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
9,105 results · page 185 of 304
- View details
completion-gateSkillAI & models
Validates agent claims against evidence trail. Use when verifying an agent has actually done what it claims — auto-fires at workflow end. Catches 'done' without proof, 'tests pass' without output, 'fixed' without verification. Called by cook and team.
Ready to connect★ 86
- View details
compliance-reviewSkillAI & models
Use this skill at Step 10 of the v2 SOP, executed by the Compliance-Agent (whose backing model must be heterogeneous from the main orchestrator), to produce a COMPLIANCE_REPORT.md for a change that has passed functional Verify and code review. Audits PHI handling, prompt-injection surface, model-cal
Ready to connect★ 86
- View details
cursor-webhooksSkillAI & models
Receive and verify Cursor Cloud Agent webhooks. Use when setting up Cursor webhook handlers, debugging signature verification, or handling Cloud Agent status change events (ERROR, FINISHED).
Ready to connect★ 85
- View details
openai-webhooksSkillAI & models
Receive and verify OpenAI webhooks. Use when setting up OpenAI webhook handlers for fine-tuning jobs, batch completions, or async events like fine_tuning.job.completed, batch.completed, or realtime.call.incoming.
Ready to connect★ 85
- View details
openclaw-webhooksSkillAI & models
Receive and verify OpenClaw Gateway webhooks. Use when handling webhook events from OpenClaw AI agents, processing agent hook calls, wake events, or building integrations that respond to OpenClaw agent activity.
Ready to connect★ 85
- View details
problem-solverSkillAI & models
Structured reasoning frameworks for complex problems. 19 analytical frameworks, 12 cognitive bias detectors, 10 decomposition methods, 10 mental models, Cynefin domain classification, ethical dimension check, and 6 communication patterns. McKinsey-grade problem solving for AI coding assistants.
Ready to connect★ 86
- View details
bntSkillAI & models
Use this model doc whenever the user wants to run BrainNetworkTransformer for fMRI phenotype prediction, including data loading, training, and evaluation. BNT uses dense FC matrices (no PyG dependency) with DEC pooling + interpretable transformer encoder.
Ready to connect★ 85
- View details
brainnetcnnSkillAI & models
Use this model skill whenever the user wants to train, evaluate, or apply BrainNetCNN to dense ROI-by-ROI structural or functional connectivity matrices for neuroimaging classification or regression. Triggers include 'BrainNetCNN', 'edge-to-edge convolution', 'connectome CNN', 'FC matrix CNN', 'brai
Ready to connect★ 85
- View details
causal-treatment-modelsSkillAI & models
Use this skill whenever the scientific target is a treatment effect rather than ordinary outcome prediction: propensity weighting, S/T/X learners, doubly robust learning, policy learning, causal forests, TARNet, DragonNet, CATE estimation, heterogeneous treatment effects, and individualized treatmen
Ready to connect★ 85
- View details
combraintfSkillAI & models
Use this model doc whenever the user wants to run Com-BrainTF (Community-aware Brain Transformer) for fMRI phenotype prediction. Com-BrainTF uses dense FC matrices with a two-level Transformer (per-community local + global) and DEC pooling. NeuroClaw auto-derives community partitions from atlas nami
Ready to connect★ 85
- View details
conda-env-managerSkillAI & models
Use this skill whenever the user wants to create, activate, list, export, update, clone, remove, or otherwise manage conda environments, or when a deep-learning / model skill requires a clean, isolated conda environment (e.g. 'create conda env for torch 2.3 cuda', 'export current env to yml', 'list
Ready to connect★ 85
- View details
connectome-discoverySkillAI & models
Use this workflow skill whenever the user wants to turn connectome-model outputs into network discoveries: compare aligned brain maps, compute permutation significance, rank neuromodulation targets, summarize atlas-level effects, or combine CPM with spatial interpretation. Triggers include 'connecto
Ready to connect★ 85
- View details
cpmSkillAI & models
Use this model skill whenever the user wants Connectome Predictive Modeling with fold-local functional-connectivity edge selection for classification or regression. Triggers include 'CPM', 'connectome predictive modeling', 'functional connectivity prediction', 'positive network', 'negative network',
Ready to connect★ 85
- View details
define-rubricSkillAI & models
Builds measurable validation criteria when no existing standards apply. Invoked by team agents during review.
Ready to connect★ 85
- View details
dependency-plannerSkillAI & models
Use this skill whenever a NeuroClaw skill, model, or sub-agent reports a missing dependency (e.g. ImportError, ModuleNotFoundError, command not found), or when the user explicitly requests to install, setup, configure, or fix any library, package, compiler, CUDA toolkit, conda environment, system to
Ready to connect★ 85
- View details
dictlearningSkillAI & models
Use this model doc whenever the user wants to perform resting-state network decomposition using DictLearning. This is a non-deep-learning unsupervised route focused on sparse component extraction, network map discovery, and subject-level time series from resting-state fMRI.
Ready to connect★ 85
- View details
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★ 85
- 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★ 85
- 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★ 85
- 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★ 85
- View details
independent-review-loopSkillAI & models
Independent review loop run before delivery in code work. An independent reviewer (Codex, or fresh Codex-style subagents) reads the whole PR against the approved outcome; the lead fixes in-scope functional findings and re-reviews until none remain. Its differentiator is independence and exhaustivene
Ready to connect★ 85
- 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★ 85
- 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★ 85
- 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★ 85
- 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★ 85
- 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★ 85
- 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★ 85
- 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★ 85
- 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★ 85
- 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★ 85
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.
55,111 of the 55,543 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.