{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"github-zhouxiaoka--autoclip","slug":"zhouxiaoka--autoclip","name":"autoclip","type":"agent","url":"https://zhouxiaoka.github.io/autoclip_intro/","page_url":"https://unfragile.ai/zhouxiaoka--autoclip","categories":["video-generation"],"tags":["ai","ai-agents","ai-tools","ai-video","ai-video-editor","auto","auto-highlight","highlight","llm","video","video-editing","video-processing","videos"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"github-zhouxiaoka--autoclip__cap_0","uri":"capability://tool.use.integration.multi.platform.video.download.and.ingestion","name":"multi-platform video download and ingestion","description":"Automatically downloads videos from YouTube and Bilibili platforms using dedicated API modules (backend.api.v1.youtube and backend.api.v1.bilibili) that handle platform-specific authentication, URL parsing, and video format selection. The system abstracts platform differences behind a unified video ingestion interface, storing downloaded content in a standardized format for downstream processing. Supports both direct URL input and account-based authentication for platform-specific features.","intents":["I want to automatically fetch videos from YouTube or Bilibili without manual downloading","I need to process videos from multiple platforms with a single unified workflow","I want to handle platform-specific authentication and account management programmatically"],"best_for":["content creators automating highlight extraction from their own channels","teams building video analysis pipelines that span multiple platforms","developers integrating video processing into existing content management systems"],"limitations":["Platform API rate limits may throttle bulk video downloads","Bilibili account authentication requires valid credentials and may break with platform changes","YouTube download may be blocked by region restrictions or account-level policies","No built-in retry logic for failed downloads — requires external orchestration"],"requires":["Python 3.9+","FFmpeg installed and accessible in system PATH","Valid API credentials for YouTube Data API (for metadata) or Bilibili account","Network connectivity to target platforms","Sufficient disk space for video storage"],"input_types":["video URL (YouTube or Bilibili)","platform account credentials","video quality preference parameters"],"output_types":["downloaded video file (MP4 or WebM)","video metadata (duration, title, description)","subtitle/caption files if available"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-zhouxiaoka--autoclip__cap_1","uri":"capability://planning.reasoning.llm.powered.video.outline.extraction.and.content.structuring","name":"llm-powered video outline extraction and content structuring","description":"Extracts structured outlines from video content by feeding transcripts or visual keyframes to DashScope API (Alibaba's LLM service), generating hierarchical topic breakdowns with timestamps. The pipeline step (backend.pipeline.step1_outline) uses prompt engineering to convert unstructured video content into machine-readable outlines that segment the video into logical sections. This structured outline becomes the foundation for all downstream analysis, enabling timeline analysis and highlight detection.","intents":["I want to automatically understand the main topics and structure of a video without watching it","I need to segment a long video into logical chapters or sections programmatically","I want to generate a table of contents for video content with timestamp references"],"best_for":["content creators managing large video libraries who need quick content summaries","educational platforms automating course material organization","video analytics teams building content understanding pipelines"],"limitations":["Outline quality depends on transcript accuracy — poor transcripts produce poor outlines","DashScope API calls incur per-token costs that scale with video length","LLM may miss subtle context or misinterpret specialized terminology without domain-specific prompts","No built-in validation that outline timestamps align with actual video content","Requires transcript or visual keyframes as input — cannot work with audio-only or corrupted video"],"requires":["Python 3.9+","DashScope API key from Alibaba Cloud","Video transcript (from speech-to-text) or visual keyframes extracted from video","Network connectivity to DashScope API endpoints","Celery worker process running to execute async tasks"],"input_types":["video transcript (text)","visual keyframes (image sequence)","video metadata (duration, title)"],"output_types":["structured outline (JSON with topics, timestamps, descriptions)","hierarchical topic tree","segment boundaries with confidence scores"],"categories":["planning-reasoning","text-generation-language"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-zhouxiaoka--autoclip__cap_10","uri":"capability://tool.use.integration.fastapi.based.rest.api.with.project.and.video.processing.endpoints","name":"fastapi-based rest api with project and video processing endpoints","description":"Exposes all system functionality through a RESTful API built with FastAPI (backend/main.py and backend/api/v1/) with automatic OpenAPI documentation. Provides endpoints for project CRUD operations, video download/processing, clip retrieval, and status monitoring. Uses FastAPI's dependency injection for authentication, validation, and error handling. Implements proper HTTP status codes, error responses, and request/response schemas with Pydantic validation.","intents":["I want to programmatically submit videos for processing without using the web UI","I need to integrate AutoClip into my own application via API calls","I want to build custom workflows that chain multiple processing operations"],"best_for":["developers building custom applications on top of AutoClip","teams integrating video processing into existing content management systems","platforms offering AutoClip as a backend service to multiple clients"],"limitations":["API rate limiting not implemented — requires external rate limiter (nginx, API gateway)","No built-in API key management — authentication requires custom implementation","Synchronous endpoints block on long-running operations — requires async/polling for large videos","No pagination for large result sets — may cause memory issues with thousands of clips","API schema is tightly coupled to database models — schema changes require API versioning"],"requires":["Python 3.9+","FastAPI 0.95+","Pydantic for request/response validation","Database connection for persistence","Celery workers for async task processing"],"input_types":["JSON request bodies with project/video parameters","URL path parameters (project ID, clip ID)","Query parameters (pagination, filtering)"],"output_types":["JSON responses with project/clip metadata","HTTP status codes (200, 201, 400, 404, 500)","OpenAPI schema (auto-generated documentation)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-zhouxiaoka--autoclip__cap_11","uri":"capability://text.generation.language.multi.language.support.and.internationalization.infrastructure","name":"multi-language support and internationalization infrastructure","description":"Implements internationalization (i18n) infrastructure supporting English and Chinese languages across frontend and backend. Frontend uses i18n library for dynamic language switching with locale-specific formatting. Backend provides language-specific API responses and LLM prompts. Documentation is maintained in both languages with synchronization mechanisms. Enables global user base without requiring separate deployments.","intents":["I want to use AutoClip in my native language (English or Chinese) without language barriers","I need to process videos with content in different languages","I want to contribute translations or add support for additional languages"],"best_for":["global platforms serving both English and Chinese-speaking users","teams building multilingual content creation tools","open-source projects with international contributor communities"],"limitations":["LLM prompts are language-specific — adding new languages requires prompt engineering for each","UI translations are manual — requires translator review for quality","Documentation synchronization is manual — English and Chinese docs can drift","No built-in language detection — users must manually select language","RTL languages (Arabic, Hebrew) are not supported"],"requires":["Python 3.9+","i18n library for frontend (React i18next or similar)","Backend language detection/selection logic","Translation files (JSON or YAML) for each language","Translator resources for quality assurance"],"input_types":["user language preference","video content language","UI locale setting"],"output_types":["localized UI text","language-specific API responses","translated documentation"],"categories":["text-generation-language","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-zhouxiaoka--autoclip__cap_12","uri":"capability://automation.workflow.docker.containerization.and.production.deployment","name":"docker containerization and production deployment","description":"Provides Docker configuration for containerized deployment of the entire system (frontend, backend, Celery workers, Redis). Includes Dockerfile for building application images, docker-compose for local development with all services, and deployment guidance for production environments. Enables consistent deployment across development, staging, and production with minimal configuration drift.","intents":["I want to deploy AutoClip to production with minimal infrastructure setup","I need to run AutoClip locally with all dependencies (Redis, database) without manual installation","I want to scale processing workers independently from the API server"],"best_for":["teams deploying to cloud platforms (AWS, GCP, Azure) with container orchestration","developers wanting reproducible local development environments","organizations with containerization-first infrastructure"],"limitations":["Docker images are large (1-2GB) due to FFmpeg and dependencies — slow to build and push","Volume mounts for video storage require careful configuration — can cause permission issues","Database migrations must be run manually before deployment — no automatic schema updates","Resource limits (CPU, memory) must be tuned per environment — no auto-scaling guidance","Secrets management (API keys, database passwords) requires external solution (Kubernetes secrets, AWS Secrets Manager)"],"requires":["Docker 20.10+","Docker Compose 1.29+ (for local development)","Container registry (Docker Hub, ECR, GCR) for image storage","Kubernetes or Docker Swarm for production orchestration (optional)","Persistent volume storage for video files and database"],"input_types":["Dockerfile configuration","docker-compose.yml with service definitions","environment variables for configuration"],"output_types":["Docker image (built and pushed to registry)","running containers for frontend, backend, workers, Redis","deployment logs and health checks"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-zhouxiaoka--autoclip__cap_2","uri":"capability://data.processing.analysis.timeline.based.video.segmentation.with.topic.detection","name":"timeline-based video segmentation with topic detection","description":"Analyzes structured outlines from step 1 to create fine-grained timeline segments with topic labels and temporal boundaries (backend.pipeline.step2_timeline). Uses LLM-powered analysis to detect topic transitions, segment boundaries, and content coherence across the video duration. Produces a timeline data structure that maps each second of video to its corresponding topic, enabling precise highlight detection and clip generation downstream.","intents":["I want to automatically identify where topics change in a video and mark segment boundaries","I need to create a detailed timeline showing what topic is being discussed at each timestamp","I want to detect natural break points in video content for clip generation"],"best_for":["automated highlight generation systems that need precise segment boundaries","video editing platforms automating chapter creation","content analysis teams studying topic distribution across videos"],"limitations":["Segment accuracy depends on outline quality from step 1 — errors cascade downstream","LLM may struggle with videos that blend multiple topics or have unclear transitions","Timeline granularity is limited by transcript/keyframe sampling rate","No built-in handling for videos with multiple speakers or overlapping conversations","Requires complete outline as input — cannot process partial or incomplete video analysis"],"requires":["Python 3.9+","Completed outline from step1_outline pipeline","DashScope API key for timeline analysis LLM calls","Celery worker process with access to Redis message broker","Video duration metadata"],"input_types":["structured outline (JSON from step 1)","video duration (seconds)","transcript with timestamps"],"output_types":["timeline segments (JSON array with start/end timestamps and topic labels)","topic distribution map (timestamp → topic mapping)","segment confidence scores"],"categories":["data-processing-analysis","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-zhouxiaoka--autoclip__cap_3","uri":"capability://planning.reasoning.ai.driven.highlight.scoring.and.importance.ranking","name":"ai-driven highlight scoring and importance ranking","description":"Scores video segments for highlight potential using LLM analysis (backend.pipeline.step3_scoring) that evaluates engagement, information density, emotional impact, and viewer interest signals. Assigns numerical scores to each timeline segment indicating likelihood of being a good highlight clip. Uses multi-dimensional scoring criteria (entertainment value, educational value, emotional peaks, etc.) to rank segments, enabling intelligent selection of top-N highlights without manual review.","intents":["I want to automatically identify the most interesting or important parts of a video","I need to rank video segments by engagement potential to prioritize clip generation","I want to generate highlights that match specific content categories (educational, entertaining, emotional)"],"best_for":["content creators automating highlight extraction from long-form videos","social media platforms auto-generating short-form clips from user uploads","video analytics platforms ranking content by engagement potential"],"limitations":["Scoring is subjective and may not align with actual viewer preferences without training data","LLM scoring cannot account for external context (trending topics, audience demographics, platform algorithms)","No built-in A/B testing or feedback loop to validate scoring accuracy against actual engagement metrics","Scoring criteria are fixed by prompt engineering — requires code changes to adjust weighting","May over-score dramatic moments while under-scoring subtle but valuable content"],"requires":["Python 3.9+","Completed timeline segments from step2_timeline","DashScope API key for scoring LLM calls","Celery worker process with Redis broker","Segment content context (transcript, visual descriptions)"],"input_types":["timeline segments with topic labels (from step 2)","transcript text for each segment","visual keyframe descriptions","video metadata (category, duration, platform)"],"output_types":["segment scores (0-100 numerical ratings)","score breakdown by dimension (entertainment, education, emotion, etc.)","ranked segment list sorted by overall score","highlight recommendations with confidence levels"],"categories":["planning-reasoning","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-zhouxiaoka--autoclip__cap_4","uri":"capability://image.visual.ffmpeg.based.video.clipping.and.format.conversion","name":"ffmpeg-based video clipping and format conversion","description":"Generates actual video clip files from scored segments using FFmpeg operations orchestrated through backend.services.video_service. Handles video codec selection, bitrate optimization, format conversion (MP4, WebM, etc.), and audio track management. Implements efficient frame-accurate clipping by calculating exact seek positions and duration parameters, avoiding re-encoding when possible to minimize processing time. Supports batch clip generation with parallel FFmpeg processes.","intents":["I want to extract specific time ranges from a video and save them as standalone clip files","I need to convert video formats or optimize bitrate for different platforms (YouTube, TikTok, Instagram)","I want to generate multiple clips from a single video efficiently without re-encoding"],"best_for":["automated highlight generation pipelines that need to produce final video artifacts","content distribution platforms optimizing videos for multiple target platforms","batch video processing systems handling thousands of clips"],"limitations":["FFmpeg re-encoding is CPU-intensive and can take 2-10x real-time depending on codec and bitrate","Frame-accurate clipping requires keyframe alignment — may produce slightly longer/shorter clips than requested","Audio/video sync issues can occur if source video has variable frame rates or dropped frames","No built-in quality validation — corrupted output clips require manual inspection","Parallel FFmpeg processes consume significant system resources — requires careful process pooling"],"requires":["Python 3.9+","FFmpeg 4.0+ installed and in system PATH","Sufficient disk space for temporary files and output clips","Sufficient CPU cores for parallel processing (1 core per concurrent clip)","Source video file accessible on local filesystem"],"input_types":["source video file path","start timestamp (seconds or HH:MM:SS)","end timestamp (seconds or HH:MM:SS)","target format (MP4, WebM, etc.)","bitrate/quality parameters"],"output_types":["video clip file (MP4, WebM, or other format)","clip metadata (duration, file size, codec info)","processing status and error logs"],"categories":["image-visual","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-zhouxiaoka--autoclip__cap_5","uri":"capability://automation.workflow.asynchronous.task.orchestration.with.celery.and.redis","name":"asynchronous task orchestration with celery and redis","description":"Manages the entire video processing pipeline as a series of asynchronous tasks using Celery (backend.core.celery_app) with Redis as the message broker. Each pipeline step (outline extraction, timeline analysis, scoring, clipping) is a separate Celery task that can be distributed across multiple worker processes. Implements task chaining to ensure steps execute in correct order, with intermediate results persisted to database. Provides real-time progress tracking and error handling with automatic retries for transient failures.","intents":["I want to process multiple videos in parallel without blocking the API server","I need to track progress of long-running video analysis operations in real-time","I want to handle processing failures gracefully with automatic retries and error notifications"],"best_for":["web applications processing videos asynchronously to keep UI responsive","systems handling variable processing loads with dynamic worker scaling","teams needing distributed processing across multiple machines"],"limitations":["Celery adds operational complexity — requires Redis broker and worker process management","Task state is eventually consistent — real-time progress updates may lag by seconds","No built-in task prioritization — all tasks processed in FIFO order regardless of urgency","Redis memory usage grows with number of pending tasks — requires monitoring and cleanup","Task result persistence requires database connection — failures in database layer block task completion"],"requires":["Python 3.9+","Redis 5.0+ running and accessible","Celery 5.0+ installed","Database (PostgreSQL/MySQL) for task state persistence","Celery worker processes running (can be same machine or distributed)"],"input_types":["task parameters (video URL, processing options)","task priority level","retry configuration"],"output_types":["task ID for tracking","task status (pending, processing, completed, failed)","intermediate results from each pipeline step","final processing results"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-zhouxiaoka--autoclip__cap_6","uri":"capability://tool.use.integration.real.time.progress.monitoring.and.websocket.based.status.updates","name":"real-time progress monitoring and websocket-based status updates","description":"Provides real-time progress tracking for video processing operations through WebSocket connections that push status updates to the frontend as pipeline steps complete. The backend tracks task state in Redis and broadcasts progress events (step completed, percentage done, current operation) to connected clients. Frontend (frontend/src/pages/ProjectDetailPage.tsx) displays live progress bars and status messages without requiring polling. Enables users to monitor long-running operations without page refreshes.","intents":["I want to see real-time progress of video processing without refreshing the page","I need to know which pipeline step is currently executing and how much longer it will take","I want to receive notifications when processing completes or fails"],"best_for":["web applications with long-running operations that need responsive UX","content creation platforms where users wait for clip generation","systems where processing time is unpredictable and users need visibility"],"limitations":["WebSocket connections require persistent server resources — scales poorly with thousands of concurrent users","Progress estimates are heuristic-based and may be inaccurate for variable-duration tasks","Network disconnections can cause missed updates — requires client-side reconnection logic","No built-in support for progress persistence across page reloads","Real-time updates add latency to task processing if broadcast overhead is not optimized"],"requires":["Python 3.9+","FastAPI with WebSocket support","Redis for task state tracking","Frontend WebSocket client (built into modern browsers)","Network connectivity between client and server"],"input_types":["task ID to monitor","WebSocket connection request"],"output_types":["progress events (JSON with step name, percentage, timestamp)","status updates (processing, completed, failed)","error messages with details"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-zhouxiaoka--autoclip__cap_7","uri":"capability://automation.workflow.project.based.video.processing.workflow.management","name":"project-based video processing workflow management","description":"Organizes video processing as discrete projects (backend.api.v1.projects) with full CRUD operations, metadata storage, and result persistence. Each project encapsulates a single video's processing state, including downloaded video, generated clips, processing logs, and user-defined settings. Projects are stored in database with relationships to all generated artifacts. Enables users to manage multiple videos simultaneously, revisit past processing results, and adjust parameters for re-processing.","intents":["I want to organize multiple video processing jobs and track their status independently","I need to store and retrieve previously generated clips without re-processing","I want to adjust processing parameters and re-run analysis on existing videos"],"best_for":["content creators managing large video libraries with persistent storage needs","teams collaborating on video projects with shared access requirements","platforms offering video processing as a service with user accounts"],"limitations":["Database storage costs scale with number of projects and generated clips","No built-in versioning — re-processing overwrites previous results unless explicitly saved","Project isolation is logical only — no multi-tenancy security boundaries","Cleanup of old projects requires manual deletion — no automatic archival","Project metadata schema is fixed — requires database migration to add new fields"],"requires":["Python 3.9+","Database (PostgreSQL/MySQL) with schema for projects and artifacts","FastAPI backend with SQLAlchemy ORM","File storage (local filesystem or S3) for video files and clips"],"input_types":["project name and description","video URL or file upload","processing parameters (quality, format, etc.)","user ID for access control"],"output_types":["project ID and metadata","list of generated clips with metadata","processing history and logs","project status and statistics"],"categories":["automation-workflow","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-zhouxiaoka--autoclip__cap_8","uri":"capability://planning.reasoning.intelligent.clip.collection.and.recommendation.generation","name":"intelligent clip collection and recommendation generation","description":"Automatically groups generated clips into thematic collections based on topic similarity and scoring patterns (backend.pipeline.step5_collection). Uses LLM analysis to identify natural groupings of related clips and suggest collection themes. Produces curated clip sets that tell coherent stories or cover specific topics, rather than just ranked individual clips. Enables users to publish clip collections as compilations or playlists.","intents":["I want to automatically group related clips into themed collections or compilations","I need to generate playlist recommendations based on clip content and viewer interests","I want to create multi-clip stories that flow naturally from one clip to the next"],"best_for":["content platforms creating curated clip compilations from long-form videos","educational systems organizing video content into learning modules","social media platforms generating shareable clip collections"],"limitations":["Collection quality depends on clip quality and scoring accuracy from earlier steps","LLM-based grouping may create unintuitive collections if topic detection is poor","No built-in validation that clips in a collection actually flow well together","Collection themes are LLM-generated and may not match creator intent","Requires minimum number of clips to form meaningful collections — fails on short videos"],"requires":["Python 3.9+","Completed scored clips from step3_scoring","DashScope API key for collection analysis","Celery worker process","Clip metadata (topic labels, scores, duration)"],"input_types":["list of scored clips with metadata","collection size preferences (min/max clips per collection)","thematic constraints (if any)"],"output_types":["clip collections (grouped lists of clip IDs)","collection themes and descriptions","suggested ordering within collections","collection metadata (duration, topic coverage)"],"categories":["planning-reasoning","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-zhouxiaoka--autoclip__cap_9","uri":"capability://tool.use.integration.react.based.web.ui.with.project.management.and.clip.preview","name":"react-based web ui with project management and clip preview","description":"Provides a responsive web interface (frontend/src/) built with React 18+ for managing projects, uploading videos, monitoring progress, and previewing generated clips. Key components include HomePage for project listing/creation, ProjectDetailPage for real-time progress monitoring, UploadModal for video input, and ClipCard for individual clip preview and management. Uses centralized API client (frontend/src/services/api.ts) with TypeScript for type safety. Implements responsive design for desktop and mobile viewing.","intents":["I want a user-friendly interface to upload videos and start processing without command-line tools","I need to preview generated clips and manage multiple projects from a web browser","I want to see real-time progress and download or share generated clips"],"best_for":["non-technical content creators who need intuitive UI for video processing","teams collaborating on video projects with web-based access","platforms offering video processing as a service to end users"],"limitations":["Large video file uploads are slow over HTTP — requires chunked upload or resumable upload implementation","Browser storage limits prevent caching of large video files locally","Real-time progress updates depend on WebSocket connection stability","No built-in video player — clip preview requires external player library","Mobile UI may be cramped for complex project management workflows"],"requires":["Modern web browser (Chrome, Firefox, Safari, Edge)","Node.js 18+ for development/build","React 18+ and TypeScript","Network connectivity to backend API","JavaScript enabled in browser"],"input_types":["video file (drag-and-drop or file picker)","video URL (YouTube, Bilibili)","project name and description","processing parameters (quality, format)"],"output_types":["rendered HTML/CSS UI","real-time progress updates","clip preview (video player embed)","download links for generated clips"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":44,"verified":false,"data_access_risk":"high","permissions":["Python 3.9+","FFmpeg installed and accessible in system PATH","Valid API credentials for YouTube Data API (for metadata) or Bilibili account","Network connectivity to target platforms","Sufficient disk space for video storage","DashScope API key from Alibaba Cloud","Video transcript (from speech-to-text) or visual keyframes extracted from video","Network connectivity to DashScope API endpoints","Celery worker process running to execute async tasks","FastAPI 0.95+"],"failure_modes":["Platform API rate limits may throttle bulk video downloads","Bilibili account authentication requires valid credentials and may break with platform changes","YouTube download may be blocked by region restrictions or account-level policies","No built-in retry logic for failed downloads — requires external orchestration","Outline quality depends on transcript accuracy — poor transcripts produce poor outlines","DashScope API calls incur per-token costs that scale with video length","LLM may miss subtle context or misinterpret specialized terminology without domain-specific prompts","No built-in validation that outline timestamps align with actual video content","Requires transcript or visual keyframes as input — cannot work with audio-only or corrupted video","API rate limiting not implemented — requires external rate limiter (nginx, API gateway)","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.6145928495383961,"quality":0.35,"ecosystem":0.6000000000000001,"match_graph":0.25,"freshness":0.6,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.1,"match_graph":0.28,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:22.064Z","last_scraped_at":"2026-05-03T13:57:16.560Z","last_commit":"2025-09-24T17:54:59Z"},"community":{"stars":5092,"forks":1046,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=zhouxiaoka--autoclip","compare_url":"https://unfragile.ai/compare?artifact=zhouxiaoka--autoclip"}},"signature":"2kGkzgtha2XPq9655ofnb+aF01xUDxhhHP3OXdm7OFbjkYePKtvJrQjUWb+TxNad/GcUpRByVnwex61Zydl/CA==","signedAt":"2026-06-20T04:55:50.265Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/zhouxiaoka--autoclip","artifact":"https://unfragile.ai/zhouxiaoka--autoclip","verify":"https://unfragile.ai/api/v1/verify?slug=zhouxiaoka--autoclip","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}