Explore skills
Showing 65671–65700 of 71451 skills
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
jackychenlu/skill-demo
Stars: 0Claude CodeCodexVision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.
jackychenlu/skill-demo
Stars: 0Claude CodeCodexAnthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.
jackychenlu/skill-demo
Stars: 0Claude CodeCodexControl LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
jackychenlu/skill-demo
Stars: 0Claude CodeCodexMeta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
jackychenlu/skill-demo
Stars: 0Claude CodeCodexState-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.
jackychenlu/skill-demo
Stars: 0Claude CodeCodexWrite publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
jackychenlu/skill-demo
Stars: 0Claude CodeCodexTrain Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.
jackychenlu/skill-demo
Stars: 0Claude CodeCodexProvides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
jackychenlu/skill-demo
Stars: 0Claude CodeCodexOptimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
jackychenlu/skill-demo
Stars: 0Claude CodeCodexTriage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
JiayiV/question_mixing
Stars: 0Claude CodeCodexExpert at designing and creating VS Code custom agents with optimal configurations
JiayiV/question_mixing
Stars: 0Claude CodeCodexImproves the accessibility of markdown files using five GitHub best practices
JiayiV/question_mixing
Stars: 0Claude CodeCodexHuman-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.
JiayiV/question_mixing
Stars: 0Claude CodeCodexElite bug-fixing agent that enriches task context from Monday.com platform data. Gathers related items, docs, comments, epics, and requirements to deliver production-quality fixes with comprehensive PRs.
JiayiV/question_mixing
Stars: 0Claude CodeCodexHolistic software architecture planner that evaluates tech stacks, designs scalability roadmaps, performs cloud-agnostic cost analysis, reviews existing codebases, and delivers interactive Mermaid diagrams with HTML preview and draw.io export
JiayiV/question_mixing
Stars: 0Claude CodeCodexGenerates professional MS Word project documentation with draw.io architecture diagrams and embedded PNG images. Automatically discovers any project's technology stack, architecture, and code structure. Produces Markdown, draw.io diagrams, PNG exports, and .docx output.
JiayiV/question_mixing
Stars: 0Claude CodeCodexVben Admin 5.0 前端框架开发技能。用于开发基于 Vue3、Vite、TypeScript 的中后台管理系统。
vbenjs/skills
Stars: 36Claude CodeCodexSync new or updated skills to the brain-os GitHub repository. Run this after creating or modifying any skill. Pushes SKILL.md files from .claude/skills/ to github.com/dgnernvsinjsbt/brain-os.
cbbkrd-tech/jl-finishes
Stars: 0Claude CodeCodexWhen the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "content ideas," "blog strategy," "topic clusters," or "content planning." For writing individual pieces, see copywriting. For SEO-specific audits, see seo-audit.
cbbkrd-tech/jl-finishes
Stars: 0Claude CodeCodexFind the next batch of Facebook Business Page URLs for HVAC/local service leads using Serper.dev. Trigger this skill when the user says "podaj mi 30 linkow", "nastepna partia leadow", "znajdz kolejne linki FB", "podaj kolejne 30", "kolejna partia", "/fb-finder", or any variant asking for the next batch of Facebook leads.
cbbkrd-tech/jl-finishes
Stars: 0Claude CodeCodexWhen the user wants to optimize any form that is NOT signup/registration — including lead capture forms, contact forms, demo request forms, application forms, survey forms, or checkout forms. Also use when the user mentions "form optimization," "lead form conversions," "form friction," "form fields," "form completion rate," or "contact form." For signup/registration forms, see signup-flow-cro. For popups containing forms, see popup-cro.
cbbkrd-tech/jl-finishes
Stars: 0Claude CodeCodexCreate stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
cbbkrd-tech/jl-finishes
Stars: 0Claude CodeCodexResearch best practices via MCP Ref/Context7/WebSearch and create documentation (guide/manual/ADR/research). Single research, multiple output types.
cbbkrd-tech/jl-finishes
Stars: 0Claude CodeCodexCommit and push ALL changes (staged + unstaged + untracked) to the remote repository
cbbkrd-tech/jl-finishes
Stars: 0Claude CodeCodexSync skills (symlinks) and MCP settings from Claude to Gemini CLI and Codex CLI
cbbkrd-tech/jl-finishes
Stars: 0Claude CodeCodexUniversal context reviewer: delegates arbitrary context (plans, decisions, documents, architecture proposals) to external agents (Codex + Gemini) for independent review with debate protocol. Context always passed via files.
cbbkrd-tech/jl-finishes
Stars: 0Claude CodeCodexMeta-orchestrator (L0): reads kanban board, lets user pick ONE Story, drives it through pipeline 300->310->400->500 via TeamCreate. User-confirmed merge to develop after quality gate PASS.
cbbkrd-tech/jl-finishes
Stars: 0Claude CodeCodexCoordinates project documentation creation. Gathers context once, detects project type, delegates to 5 L3 workers (ln-111-115). L2 Coordinator invoked by ln-100.
cbbkrd-tech/jl-finishes
Stars: 0Claude CodeCodexCreates runbook.md for DevOps setup. L3 Worker invoked CONDITIONALLY when hasDocker detected.
cbbkrd-tech/jl-finishes
Stars: 0Claude CodeCodex