All categories
Documentation
Docs, README files, API references, tutorials, specs, and changelogs
- 16,089
- 671
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse documentation skills
Showing 6,913–6,936 of 16,089 skills
- Reinforcement Learning Vision ModelsTrain multimodal LLMs with RL (PIVOT) instead of SFT to produce stronger, precisely-localized visual representations in vision encoders using <1% of standard pretraining cost.Votes: 0GitHub stars: 6
- Reasoning Gym Verifiable RewardsCreate infinite training environments for reasoning with automatic verification using procedural generation and domain-specific evaluators.Votes: 0GitHub stars: 6
- Reasongen R1 Cot Image GenerationEnable image generators to reason explicitly through text before creating images using supervised fine-tuning and reinforcement learning optimization.Votes: 0GitHub stars: 6
- Quantized Evolution StrategiesFine-tune quantized LLMs directly in low-precision discrete parameter space using evolution strategies with accumulated error feedback. Overcome gradient stagnation in quantized models by accumulating fractional updates using Delta-Sigma modulation, achieving significant improvements in INT4 quantized models without full-precision gradients.Votes: 0GitHub stars: 6
- Multiverse Parallel GenerationEnable native parallel token generation in language models by implementing adaptive task decomposition and merge strategies, achieving 2x speedup with 1.87% performance gains.Votes: 0GitHub stars: 6
- Minority Aware Adaptive Dpo DiffusionImprove diffusion model alignment with human preferences by handling subjective and conflicting annotations. Adaptive-DPO incorporates minority-instance metrics (intra-annotator confidence and inter-annotator stability) to distinguish majority from minority samples, enhancing performance on both synthetic and real preference data.Votes: 0GitHub stars: 6
- Llm Finetuning Dataset SynthesisAutomatically generate high-quality domain-specific fine-tuning datasets from raw documents using adaptive processing and persona-driven synthesis, preserving general capabilities while specializing models.Votes: 0GitHub stars: 6
- Livr Visual ReasoningEnable richer visual reasoning in multimodal models via learnable latent tokens trained with visual bottlenecking. Introduces special tokens that implicitly learn task-relevant visual abstractions without explicit supervision, through attention masking forcing visual information through latents—improving vision-heavy tasks without task-specific annotations.Votes: 0GitHub stars: 6
- Hpsv3 Human Preference Score EvaluationA VLM-based preference scoring system trained on 1.17M annotated comparisons to evaluate text-to-image generation quality at scale. Uses uncertainty-aware ranking loss for fine-grained assessment across diverse images and supports iterative quality improvement through chain-of-human-preference sampling.Votes: 0GitHub stars: 6
- Golden Goose Task SynthesisSynthesize unlimited verifiable training tasks from unverifiable text by converting reasoning passages into multiple-choice problems. Creates higher-quality training data for RLHF systems without requiring new human labels.Votes: 0GitHub stars: 6
- Deepseek Math V2 Self VerifiableSynergistic verifier-generator training loop enabling LLMs to identify logical issues in mathematical proofs without reference solutions, improving reasoning rigor through meta-verification. Apply when you need to scale mathematical reasoning without hand-labeled proof annotations.Votes: 0GitHub stars: 6
- Dcm Dual Expert ConsistencyAccelerate video generation through dual-expert consistency distillation, using separate denoisers for semantic layout/motion and detail refinement to resolve conflicting optimization gradients.Votes: 0GitHub stars: 6
- Data Recipe Rl OptimizationAutomatically synthesize and optimize training data using GRPO to generate data recipes (specifications for dataset creation). Use a Data Verifier to efficiently evaluate sample quality without full model training. Achieve performance comparable to human expert curation across diverse domains.Votes: 0GitHub stars: 6
- Control R Controllable ScalingEnable dynamic control over reasoning depth during inference using Reasoning Control Fields that guide long chain-of-thought generation based on execution and quality parameters.Votes: 0GitHub stars: 6
- Confidence Rl FinetuningImprove language model reasoning using only model confidence as reward signals, eliminating need for labels or preference models while achieving substantial gains with minimal data.Votes: 0GitHub stars: 6
- Complex Image EditingDecompose complex image editing instructions into simpler sub-tasks with automatically generated control guidance. Handles multi-object edits, preserves identity of surrounding regions, and eliminates manual mask creation.Votes: 0GitHub stars: 6
- Automated Tool Learning RlImproves LLM tool-use capabilities through automated environment construction that generates realistic feedback and verifiable rewards for RL-based training without external tools.Votes: 0GitHub stars: 6
- Paper2skill V0.0.2Convert arXiv and ML/AI research papers into ready-to-use Claude agent skills in seconds — so anyone can apply cutting-edge techniques without reading the full paper. Use this skill whenever the user wants to turn a paper into a skill, extract practical techniques from research, build a skill library from papers, create a paper-to-skill pipeline, convert arXiv papers into reusable agent instructions, or batch-process multiple papers into skills. Also trigger when someone asks about extracting...Votes: 0GitHub stars: 6
- Scan[Documentation] Use when a workflow step or the user asks for one project-reference doc to be regenerated. --target=<doc key> (project-structure, code-review-rules, domain-entities, docs-index). All docs: scan-all.Votes: 0GitHub stars: 3
- Release Doc[Git] Use when creating release notes or a release document from git history at any scope (tag, branch, time range), as markdown plus a standalone HTML presentation.Votes: 0GitHub stars: 3
- Kg FactoriesAuthor genai-graph factories that turn a data source into graph nodes — JsonFileBackedFactory, TableBackedFactory, DocumentGraphFactory, MarkdownBamlFactory (inline BAML entity extraction), DocumentDirectoryFactory, Neo4jImportFactory, SimilarityFactory, canonical node reuse, and GraphRegistry multi-source merge. Use when adding a new data source to a Knowledge Graph, writing a factory subclass, or editing genai_graph/kg/factories.Votes: 0GitHub stars: 3
- StandardsMandatory workflow for engineering-critical GitHub issues — resource intelligence, plan review, TDD, implementation, and 3-provider cross-review.Votes: 0GitHub stars: 17
- Yaml Workflow ExecutorExecute data processing workflows defined in YAML configuration files. Supports data loading, transformation, validation, and reporting pipelines.Votes: 0GitHub stars: 17
- Astm> American Society for Testing and Materials (ASTM) standards for material properties and testing methods. **Version:** 1.0.0 **Created:** 2026-01-12 **Category:** SME / Codes & StandardsVotes: 0GitHub stars: 17