Results for “references”

Requires OFOX_API_KEY — create one at https://app.ofox.ai, plus a publicly reachable reference video the user is authorized to use. Use when a user has a rough 3D white-model, clay, wireframe, blockout, previs, or animatic clip and wants a finished visual treatment that preserves its shot order, cut timing, camera framing, spatial layout, and motion directions. Distinguishes that structure-preserving job from a continuation beginning at the reference's final state. Do not use for two still endpoints (keyframe-animation), for appending and locally joining a new ending (video-extend-edit), or when still-image references must be combined with the video in one request — first/last-frame anchors conflict with video references in the shipped core, while mixed image/video references are untested.

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

Guides multi-step web tasks with the OpenClaw browser tool, including login checks, tab reuse, and page inspection before actions. It also covers recovery when element references expire or browser operations time out.

• Completing web tasks with several steps
• Checking login status before browser actions
• Reusing tabs and closing duplicates

Rebuild OpenClaw release changelogs from Git history, the recorded code changes. Group changes by user impact, preserve issue and pull request references and contributor credits, and verify the notes against the release history and published GitHub release text.

• Preparing changelog notes before a stable release
• Extracting changes since the previous beta baseline
• Checking contributor credits and pull request references

Create or revise agent skills by defining when they run, what they produce, and how their files are organized. Validate SKILL.md settings, resource links, and changed helper scripts before completing the work.

• Creating a skill for a recurring workflow
• Repairing an existing SKILL.md
• Organizing bundled references and scripts

Add a model provider to OpenClaw and verify it with a real response. The skill validates configuration, keeps credentials in environment or file references, and reports test results and any default model changes.

• Adding a model provider to OpenClaw
• Configuring credentials through environment or file references
• Checking whether a model returns a real response

Summarize an ongoing conversation and launch a fresh background agent to continue the work. The handoff includes the next focus, references to existing documents, and suggested skills, with sensitive information removed.

• Continue ongoing work with a fresh agent
• Hand off work with a specific next focus
• Organize document references for the next session

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

Build a project-specific ECC installation plan from evidence in its code and configuration. Sort skills, rules, commands, and hooks into everyday components and references available when needed, then verify that the applied setup matches the project.

• Selecting ECC components for a specific project
• Separating daily tools from occasional references
• Reviewing outdated language rules and incompatible hooks

Build a shared animation foundation for React and Next.js with motion/react. Define reusable timing and spring settings, respect reduced-motion preferences, adapt to device performance, and align initial animation states with server-rendered content.

• Standardize animation settings across components
• Define reusable spring animation presets
• Respect users' reduced-motion preferences

Review router and switch configurations before deployment. Check for dangerous commands, duplicate IP addresses, overlapping network ranges, undefined references, and exposed management access, using layered checks that help engineers assess changes before applying them.

• Reviewing configuration before a maintenance window
• Auditing configuration generated from templates
• Checking duplicate IP addresses and overlapping network ranges

Look up current library and framework documentation through Context7 MCP, a connection to live documentation tools. Supports setup questions, API references, and code examples, using version-specific sources when available to ground answers in retrieved material.

• Looking up framework setup and configuration
• Checking library API methods and usage
• Finding documentation examples for Prisma queries

Build a project-specific ECC installation plan using evidence from code and configuration. Sort skills, rules, hooks, and other components into items loaded every session and references kept available for occasional use.

• Select ECC components that match a project's technology
• Separate everyday tools from occasional references
• Clean up outdated language rules and incompatible hooks

Get guidance for fine-tuning large language models with Axolotl, adapting them through additional training. Use YAML configuration examples, dataset references, and training methods such as LoRA to set up training and investigate problems.

• Preparing YAML configuration for model fine-tuning
• Exploring LoRA and QLoRA training methods
• Checking dataset formats and API usage

Search arXiv papers by topic, author, category, or ID, then inspect abstracts and full texts or create citation entries. Use Semantic Scholar alongside arXiv to explore related research, references, and citation counts.

• Find recent papers on a research topic
• Look up papers by a specific author
• Explore references and related research

Turn articles, papers, and notes into an interlinked Markdown knowledge base. Summarize sources, update topic pages, answer questions with references, preserve useful comparisons, and audit broken links, conflicting claims, and outdated content.

• Building a research knowledge base from articles and papers
• Adding new sources to existing topic notes
• Saving answers and comparisons with source references

Turn recurring Claude Code tasks into reusable slash commands stored as Markdown files. The guidance covers arguments, file references, tool permissions, shell execution, and plugin integration so commands can run consistent, context-aware workflows.

• Turning recurring review instructions into a command
• Creating commands that accept file paths or issue numbers
• Sharing standard workflows across a project team

Review confirmation questions across gstack skills and set which should always appear, be skipped, or appear only for irreversible actions. Use conversation to manage question tuning and inspect declared preferences alongside patterns inferred from behavior.

• Reviewing previously asked confirmation questions
• Setting when a particular question should appear
• Comparing declared preferences with observed behavior

Implement purposeful animations for existing interfaces or an agreed UI brief. It selects motion based on purpose and usage frequency, then handles timing, interrupted interactions, exits, and reduced-motion preferences while reusing the project’s tools and design values.

• Adding opening and closing motion to modals or drawers
• Implementing button and toggle feedback
• Handling animations interrupted by repeated actions

Choose one visual direction before building, using an existing design system, supplied brand references, or the project brief. Record the choice and define the colors, typography, and other visual settings that guide implementation.

• Set a visual direction before implementation
• Apply an existing design system to a new project
• Turn brand references into a clear design direction

Build a single mobile app screen mockup in an iPhone 15 Pro frame. Choose from six layout types, apply the project's design settings, and produce HTML with device details such as the Dynamic Island and status icons.

• Mocking up a feed or message list
• Exploring a profile or product detail screen
• Presenting a checkout or welcome screen

Turn screenshots, reference links, and rough visual preferences into a reusable DESIGN.md, a record of design decisions, and practical handoff instructions for building prototypes, presentations, redesigns, or image remixes.

• Define an app's visual direction from reference images
• Document design decisions before a redesign
• Hand off consistent visual rules for presentation production

Build and review web animations with GSAP's core API, including movement, rotation, fades, and staggered starts. Adjust timing and easing, meaning changes in speed, and adapt animations to screen size and reduced-motion preferences.

• Adding movement and fades to web page elements
• Animating multiple elements with staggered starts
• Adapting animations to desktop and mobile screens

Build AI agents that retain conversation history, user preferences, and useful interaction patterns with AgentDB. The skill covers persistent storage, meaning memories survive between sessions, plus retrieval, context management, and ReasoningBank integration.

• Add conversation history to a chat system
• Remember user preferences across sessions
• Reuse patterns from successful interactions

Investigate a username, file, code identifier, URL, or concept by exploring connected entities across relevant sources. Produce a dossier with a summary, relationship diagram, source references, and a machine-readable JSON graph.

• Mapping connections around a username or concept
• Investigating references to a file or code identifier
• Tracing links to an architecture decision record