@davila7
Building AI dev tools with LLMs
350 skills4 repositories 32.9K
Improve a LinkedIn profile with clearer headlines, summaries, experience descriptions, and relevant keywords. The skill provides revised sections and action items to help recruiters understand your background while keeping the profile consistent with your resume.
Plan creative resumes in two versions: one readable by applicant tracking systems, which process job applications, and one designed for direct sharing. Get guidance on typography, layout, content, and portfolio links suited to your creative field.
Creates tailored cover letters from a resume and job description, connecting experience and achievements to the role’s requirements. Adapts tone to the company, addresses qualification gaps, and provides alternative openings and interview talking points.
Create social posts, short video scripts, and content calendars suited to each platform. Repurpose existing articles, podcasts, or videos, then use engagement data and successful post patterns to guide improvements.
Audit a site's SEO, plan related topic groups and internal links, and create page briefs and article drafts with metadata and structured data. Save findings and deliverables locally so later sessions can continue from previous work.
Plan a small SaaS business, from checking demand to launching an initial product. The skill helps define an MVP, a first version with only essential features, choose pricing, organize launch tasks, and consider customer acquisition and retention.
Prioritize product features, analyze customer interviews, and draft product requirements documents. Scoring scripts and document templates help turn customer problems, expected impact, and development effort into a roadmap with clear scope and success measures.
Improve the experience after signup so new users reach their first useful result sooner. The skill reviews setup steps, checklists, empty screens, and follow-up messages, then proposes prioritized changes and metrics for measuring activation and retention.
Guides Python agent development with PydanticAI, covering tool calls and structured outputs checked against defined data types. Explains service injection, provider switching, streaming responses, and tests that run without calling a real language model.
Set up reinforcement learning, which trains models using rewards, with verl. Follow workflows for preparing data, configuring GRPO or PPO training, scaling across GPUs, and addressing memory errors or unstable training.
Set up model training with torchforge for reinforcement learning, where rewards guide improvement. Covers training configurations, custom reward and loss functions, and distributed execution with Monarch and TorchTitan, keeping algorithm experiments separate from infrastructure concerns.
Guides language model training with GRPO in TRL, comparing several responses and rewarding better results. Covers dataset preparation, scoring rules for correctness and format, training configuration, monitoring, and saving models for later use.
Use Perplexity to find web resources, recent information, or clear explanations drawn from the web. The skill chooses between search results and conversational answers, while directing specialized documentation and workspace questions to other tools.
Style materials with Anthropic's brand colors and typography. Apply distinct heading and body fonts, choose text colors for the background, and use coordinated accent colors for shapes, with fallback fonts when Poppins or Lora are unavailable.
Design RAG systems that retrieve relevant documents to support LLM answers. The skill guides document splitting, meaning-based and keyword search, result reranking, and separate retrieval evaluation to improve the context passed to the model.
Explore training workflows that reduce harmful model responses using a written set of principles. The skill covers self-critique, revised training examples, and RLAIF, reinforcement learning from AI feedback, with implementation examples and hardware guidance.
Build workflows that extract structured data from LLM responses, check field types and values with Pydantic, and retry failed extractions. Includes examples for nested data, classification, and receiving results as they are generated.
Convert LLMs to GGUF and reduce model size through quantization, which stores weights at lower numerical precision. Prepare models for CPU or Apple Silicon inference, compare compression levels, and integrate them with local AI tools.
Design and refine prompts for language model applications. Choose useful examples, create reusable templates and system instructions, and compare prompt variations using accuracy, consistency, response time, and token usage to guide improvements.
Prepare text for language models using HuggingFace Tokenizers, which splits text into model-readable units. Train custom vocabularies, process batches, track original text positions, and configure input lengths for use with transformers.
Coordinate specialized agents in Claude Code to divide development and review tasks, pass findings between stages, and combine results into one report with prioritized recommendations and action items.
Build voice applications and phone agents with guidance on OpenAI Realtime API, Vapi, Deepgram, ElevenLabs, and LiveKit. Choose services for speech recognition, voice generation, and live communication, while addressing response delays and interruptions.
Improve mobile app listings on Apple App Store and Google Play Store through keyword research, clearer descriptions, visual asset guidance, and review analysis. Create competitor reports, A/B test plans, and launch checklists to guide store page improvements.
Plan, implement, and audit website or app analytics with GA4 and Google Tag Manager. Define meaningful events, standardize campaign tags, and validate data collection so marketing and product decisions use consistent measurements.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)