High-intent entry points

Start from the task, not a keyword list.

These shortcuts use the same trust, supply, and relevance signals as the registry API, so humans and agents land on a useful shortlist faster.

Agent-readable index

FinanceStock analysis QuantTrading research SlidesPPT generation DocsPDF parsing ExtractWeb scraping CreativeDesign workflow SportsFootball analytics

Decision filters

Choose by scenario, quality, and trust signals.

Use casePlatform fitQuality tierTrust profileSafety gateGitHub adoption

Showing 1-16 of 719 ranked candidates matching "distillation"

Best blend of quality, stars, freshness, and agent usage

Revisiting Reverse Distillation

NEEDS REVIEW · 48TRUST · 70SAFE · EXPERIMENTALCODING

(CVPR 2023) Revisiting Reverse Distillation for Anomaly Detection

$ npx skills add tientrandinh/Revisiting-Reverse-Distillation

170 stars34 quality70 trustExperimentalClaude Code3y since pushNeeds review

QualityInspect the repository carefully before adding it to an agent workflow.Check: Repository looks stale

TrustPotentially useful, but at least one trust signal needs human inspection.Review: Repository looks stale

Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

Claude Code + CLI · 4 targets

pythoncomputer-vision

by tientrandinhDetailsQuick view

Stagewise Knowledge Distillation

NEEDS REVIEW · 42TRUST · 67SAFE · BLOCKEDRESEARCH

Code implementation of Data Efficient Stagewise Knowledge Distillation paper.

$ npx skills add IvLabs/stagewise-knowledge-distillation

114 stars33 quality67 trustBlocked for auto-installClaude Code6y since pushRisky

QualityInspect the repository carefully before adding it to an agent workflow.Check: Repository looks stale

TrustPotentially useful, but at least one trust signal needs human inspection.Review: License is unclear

Safety gateThis skill should not be selected by an agent without explicit human security review.

Scenario RAG and knowledge · I need my agent to build a RAG workflow over documents and retrieve reliable context.

Claude Code + CLI · 4 targets

jupyter-notebookresearch

by IvLabsDetailsQuick view

Mtt Distillation

NEEDS REVIEW · 48TRUST · 71SAFE · EXPERIMENTALCODING

Official code for our CVPR '22 paper "Dataset Distillation by Matching Training Trajectories"

$ npx skills add GeorgeCazenavette/mtt-distillation

441 stars37 quality71 trustExperimentalClaude Code2y since pushNeeds review

QualityInspect the repository carefully before adding it to an agent workflow.Check: Repository looks stale

TrustPotentially useful, but at least one trust signal needs human inspection.Review: License is unclear

Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

Claude Code + CLI · 4 targets

pythoncomputer-vision

by GeorgeCazenavetteDetailsQuick view

Awesome Human Distillation

STRONG · 80TRUST · 79SAFE · REVIEWEDCODING

A curated catalog of human distillliation agent skills

$ npx skills add mliu98/awesome-human-distillation

650 stars53 quality79 trustReviewedClaude Code23d since pushSafe to try

QualitySolid option that is likely worth shortlisting for production workflows.

TrustGood trust signals with a few areas worth checking before rollout.Review: License is unclear

Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

Claude Code + CLI · 4 targets

pythonai-agents

by mliu98DetailsQuick view

Knowledge Distillation Pytorch

VERIFIEDSTRONG · 73TRUST · 82SAFE · EXPERIMENTALCODING

A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility

$ npx skills add haitongli/knowledge-distillation-pytorch

2.0K stars50 quality82 trustExperimentalClaude Code3y since pushNeeds review

QualitySolid option that is likely worth shortlisting for production workflows.Check: Repository looks stale

TrustGood trust signals with a few areas worth checking before rollout.Review: Repository looks stale

Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario GitHub automation · I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

Claude Code + CLI · 4 targets

pythoncomputer-vision

by haitongliDetailsQuick view

Lightly Train

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · VERIFIEDCODING

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

$ npx skills add lightly-ai/lightly-train

1.6K stars64 quality91 trustVerifiedClaude Code21d since pushSafe to try

QualityHigh-confidence pick with strong adoption and healthy maintenance signals.

TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…

Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

Scenario Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

Claude Code + CLI · 4 targets

pythoncomputer-vision

by lightly-aiDetailsQuick view

Causal Forcing

STRONG · 83TRUST · 82SAFE · REVIEWEDDESIGN

[ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal For…

$ npx skills add thu-ml/Causal-Forcing

786 stars54 quality82 trustReviewedClaude Code1mo since pushSafe to try

QualitySolid option that is likely worth shortlisting for production workflows.

TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review

Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Design and creative · I need my agent to produce design assets, UI directions, presentations, or creative media workflows.

Claude Code + CLI · 4 targets

pythonvideo-generation

by thu-mlDetailsQuick view

Rcm

STRONG · 83TRUST · 82SAFE · REVIEWEDDESIGN

rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale

$ npx skills add NVlabs/rcm

701 stars54 quality82 trustReviewedClaude Code1mo since pushSafe to try

QualitySolid option that is likely worth shortlisting for production workflows.

TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review

Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Design and creative · I need my agent to produce design assets, UI directions, presentations, or creative media workflows.

Claude Code + CLI · 4 targets

pythonvideo-generation

by NVlabsDetailsQuick view

Mdistiller

NEEDS REVIEW · 51TRUST · 72SAFE · EXPERIMENTALRESEARCH

The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679 and [ICCV2023] DOT: A Distillation-Oriented Trainer https://o…

$ npx skills add megvii-research/mdistiller

901 stars39 quality72 trustExperimentalClaude Code3y since pushNeeds review

QualityInspect the repository carefully before adding it to an agent workflow.Check: Repository looks stale

TrustGood trust signals with a few areas worth checking before rollout.Review: License is unclear

Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario RAG and knowledge · I need my agent to build a RAG workflow over documents and retrieve reliable context.

Claude Code + CLI · 4 targets

pythoncomputer-vision

by megvii-researchDetailsQuick view

EdgeCrafter

STRONG · 75TRUST · 80SAFE · REVIEWEDCODING

Pytorch implementation of "EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation"

$ npx skills add Intellindust-AI-Lab/EdgeCrafter

253 stars48 quality80 trustReviewed with permission notesClaude Code2mo since pushSafe to try

QualitySolid option that is likely worth shortlisting for production workflows.

TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review

Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario GitHub automation · I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

Claude Code + CLI · 4 targets

pythoncomputer-vision

by Intellindust-AI-LabDetailsQuick view

WaDi

STRONG · 71TRUST · 77SAFE · REVIEWEDDESIGN

[CVPR 2026] Official PyTorch implementation of WaDi: Weight Direction-aware Distillation for One-step Image Synthesis

$ npx skills add gudaochangsheng/WaDi

153 stars49 quality77 trustReviewed with permission notesClaude Code1mo since pushNeeds review

QualitySolid option that is likely worth shortlisting for production workflows.

TrustGood trust signals with a few areas worth checking before rollout.Review: License is unclear

Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Design and creative · I need my agent to produce design assets, UI directions, presentations, or creative media workflows.

Claude Code + CLI · 4 targets

pythonimage-generation

by gudaochangshengDetailsQuick view

Annotated Deep Learning Paper Implementations

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · VERIFIEDCODING

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (ad…

$ npx skills add labmlai/annotated_deep_learning_paper_implementations

66.9K stars70 quality91 trustVerifiedClaude Code6mo since pushSafe to try

QualityHigh-confidence pick with strong adoption and healthy maintenance signals.

TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…

Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

Scenario Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

Claude Code + CLI · 4 targets

pythonmachine-learning

by labmlaiDetailsQuick view

Diffusion Distiller

NEEDS REVIEW · 50TRUST · 72SAFE · EXPERIMENTALDESIGN

🚀 PyTorch Implementation of "Progressive Distillation for Fast Sampling of Diffusion Models(v-diffusion)"

$ npx skills add Hramchenko/diffusion_distiller

260 stars36 quality72 trustExperimentalClaude Code4y since pushNeeds review

QualityInspect the repository carefully before adding it to an agent workflow.Check: Repository looks stale

TrustGood trust signals with a few areas worth checking before rollout.Review: Repository looks stale

Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario Multimodal media · I need my agent to process images, video, or audio and extract useful information.

Claude Code + CLI · 4 targets

pythonimage-generation

by HramchenkoDetailsQuick view

Efficientsam3

STRONG · 80TRUST · 80SAFE · REVIEWEDCODING

EfficientSAM3 compresses SAM3 into lightweight, edge-friendly models via progressive knowledge distillation for fast promptable concept segmentation and tracking.

$ npx skills add SimonZeng7108/efficientsam3

610 stars53 quality80 trustReviewedClaude Code25d since pushSafe to try

QualitySolid option that is likely worth shortlisting for production workflows.

TrustGood trust signals with a few areas worth checking before rollout.Review: License is unclear

Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario GitHub automation · I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

Claude Code + CLI · 4 targets

jupyter-notebookcomputer-vision

by SimonZeng7108DetailsQuick view

RLeXplore

NEEDS REVIEW · 53TRUST · 73SAFE · EXPERIMENTALCODING

RLeXplore provides stable baselines of exploration methods in reinforcement learning, such as intrinsic curiosity module (ICM), random network distillation (RND) and rew…

$ npx skills add RLE-Foundation/RLeXplore

465 stars37 quality73 trustExperimentalClaude Code1y since pushNeeds review

QualityInspect the repository carefully before adding it to an agent workflow.Check: Repository looks stale

TrustGood trust signals with a few areas worth checking before rollout.Review: Repository looks stale

Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario GitHub automation · I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

Claude Code + CLI · 4 targets

jupyter-notebookrobotics

by RLE-FoundationDetailsQuick view

Nix Tts

PROMISING · 63TRUST · 77SAFE · REVIEWEDCODING

🐤 Nix-TTS: Lightweight and End-to-end Text-to-Speech via Module-wise Distillation

$ npx skills add rendchevi/nix-tts

265 stars40 quality77 trustReviewed with permission notesClaude Code8mo since pushNeeds review

QualityUseful candidate, but compare it with alternatives before adopting.

TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review

Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

Claude Code + CLI · 4 targets

pythonvoice

by rendcheviDetailsQuick view

Page 1

Showing the strongest 16 results to keep the registry fast for humans and agents. Refine by use case, platform, stars, or search query for a narrower shortlist.

Try the agent resolve API

AI Agent Skills Directory

Real skills, grouped by the work your agent needs to finish.

Build the registry by domain, not just by count.

Coding and developer agents

Research and knowledge work

Presentation and deck workflows

Finance and quant workflows

Marketing and growth automation

Design and creative production

Data, BI, and analytics

Legal, policy, and compliance

Education and tutoring

Football and World Cup analytics

Start from the task, not a keyword list.

Choose by scenario, quality, and trust signals.

Revisiting Reverse Distillation

Stagewise Knowledge Distillation

Mtt Distillation

Awesome Human Distillation

Knowledge Distillation Pytorch

Lightly Train

Causal Forcing

Rcm

Mdistiller

EdgeCrafter

WaDi

Annotated Deep Learning Paper Implementations

Diffusion Distiller

Efficientsam3

RLeXplore

Nix Tts