1.3K skills · sorted by relevance
The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA auditing.
The English summary is being prepared. Showing the original description.
The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA auditing.
The English summary is being prepared. Showing the original description.
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.
The English summary is being prepared. Showing the original description.
Create or revise skills shipped within the Hermes Agent repository. The guidance covers file placement, required metadata, clear procedures, platform checks, tests, and documentation updates so contributions follow the repository’s authoring standards.
Turn written content and data into a sequence of animated frames for Hyperframes or Remotion. The output includes autoplay, manual navigation, a progress bar, and timing metadata for later video rendering.
Turn repeated corrections into automated safeguards, such as code checks, metadata flags, or scripts. This skill helps choose where each lesson belongs and turns recurring mistakes into concrete changes or actionable tasks.
Convert text, code, or documents into 384-dimensional vectors, numerical representations used for meaning-based search, similarity comparison, and clustering. Save vectors to files, check their dimensions and magnitude, and optionally record metadata in AgentDB.
Manage Contentful spaces, the containers used to organize content, from Claude Code through Composio. List accessible spaces, inspect creation dates and current versions, rename spaces, and review the organization's space inventory.
Create Claude skills with the required files and metadata, validate their structure, and package them as zip files. The skill also shares summaries and file links in designated Slack channels through Rube.
Review OpenAI Cookbook documentation and notebook prose for technical accuracy, readable wording, consistent terminology, and publication metadata. Make focused edits, preserve notebook code and outputs, and report unresolved issues with validation results.
Check images used in social link previews through Open Graph metadata. Verify dimensions, aspect ratio, file size, and HTTPS URLs, then resize assets and update tags to reduce missing images and unwanted cropping.
Audit website images for excessive file sizes, unnecessary metadata, and loading issues. Apply format-specific compression and cleanup, then compare file sizes before and after changes to show the resulting reduction in image data.
Audit the titles, descriptions, images, and URLs shown when web pages are shared on social networks or messaging apps. Check Open Graph metadata, the tags that define link previews, for missing values and incorrect settings.
Check and fix hreflang tags, which identify language and regional versions of web pages for search engines. Review rendered HTML and HTTP responses to find missing reciprocal links, incorrect language codes, and fallback settings.
Audit canonical URLs, which tell search engines the preferred page address, for redirects. The skill checks rendered HTML and HTTP responses, identifies affected routes or templates, and guides updates that point directly to the final URL returning 200 OK.
Audit AI-generated articles for factual accuracy, original value, and a natural voice. Suggest revisions grounded in original research or experience, and inspect rendered HTML, metadata, and response headers to identify issues in search-facing pages.
Audit whether author profiles clearly present relevant experience, qualifications, and professional links. Review rendered pages, metadata, structured data, and HTTP responses to identify specific places where author expertise needs clearer presentation and explain how to verify improvements.
Review article bylines to check that author names, roles, and biography links are clearly visible. Inspect rendered pages and related metadata to identify specific pages or templates that need clearer author information.
Migrate existing Remotion video compositions to HyperFrames HTML and GSAP. Checks source code for unsupported patterns, maps animation and media features, compares rendered videos for visual similarity, and documents translation gaps.
Generate Mandarin and multilingual narration with Volcengine Doubao Speech 2.0. Choose a voice and speaking speed, save the audio, and retain character-level timing metadata for subtitles in an OpenMontage workflow.
Find and read documents in Box, upload or download files, and organize shared content. Manage comments and metadata, rename or move items, and restore files or folders that remain in the trash.
Create integration tests for syncable metadata entities in Twenty itself. Cover invalid inputs, validation errors, and successful data operations, using reusable GraphQL request helpers, error snapshots, and cleanup routines to organize the test suite.
Draft Appwrite blog posts around concrete developer problems and search intent. Structure the article, prepare titles, summaries, FAQs, and article metadata, check product claims against local documentation, and generate a cover image using Appwrite's cover API.
Prepare WaveTone 2.61 audio analysis workflows by inspecting audio metadata and recording tempo, labels, and intended settings in a JSON project manifest. Launch the Windows application to perform analysis and save its outputs.