CS-EEng
Wayner Barrios publishes skills that help an AI agent select and run Hugging Face models, including locally with llama.cpp and GGUF, and train or fine-tune language models on cloud jobs. His catalog also covers code review, security false-positive triage, porting Semgrep rules across languages, and rewriting AI-generated text in Spanish and English. Taken together, his most popular skills lean toward machine learning infrastructure paired with software security and code quality work.
Opencode Power Pack
46 skills · 551 stars · MIT
Agentic Actions Auditor Audit GitHub Actions that run AI agents for prompt injection, unsafe interpolation, sandbox gaps,…
Agents Md Improver Audit and improve project-rules files (AGENTS.md, CLAUDE.md, .agents/instructions, local override…
Agents Md Revise Capture learnings from the current session into the project-rules file (AGENTS.md, CLAUDE.md, or…
Ai Slop Operational rubric that turns "don't make AI slop" into observable properties, severity levels, e…
Code Architect Design a feature architecture by analyzing existing codebase patterns and conventions, then provi…
Code Explorer Deeply analyze an existing codebase feature by tracing execution paths, mapping architecture laye…
Code Quality Agents should invoke this skill for code reviews, linting/formatting setup, maintainability check…
Code Review Review a pull request or a set of code changes for bugs, logic errors, and project-convention vio…
Code Reviewer Review code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence…
Codeql Run CodeQL database creation and security queries, add data-extension models, or process CodeQL S…
Design Patterns Agents should invoke this skill when choosing patterns, designing traits/interfaces/components, d…
Differential Review Performs security-focused differential review of code changes (PRs, commits, diffs).
Feature Dev Guide a feature implementation through a structured seven-phase workflow with deep codebase under…
Fp Check Systematically verifies suspected security bugs to eliminate false positives.
Frontend Design Create distinctive, production-grade frontend interfaces with high design quality and accessible…
Hf Cli Use the `hf` CLI for Hub authentication, downloads, uploads, repositories, cache, jobs, buckets,…
Hf Cloud Sagemaker Deployment Planner Plan and coordinate a model deployment to Amazon SageMaker, including serving stack and real-time…
Hf Cloud Sagemaker Iam Preflight Verify or select a SageMaker execution role before creating models, endpoints, or training jobs.
Hf Cloud Sagemaker Production Defaults Implement a production SageMaker endpoint with autoscaling, CloudWatch alarms, and tags.
Hf Cloud Serving Image Selection Select and verify the current region-specific serving container URI for a SageMaker model deploym…
Huggingface Best Find and compare recommended Hugging Face models for a task using benchmarks, model size, and dev…
Huggingface Community Evals Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware.
Huggingface Llm Trainer Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO,…
Huggingface Local Models Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm.
Huggingface Paper Publisher Publish and manage research papers on Hugging Face Hub.
Huggingface Papers Look up and read Hugging Face paper pages in markdown, and use the papers API for structured meta…
Huggingface Spaces Build, deploy, debug, or maintain a Hugging Face Space using Gradio, Docker, or Static SDKs.
Huggingface Vision Trainer Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs.
Huggingface Zerogpu Implement or debug Hugging Face Spaces ZeroGPU code using `@spaces.GPU`, including isolation, sta…
Humanizer Rewrite AI-generated copy in Spanish and English so it sounds direct, concrete and human while pr…
Insecure Defaults Detects fail-open insecure defaults (hardcoded secrets, weak auth, permissive security) that allo…
Mcp Builder Guide the creation of high-quality MCP (Model Context Protocol) servers that enable LLMs to inter…
Paper Summarizer Agents should invoke this skill for academic or technical papers, arXiv/PubMed/IEEE/ACM links, PD…
Sarif Parsing Parses and processes SARIF files from static analysis tools like CodeQL, Semgrep, or other scanners.
Security Review Perform a focused security review of pending git changes to identify high-confidence security vul…
Semgrep Run Semgrep static analysis across a codebase, optionally using Semgrep Pro for cross-file taint…
Semgrep Rule Creator Creates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patte…
Semgrep Rule Variant Creator Creates language variants of existing Semgrep rules.
Sharp Edges Identify error-prone APIs, dangerous configuration, and footgun designs that enable security mist…
Skill Creator Create new skills (SKILL.md files), modify and improve existing skills, and design skill descript…
Supply Chain Risk Auditor Identifies dependencies at heightened risk of exploitation or takeover.
Train Sentence Transformers Train or fine-tune SentenceTransformer bi-encoders, CrossEncoder rerankers, or SparseEncoder mode…
Transformers Js Run Hugging Face models in JavaScript or TypeScript with Transformers.js, WebGPU, or WASM across…
Trl Training Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning).
Variant Analysis Find similar vulnerabilities and bugs across codebases using pattern-based analysis.
Vuln Report Turn one confirmed security finding into a disclosure-ready GitHub advisory with root cause, proo…