floytra-dev/ultra-max-token-burner
Skill Claude CodeCodex
Expand concise requests into larger, coherent, manager-visible prompts using controlled procedural overhead.
not rated 4 2mo ago A 24 tokens
original MIT
deepseek-api
554prakhargaba007/deepseek-agent-docs
Skill Claude CodeCodex
Reference guide for DeepSeek API integration, parameter specs, thinking mode, OpenAI/Anthropic SDK compatibility, FIM, tool calling, and code generation best practices.
not rated 4
changed 5d ago A 38 tokens
original MIT
prompt-rewrite
555jidechao/Prompt-Best-Practices
Skill Codex
Rewrite a weak or vague prompt into a strong one following the four-part framework (Goal / Context / Output / Boundaries) and six prompting principles. Output is a fixed four-section structure: diagnosis, rewritten prompt, change notes, and assumptions made. Use when the user provides an existing prompt (any language)…
not rated 4 1mo ago A 156 tokens
promptopskit
556PredictabilityAtScale/promptopskit
Skill Claude CodeCodex
Guidance for creating and editing promptopskit prompt files, defaults, variables, and validation-safe templates.
not rated 4 1mo ago A 27 tokens
flash-attention
557Skill Claude CodeCodex
The following reference files contain in-depth documentation for each component.
not rated 4 4mo ago A 0 tokens
project-osmos
558Skill Claude CodeCodex ✓ vendor
Use Project Osmos agents for Microsoft Fabric data engineering tasks that create or update notebooks, Spark code, Lakehouses, and OneLake resources. Triggers: "Project Osmos", "Fabric data engineering", "Spark Transform Notebook", "OneLake ETL", "Fabric Project Osmos".
not rated 4
changed 5d ago A 62 tokens
prompt-reframe
559Skill Claude CodeCodex
Tighten user prompts before they reach a model — strip conversational filler, drop fragments, dedupe sentences, rank by relevance, and compose a short, declarative system prompt that doesn't waste context. CPU-only, deterministic, dependency-free. Use it whenever a request is long, rambling, or covered in pleasantries…
not rated 4 today A 88 tokens
original MIT
k-vaca/prompt-engineering-skill
Skill Claude CodeCodex
Write, review, and optimize professional prompts for large language models. Use this skill whenever the user asks to write, draft, design, improve, fix, debug, review, or optimize a prompt, system prompt, prompt template, meta-prompt, or agent instructions; asks why a prompt "isn't working" or gives inconsistent…
not rated 4
+1 1mo ago A 215 tokens
original MIT
Skill Codex
Use when creating, auditing, rewriting, debugging, migrating, or evaluating GPT-5.6 Sol, Terra, or Luna prompt layers, tool descriptions, agent briefs, or prompt stacks; choosing runtime configuration; or comparing controlled prompt candidates.
not rated 4
+1 1mo ago A 58 tokens
original MIT
vision
562Skill Claude CodeCodex
A vision bridge that sends images to supported visual-language services and returns text descriptions to a text-only model. It includes tools for image analysis, text extraction, image comparison, error screenshots, diagrams, and interface reviews.
not rated 4
+1 2mo ago A 80 tokens
original MIT
Skill Claude CodeCodex
Use this skill whenever asked to join an autoevolve run, evolve code toward a measured target, work an evolution population, mutate a candidate under EVOLVE-BLOCK rules, or report measured autoevolve progress and artifacts.
not rated 4
+1 1mo ago A 50 tokens
original Apache-2.0
COAMS
564Skill Claude CodeCodex
Content Operating and Management System (Markdown-Native CMS).
not rated 4
+1 5mo ago A 14 tokens
original MIT
catalog-config
565Skill Claude CodeCodex
Kedro catalog configuration guidance for conf//.yml files. Use when adding datasets, editing catalog entries, setting up factories, or working with credentials and parameter interpolation.
not rated 4
+2 7d ago A 37 tokens
original Apache-2.0
Skill Claude CodeCodex
Analyze Power BI semantic models for column-level overlaps that confuse Copilot and Fabric data agents. Detect ambiguity, review with domain expert, apply fixes via MCP.
not rated 4 3d ago A 37 tokens
original MIT
migrate
567Bilal140202/the-lord-of-the-skills
Skill Claude CodeCodex
Migrate an application with hardcoded LLM prompts to a full LaunchDarkly AgentControl implementation in five stages: audit the code, wrap the call, move the tools, add tracking, attach evaluators. Use when the user wants to externalize model/prompt configuration, move from direct provider calls (OpenAI, Anthropic…
not rated 4 4d ago A 96 tokens
original MIT
Skill Claude CodeCodex
A tool for creating example time-series data and loading it into an IDMP system. It models assets such as equipment and their hierarchy, then produces configuration and simulated readings.
not rated 3
changed 3d ago A 64 tokens
original MIT
hotin
569Skill Claude CodeCodex
Use when asked what is new, trending, hot, or worth using in AI right now - which repos, models, papers or launches matter this week, or whether a specific project is gaining traction. Answers from a ranked board with evidence instead of from training data or search-engine marketing.
not rated 3 2d ago A 60 tokens
original Apache-2.0
echoyu1025-a11y/ai-product-skills
Skill Claude CodeCodex
A planning guide for turning an AI product idea into a written product architecture. It organizes the idea around users, situations, capabilities, and data, then explains how information moves through the product.
not rated 3 2mo ago A 159 tokens
original MIT
H-Ali13381/recursive-agent-improvement
Skill Claude CodeCodex
Use when an agent repeatedly fails at a narrow measurable subtask, the user wants a trainable specialist tool instead of more prompting, or the task needs an evaluator, reranker, classifier, detector, verifier, or small PyTorch model exposed to an agent.
not rated 3 3mo ago A 57 tokens
original MIT
Liu-MingH/Scientific-research-SKILL
Skill Claude CodeCodex
Structured AI-assisted scientific code generation. 6 safety guards, 8 principles, 11 prompt templates. Grounded in Nature (2026).
not rated 3 2mo ago A 35 tokens
original MIT
colab-mcp-server
573Skill Claude CodeCodex
This repository exposes a headless Google Colab MCP server. Use it when you need an AI agent to control a live Colab notebook through MCP without browser automation.
not rated 3 6d ago A 0 tokens
original Apache-2.0
prompt-pyramid
574Skill Claude CodeCodex
Reorder and purify scattered image-generation tags (Stable Diffusion, Flux, NovelAI, ComfyUI, WebUI, danbooru-style booru tags) into a single clean comma-separated prompt string built on a visual-weight pyramid. Use this skill PROACTIVELY whenever the user is writing or fixing a prompt for diffusion models — tags…
not rated 3
+1 1mo ago A 210 tokens
original MIT
Hearmeman24/minimax-worldbuilder
Skill Claude CodeCodex
Compose MiniMax-H3 video-with-native-audio prompts in H3's mandatory structured format — full-reference (Ref2VA) and text-to-video (T2VA) only. Use whenever the target model is MiniMax-H3: the user says MiniMax, MiniMax-H3, H3, ref2va / r2v / t2v, names a minimaxh3 checkpoint, or names the MiniMaxH3ReferenceToVideo /…
not rated 3
+1 1mo ago A 333 tokens
Ztsdut/ml-architecture-diagram-skill
Skill Claude CodeCodex
Create accurate, publication-ready, editable machine-learning and deep-learning architecture diagrams from model code, configuration files, model summaries, graph exports, or written specifications. Use for neural-network figures, architecture schematics, model block diagrams, training/inference diagrams, paper…
not rated 3
+1 29d ago A 95 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: