Profile My skills Saved Collections Edit profile Submit a skill

← all publishers

jrajasekera

@jrajasekera source repo

9 published skills

  1. ▌
    AI Toolkit Training · jrajasekera bundle
    Plan, configure, run, debug, and evaluate image, instruction/edit, video, and audio training jobs with Ostris AI Toolkit. Use for LoRA/LoKr/LoRM training, dataset and caption preparation, YAML creation or review, model-specific setup, quantization and memory decisions, resume/checkpoint handling, cloud deployment, or Hugging Face publishing. Always verify the user's installed AI Toolkit revision before relying on model-specific fields.
    0
    installs
  2. ▌
    Modal Serverless Gpu · jrajasekera bundle
    Modal Serverless GPU — deploy Python functions with GPUs, web endpoints, and scaling
    0
    installs
  3. ▌
    Z AI API · jrajasekera bundle
    Z.ai API integration for building applications with GLM models. Use when working with Z.ai/ZhipuAI APIs for: (1) Chat completions with GLM-4.7/4.6/4.5 models, (2) Vision/multimodal tasks with GLM-4.6V, (3) Image generation with GLM-Image or CogView-4, (4) Video generation with CogVideoX-3 or Vidu models, (5) Audio transcription with GLM-ASR-2512, (6) Function calling and tool use, (7) Web search integration, (8) Translation, slide/poster generation agents. Triggers: Z.ai, ZhipuAI, GLM, BigModel, Zhipu, CogVideoX, CogView, Vidu.
    0
    installs
  4. ▌
    Codex Review · jrajasekera
    Review non-trivial design docs or implementation plans with Codex before coding; validate feedback; fix critical plan issues; ask about non-critical choices. Also triggers when the user says "use codex-review", "ask Codex", or "get Codex feedback".
    0
    installs
  5. ▌
    Venice AI API · jrajasekera bundle
    Build, migrate, and debug integrations with the Venice.ai API. Covers OpenAI-compatible chat and Responses, live model discovery and routing, multimodal and file inputs, reasoning, tools, web/X search, image generation and editing, audio, video, embeddings, augment APIs, characters, API-key administration, billing, x402/SIWX wallet authentication, and crypto RPC. Use whenever code calls api.venice.ai, a user asks which Venice model or endpoint to use, or an existing Venice integration may be stale.
    0
    installs
  6. ▌
    Openrouter API · jrajasekera bundle
    Build, migrate, debug, and operate integrations with the OpenRouter API. Covers live model and provider discovery, Chat Completions, the stateless Responses API, the Anthropic-compatible Messages API, official SDKs, routing and fallbacks, reasoning, structured outputs, client and server tools, streaming, multimodal inputs, image/audio/video generation, embeddings, reranking, caching, OAuth, administration, observability, privacy, and production error handling. Use whenever code calls openrouter.ai, a user asks which OpenRouter endpoint/model/provider to use, or an existing OpenRouter integration may be stale.
    0
    installs
  7. ▌
    Pandoc Converter · jrajasekera bundle
    Convert documents between formats using Pandoc. Use when the user asks to convert files between formats like markdown, docx, html, pdf, latex, epub, rtf, csv, xlsx, or pptx. Triggers on requests like "convert this to Word", "export as PDF", "turn this markdown into HTML", or "convert the CSV to a table".
    0
    installs
  8. ▌
    Article Extractor · jrajasekera bundle
    Extract clean article content from URLs and save as markdown. Triggers when user provides a webpage URL and wants to download it, extract content, get a clean version without ads, capture an article for offline reading, save an article, grab content from a page, archive a webpage, clip an article, or read something later. Handles blog posts, news articles, tutorials, documentation pages, and similar web content. Supports Wayback Machine for dead links or paywalled content. This skill handles the entire workflow - do NOT use web_fetch or other tools first, just call the extraction script directly with the URL.
    0
    installs
  9. ▌
    Sqlite Optimization · jrajasekera bundle
    Optimize SQLite database performance through configuration, schema design, indexing, and query tuning. Use when users ask to improve SQLite speed, reduce latency, optimize queries, configure PRAGMAs, fix slow queries, handle concurrency, optimize writes/inserts, or tune SQLite for production. Triggers on mentions of SQLite performance, slow queries, PRAGMA settings, WAL mode, indexing strategies, bulk inserts, or database maintenance (VACUUM, ANALYZE).
    0
    installs