Iced GUI framework Elm architecture patterns for Rust. Feature-based code organization, message flow, Task::done dispatch, core/UI separation, snapshots, deferred side effects, subscriptions, component independence. Persistence and app state: database initialization only in main.rs; transient store (no singleton, no factory); Directory generic over store; store only in constructor; call store.get_last_session from workspace; on folder load failure keep previous state. Solved patterns: keyboard→app→workspace→feature message chain, selectable rows with one parent background (hover/delete without breaking layout), consolidated styles in theme.rs, delete+hover list UX, selection styling (widget outline + row background, same accent family, vertical centering in cells). Use when building iced UI features, adding messages, creating views, wiring components, organizing iced code, implementing persistence/session, row layout, or selection styling.

Cerate or Update a GitHub Issue for each Module in the task document.

>

>-

Rapid context loading for new agents. Reads key documentation to build a mental model.

Master reference for building premium, production-quality UI on Stratify. Enforces surgical mode, auth protection, icon/badge rules, design system, soft glass cards, motion, and trading patterns. Use for all Stratify dashboard, components, and UI work.

antv-l7

Use this skill whenever PDF files are created, read, merged, split, transformed, OCR-processed, or data-extracted.

Draw shapes, arrows, and diagrams on a TLDraw canvas via the agent-canvas CLI. Use when an agent needs to visually communicate ideas, create diagrams, flowcharts, or annotate a whiteboard. Triggers on tasks involving drawing, diagramming, visual explanations, or canvas manipulation.

>

DAST/ASM workflow for external asset discovery, probing, and scanning with SARIF output. Use for runtime/endpoint-based assessments and asset management scanning.

Skill for using Fabro, the open source AI coding workflow orchestrator that lets you define agent pipelines as Graphviz DOT graphs with human gates, multi-model routing, and cloud sandboxes.

Diagnose GitHub Actions CI failures and suggest fixes. Use when the user reports CI failed, GitHub job failed, Actions failed, build failed on remote, upload artifact failed, or pastes a failure from the Actions tab.

This skill should be used when the user asks to 'write a paper', 'start a writing project', 'draft an article', 'write about', 'brainstorm writing topics', 'gather sources for a paper', 'what should I write about', or needs the writing workflow entry point for any writing task.

Break down unknowable quantities into estimable components to reach order-of-magnitude accuracy when making quick decisions without precise data

Using Punkt design system components (React and Elements/Web Components). Covers component APIs, props, events, slots, and usage patterns for all Punkt UI components. Use when building UIs with Punkt components.

Seismological data analysis with ObsPy — FDSN waveform download, response removal, phase picking, moment tensor inversion, and seismicity mapping.

Run a dependency scan using the Socket CLI. Prompts unauthenticated users

Workflow Design - designs graph-based agent workflows with branching, chaining, suspend/resume, streaming, and observability

End-to-end 8-dimension verification — requirements through delivery, all aligned and correct

You are the **Data Engineer** on a 10-agent AI dev team.

Mandatory bootstrap mode for GRACE-CODER. Loads the shared protocols required before any contract-aware implementation or patching.

Read a research paper and extract structured notes. Use when analyzing papers for a survey.

> Fetch route data before rendering using SvelteKit's load functions — server-only, universal, streaming, and invalidation patterns

> Deploy React Native apps with EAS Build, EAS Submit, OTA updates, and automated CI/CD pipelines

Manipulate form field state using g_form APIs — no server calls required. Covers field value get/set, mandatory/read-only/hidden control, inline validation and error messages, section and tab visibility, and form state checks. Use for dynamic/runtime field manipulation triggered by user actions (onChange, onLoad, onSubmit). For static field behavior based on conditions, prefer UI Policies instead — they load faster and don't require scripting. For scripts requiring GlideAjax server communication, use the servicenow-client-scripts skill. Trigger this skill whenever the user needs to control field visibility, mandatory state, read-only state, field values, or form messages in a ServiceNow client script without making server calls.

Web search, scraping, and crawling via the Firecrawl API. Use when you need to search the web, scrape websites (including JS-heavy pages), or extract structured data.

> Define and manage design tokens for colors, spacing, typography, and effects in Tailwind CSS

> Master lazy loading strategies — Intersection Observer-based visibility triggers, route-based lazy loading, component-level deferral, progressive hydration, and virtual scrolling to minimize initial

> Model mutually exclusive states with discriminated unions and exhaustive narrowing

> LONG-RUNNING OPERATIONS REQUIRE AN EXPLICIT ASYNC CONTRACT — A 202 ACCEPTED RESPONSE WITH AN OPERATION RESOURCE THAT CLIENTS CAN POLL OR SUBSCRIBE TO IS THE DIFFERENCE BETWEEN A SYNCHRONOUS BOTTLENE

> Measure and prevent unexpected layout shifts — elements visually moving after being rendered — by reserving space for dynamic content, handling font loading, setting explicit dimensions, and underst

> Structure applications with file-based routing, named layouts, and per-page configuration via definePageMeta

>

>

Mandatory bootstrap mode for GRACE-COORDINATOR. Loads governance, traceability, and living-document protocol skills before routing work.

Comprehensive guide for Crawl4AI - open-source LLM-friendly web crawler and scraper with 62k+ GitHub stars. Covers CLI commands (crwl), Python API, Docker API, deep crawling strategies (BFS, DFS, best-first), content extraction (CSS selectors, LLM-based extraction), markdown/json output, anti-bot bypass, and advanced features for RAG pipelines, data extraction, and batch URL processing.

Expert in building end-to-end speech transcription pipelines using Whisper-style models and cloud ASR services — from raw audio ingestion through preprocessing, transcript cleanup, subtitle generation, speaker diarization, and structured downstream integration into apps, APIs, and CMS platforms.

Lottie animations. Pre-made icon animations, loading states, micro-interactions. LottieFiles library.

> UI state inventory — empty, loading, partial, error, success, offline, disabled, read-only, and how each state communicates system status

Use this skill when the user asks to build the datadog-agent locally and load it onto the Kind cluster in the Lima VM. Covers building the arm64 Docker image with dda inv, saving and copying the tar to the Lima VM, loading it into Kind, and restarting the agent pods.

Build NowAssist Skill configurations using the Fluent SDK NowAssistSkillConfig API. Covers the two-argument skill definition pattern, input/output typing, tool graph construction (Script, InlineScript, FlowAction, Subflow, WebSearch, Decision), LLM provider and prompt configuration with versioning, security controls (MANDATORY), and deployment settings. Use when creating AI-powered skills that appear in the Now Assist Panel, UI Actions, or as reusable Flow Actions. Trigger this skill whenever the user mentions NowAssist, NowAssistSkillConfig, Now Assist skills, LLM-powered skills, generative AI in ServiceNow, prompt configuration, or building AI capabilities with the Fluent SDK.

> Configure and run Apollo Server with plugins, context, data sources, and framework integrations

| Field | Value |

fact check

Builds and installs new agents end-to-end: design, code, package, gate, install.

> The low-level SDK for direct interaction with Nookplot smart contracts and the Gateway API.

Plan and execute reproducible computer science paper reproductions. Use when Codex needs to extract implementation-critical details from a paper, inventory required artifacts and environments, build a runnable draft reproduction, track missing details and deviations, compare reproduced results with the paper, or package the work into reusable experiment notes.

Query AND UPLOAD to Google NotebookLM. Create new notebooks, upload local files (PDF/MD/TXT), add URLs, paste text content. Browser automation with persistent auth.

- **名称**：Addax