Skills.

Give your AI a better way to work.

A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.

Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.

Category: AI & models

8,992 results · page 178 of 300

  • experiment-controllerSkillAI & models

    Use this skill whenever the user wants to execute experiments based on a finalized method and record results. Triggers include: 'run experiment', 'experiment controller', 'implement experiment', 'run model', 'execute training', 'experiment-controller', 'record results', 'ablation study', or any requ

    Ready to connect★ 89

    github.com/cuhk-aim-group/neuroclaw83 stars

    View details
  • filteringSkillAI & models

    Use this model doc whenever the user wants to perform neuroimaging signal denoising with classical temporal filtering methods. This is a non-deep-learning preprocessing route focused on temporal cleaning, frequency selection, and preparation of cleaner time series for downstream analysis.

    Ready to connect★ 89

    github.com/cuhk-aim-group/neuroclaw83 stars

    View details
  • gpt-5-6-best-practiceSkillAI & models

    Route GPT-5.6 tiers, reasoning effort, and subagents to minimize accepted-result cost subject to an explicit quality floor.

    Ready to connect★ 88

    github.com/wquguru/skills89 stars

    View details
  • hierarchicalSkillAI & models

    Use this model doc whenever the user wants to perform brain parcellation using Hierarchical clustering. This is a non-deep-learning unsupervised route focused on multi-scale parcel discovery, voxel or vertex grouping, and atlas-like region generation from neuroimaging features.

    Ready to connect★ 89

    github.com/cuhk-aim-group/neuroclaw83 stars

    View details
  • hyper-cliSkillAI & models

    Use the Hyper CLI to run Hyper marketing skills from a terminal. Use when the user wants to use `hyperai`, inspect live tool schemas, run a tool by its canonical name, switch connected accounts, or run marketing tools outside an MCP-native agent host.

    Ready to connect★ 89

    github.com/hyperfx-ai/marketing-skills89 stars

    View details
  • icaSkillAI & models

    Use this model doc whenever the user wants to perform resting-state network decomposition using ICA. This is a non-deep-learning unsupervised route focused on extracting intrinsic connectivity networks, component maps, and subject-level time series from resting-state fMRI.

    Ready to connect★ 89

    github.com/cuhk-aim-group/neuroclaw83 stars

    View details
  • improve-codebase-architectureSkillAI & models

    Use when reviewing PlainTab architecture, looking for refactoring opportunities, reducing coupling, improving testability, or making modules easier for agents to understand without redesigning stable behavior.

    Ready to connect★ 89

    github.com/kaininx/plaintab88 stars

    View details
  • kg-link-predictionSkillAI & models

    Use this skill whenever the user wants knowledge-graph embeddings or graph neural link prediction over NeuroOracle: ComplEx, R-GCN, GraphSAGE, or GAT encoders; relation-aware triple scoring; filtered MRR/Hits evaluation; or hypothesis plausibility features. Triggers include 'KG embedding', 'link pre

    Ready to connect★ 89

    github.com/cuhk-aim-group/neuroclaw83 stars

    View details
  • lggnnSkillAI & models

    Use this model doc whenever the user wants to run LG-GNN (Local-to-Global GNN) for fMRI phenotype prediction. LG-GNN is a PyG-based GNN with SABP (Self-Attention Brain Pooling) and mutual-information regularization. NeuroClaw adapts the original population-graph version to single-subject brain graph

    Ready to connect★ 89

    github.com/cuhk-aim-group/neuroclaw83 stars

    View details
  • model-interpretabilitySkillAI & models

    Export trained-model attention weights, target-specific Integrated Gradients or Grad-CAM, patient-level feature attributions and spatial NIfTI maps with numerical QA and required-output validation. Use for post-training explanations or attention/attribution maps, not causal effect estimation.

    Ready to connect★ 89

    github.com/cuhk-aim-group/neuroclaw83 stars

    View details
  • neurostormSkillAI & models

    Use this skill whenever the user wants to run the NeuroSTORM multi-model fMRI platform: preprocessing, pretraining (MAE or contrastive), fine-tuning, inference, or benchmarking. It covers 8 built-in models — NeuroSTORM, SwiFT, BrainGNN, BrainNetworkTransformer (BNT), LG-GNN, Com-BrainTF, IBGNN, Brai

    Ready to connect★ 89

    github.com/cuhk-aim-group/neuroclaw83 stars

    View details
  • run_modelsSkillAI & models

    Use this skill whenever the user wants to run phenotype-prediction models, browse model cards, map model inputs/outputs, or choose an execution route for fMRI/sMRI based models. This is a model-entry orchestration skill: it routes requests to model-specific docs and delegates preprocessing to modali

    Ready to connect★ 89

    github.com/cuhk-aim-group/neuroclaw83 stars

    View details
  • spacenetSkillAI & models

    Use this model doc whenever the user wants to perform disease classification with SpaceNet. This is a non-deep-learning supervised route focused on voxel-wise neuroimaging-based case-control prediction with sparse and interpretable weight maps.

    Ready to connect★ 89

    github.com/cuhk-aim-group/neuroclaw83 stars

    View details
  • statistical-mlSkillAI & models

    Use this skill whenever the user needs classical statistical inference or tabular machine learning for neuroimaging-derived features: OLS/GLM, Cohen's d, logistic regression, Ridge, Elastic Net, SVM/SVR, XGBoost, mixed-effects models, site-aware cross-validation, or imaging-by-treatment interactions

    Ready to connect★ 89

    github.com/cuhk-aim-group/neuroclaw83 stars

    View details
  • subject-subtypingSkillAI & models

    Use this skill whenever the user wants unsupervised disease subtyping, patient stratification, latent phenotype discovery, cluster stability analysis, or low-dimensional embeddings from neuroimaging features. It supports K-means, Gaussian mixture models, spectral clustering, NMF, consensus clusterin

    Ready to connect★ 89

    github.com/cuhk-aim-group/neuroclaw83 stars

    View details
  • survival-modelsSkillAI & models

    Use this skill whenever the outcome is right-censored time-to-event data, including progression, conversion, relapse, hospitalization, or mortality prediction. It supports Cox proportional hazards, Random Survival Forest, DeepSurv, and XGBoost Cox survival with censor-aware cross-validation. Trigger

    Ready to connect★ 89

    github.com/cuhk-aim-group/neuroclaw83 stars

    View details
  • temporal-modelsSkillAI & models

    Use this skill whenever the input contains ordered repeated measurements, longitudinal visits, ROI time series, dynamic connectivity features, or variable-length sequences. It supports LSTM, GRU, temporal convolutional networks, and temporal Transformers for classification and regression. Triggers i

    Ready to connect★ 89

    github.com/cuhk-aim-group/neuroclaw83 stars

    View details
  • typescript-v6SkillAI & models

    Advanced TypeScript patterns for type-safe, maintainable code using sophisticated type system features. Use when building type-safe APIs, implementing complex domain models, or leveraging TypeScript's advanced type capabilities.

    Ready to connect★ 89

    github.com/blockmatic/basilic89 stars

    View details
  • agent-plugin-evalSkillAI & models

    Audit, score, and compare repositories containing portable Agent Plugins against the official Agent Plugins specification. Use when asked to review a plugin repo, check plugin.json or mcp.json conformance, assess bundled skills and MCP servers, produce an evidence-cited 0–100 plugin scorecard, ident

    Ready to connect★ 88

    github.com/fabricioctelles/skills88 stars

    View details
  • agent-ready-dns-aidSkillAI & models

    Sub-skill: Implement DNS-AID records so agents discover endpoints through DNS. Use SVCB/HTTPS records under _agents namespace with alpn and connection parameters.

    Ready to connect★ 88

    github.com/fabricioctelles/skills88 stars

    View details
  • agent-ready-scan-siteSkillAI & models

    Sub-skill: Scan any URL for agent readiness. Checks 22 standards across 5 categories, returns readiness level (0-5), status of all checks, and fix instructions.

    Ready to connect★ 88

    github.com/fabricioctelles/skills88 stars

    View details
  • code-review-fixSkillAI & models

    Auto-fix issues found by code review in REVIEW.md. Spawns fixer agent, commits each fix atomically, produces REVIEW-FIX.md summary.

    Ready to connect★ 88

    github.com/buildomator/buildomator86 stars

    View details
  • discuss-phaseSkillAI & models

    Gather phase context through adaptive questioning before planning. Use --all to skip area selection and discuss all gray areas interactively. Use --auto to skip interactive questions (Claude picks recommended defaults). Use --chain for interactive discuss followed by automatic plan+execute. Use --po

    Ready to connect★ 88

    github.com/buildomator/buildomator86 stars

    View details
  • geo-optimizationSkillAI & models

    Optimize content for AI-generated responses and LLM citations (ChatGPT, Perplexity, Google AI Overview, Claude, Gemini). Use when the user mentions 'GEO', 'AEO', 'AI SEO', 'LLM optimization', 'citation rate', 'AI visibility', 'optimize for ChatGPT', 'roundup pages', or wants to audit pages for AI di

    Ready to connect★ 88

    github.com/fabricioctelles/skills88 stars

    View details
  • list-phase-assumptionsSkillAI & models

    Surface Claude's assumptions about a phase approach before planning

    Ready to connect★ 88

    github.com/buildomator/buildomator86 stars

    View details
  • profile-userSkillAI & models

    Generate developer behavioral profile and create Claude-discoverable artifacts

    Ready to connect★ 88

    github.com/buildomator/buildomator86 stars

    View details
  • research-innovation-explorerSkillAI & models

    Build literature-grounded research-question candidate landscapes by collecting papers, generating A+B matrices, and dynamically reviewing combinations with traceable evidence, uncertainty, and next checks. Use when an AI agent needs to explore a field, screen research questions, compare paper combin

    Ready to connect★ 88

    github.com/foryourhealth111-pixel/research-innovation-explorer88 stars

    View details
  • set-profileSkillAI & models

    Switch model profile for GSD agents (quality/balanced/budget/inherit)

    Ready to connect★ 88

    github.com/buildomator/buildomator86 stars

    View details
  • settingsSkillAI & models

    Configure GSD workflow toggles and model profile

    Ready to connect★ 88

    github.com/buildomator/buildomator86 stars

    View details
  • skill-evaluationSkillAI & models

    Evaluate any agent skill against a merged framework — Anthropic's Claude Code best practices plus Matt Pocock's writing-great-skills methodology — across 4 axes (Trigger, Structure, Steering, Pruning). Produces an evidence-cited scorecard (0–100), a weighted overall score, and diagnosed failure mode

    Ready to connect★ 88

    github.com/fabricioctelles/skills88 stars

    View details

What is a skill?

A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.

54,624 of the 55,055 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.

Install one and every AI you use gets it

Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.

Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.

See how to connect your AI