Results for “reference”

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.

The English summary is being prepared. Showing the original description.

Build a reference system that returns the right reference in under 60 seconds. Use when setting up a design reference library, reorganizing existing collections, or helping teams build shared reference systems.

The English summary is being prepared. Showing the original description.

Select, document, download, and checksum-verify the most appropriate NCBI reference genome on an HPC cluster. Use whenever an analysis needs a reference genome, genome FASTA, genome annotation, assembly accession, or genome index and no exact approved assembly is already available; when a user asks to fetch a species genome from NCBI; or when a pipeline must resolve and cache a reproducible reference assembly on a remote cluster.

The English summary is being prepared. Showing the original description.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

The English summary is being prepared. Showing the original description.

Analyze a set of design samples (HTML mockups + website URLs) and produce a structured style guide that anchors the rest of the stardust redesign pipeline. Use when the user supplies reference designs ("design samples", "mockups", "inspiration sites", "style references") and wants to extract a consistent visual language — type system, color palette, spacing, motion, and reusable component patterns — before redesigning a target site. Triggers on phrases like "distill these samples", "extract a style guide from these examples", "use these as design references", or "analyze these mockups". Outputs a `trait-matrix.json` (structured per-sample + cross-sample design tokens) and a `SAMPLES.md` narrative brief that `stardust:direct` reads under Mode B (anchor-reference precedence) when picking a redesign direction.

The English summary is being prepared. Showing the original description.

Select, document, download, and checksum-verify the most appropriate NCBI reference genome on an HPC cluster. Use whenever an analysis needs a reference genome, genome FASTA, genome annotation, assembly accession, or genome index and no exact approved assembly is already available; when a user asks to fetch a species genome from NCBI; or when a pipeline must resolve and cache a reproducible reference assembly on a remote cluster.

The English summary is being prepared. Showing the original description.

Creates exhaustive technical references and API documentation. Generates comprehensive parameter listings, configuration guides, and searchable reference materials. Use PROACTIVELY for API docs, configuration references, or complete technical specifications.

The English summary is being prepared. Showing the original description.

Review MCP configuration without running its servers. Identify npm, Python, and Docker references that may fetch different code later, classify their version settings, and recommend pinning versions or image contents that the team has reviewed.

• Reviewing MCP configuration before approval
• Checking latest tags and version ranges
• Adding a deterministic configuration check to CI

Route broad requests about project documentation to a suitable specialist skill. When requested, run a read-only audit of document roles, local links, architecture decision indexes, and evidence references, reporting failures and items needing review.

• Choose a workflow for organizing project documentation
• Identify existing documentation sources
• Audit local links and architecture decision indexes

Create and edit videos using a measured reference style for color and cutting rhythm. Combine generated clips, existing footage, overlays, and 3D props, then check visual measurements and deliver both a video and an editable timeline.

• Creating a video in a captured reference style
• Supplementing existing footage with generated clips
• Adding overlays and rendered 3D props

Turn visual preferences and local references into reusable style packs, validated settings for look and rhythm. Plan cuts for local footage, export editable timelines, and prepare image, video, or 3D asset plans without calling generation providers.

• Interview for visual direction and create a reusable style pack
• Validate style packs and audit their sources
• Plan local footage cuts using measured reference rhythm

Train language models on pairs of preferred and rejected answers without a separate reference model. The skill guides training setup, model-specific configurations, parameter tuning, and troubleshooting for unstable training or memory limits.

• Train a base model using preferred and rejected answer pairs
• Further tune an instruction-following model
• Adjust training settings for math and coding tasks

Create or improve skills for Claude Code plugins by defining clear activation conditions, writing focused instructions, and organizing supporting files. The guidance covers reusable scripts, reference documents, examples, and testing whether a skill activates for the intended requests.

• Creating a new skill inside a plugin
• Clarifying when an existing skill should activate
• Splitting long instructions into reference files

Create photos, illustrations, product mockups, and other bitmap images, or edit existing images by replacing backgrounds, removing objects, and making transparent cutouts. Use reference images to guide style, composition, or visual variants.

• Create a website hero image
• Explore product or packaging mockups
• Remove objects or replace an image background

Store facts, daily events, and user preferences in files that persist across sessions. Organize knowledge with PARA, a method separating projects, ongoing responsibilities, references, and archives, and retrieve saved information through qmd search.

• Keeping facts available across sessions
• Recording daily events and conversations
• Organizing knowledge about people and projects

Generate and edit project images with OpenAI's Image API, including UI mockups, icons, illustrations, social cards, and visual references. This catalog entry helps agents discover the skill; the complete workflow requires installing the upstream bundle.

• Creating UI mockup images
• Generating icons and illustrations
• Preparing social card images

Generate website design images before coding, then analyze their text, spacing, colors, and layout to guide implementation. Separate references for each section help translate the design into a responsive frontend with a readable first screen on smaller laptops.

• Design a landing page from generated visual references
• Build a clear hero section for smaller laptop screens
• Create a portfolio with a consistent visual direction

Generate videos from structured prompts describing subjects, visual style, camera work, and other scene details. The workflow creates English JSON prompts and runs a Python script, with optional reference images to guide the result.

• Turn a scene idea into a video
• Generate a video guided by a reference image
• Specify visual style and camera movement

Create character, scene, and product images from structured descriptions of style, composition, lighting, and color. Guide generation with reference images and aspect ratio settings, using a Python script connected to a supported image generation service.

• Creating characters with specified clothing, era, and appearance
• Visualizing scenes with a chosen mood, weather, and lighting
• Producing product images with specified materials and viewing angles

Check a Claude Code plugin before publishing. Inspect file placement, required configuration fields, metadata at the start of skill and agent files, and MCP tool references, then report failures with practical suggestions for fixing them.

• Check a newly created plugin before publishing
• Review structure after adding skills or agents
• Find missing fields and misplaced files

Review rendered HTML for duplicate IDs used by ARIA attributes, which connect elements to labels and descriptions for assistive technology. Identify ambiguous references, correct IDs and their links, and explain how to verify the changes.

• Investigating incorrect labels read by screen readers
• Checking repeated components for duplicate IDs
• Reviewing ARIA references in a design system

Generate short videos with audio from prompts and reference images, then refine them through conversational edits. The skill covers targeted object, lighting, and text changes, plus timed actions, using Gemini Omni Flash through documented video tools.

• Creating short videos with sound from written prompts
• Assigning reference images to characters, products, or styles
• Refining objects, lighting, and text through conversation

Generate 4–30 second videos with synchronized audio using ByteDance Seedance 2.5. Organize image, video, and audio references, write shot-by-shot prompts, and define continuity rules to keep characters and locations consistent across cuts.

• Generating short videos with synchronized audio
• Planning multi-shot scenes with consistent characters and locations
• Building video prompts from image, video, and audio references

Generate short videos with MiniMax H3 from text, starting images, or reference media. The skill guides camera and motion prompts, first-to-last-frame animation, and route selection across hosted services and local ComfyUI workflows.

• Generate a short clip from text
• Animate between a first and last frame
• Create video using image, video, and audio references