESSION LAW).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Redux Toolkit selector rules against re-renders, recalculation warnings, and render loops. Use when writing useSelector/useAppSelector or createSelector, deriving state in a connected component, or seeing 'Selector returned a different result when called with the same parameters'.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.