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.
Filter by category
65,055 results · page 1451 of 2,169
- View details
harmonization-toolSkillDatabases & data
Lets your agent remove site, scanner, and batch effects from neuroimaging features so datasets can be pooled and compared.
Ready to connect★ 91
- View details
harness-coreSkillMonitoring & ops
Lets your agent's skills share one Python library for validation, checkpoints, drift detection, and audit logging.
Ready to connect★ 91
- View details
hbn-skillSkillDatabases & data
Lets your agent download the Healthy Brain Network dataset and organize its MRI and EEG scans into BIDS format.
Ready to connect★ 91
- View details
hcpa-skillSkillDatabases & data
Lets your agent download the HCP Aging brain imaging dataset and run structural, functional, and diffusion MRI processing.
Ready to connect★ 91
- View details
hcpd-skillSkillDatabases & data
Lets your agent download the HCP Development brain imaging dataset, organize it into BIDS, and run structural, functional, and diffusion MRI processing.
Ready to connect★ 91
- View details
hcpep-skillSkillDatabases & data
Lets your agent download and process the HCP Early Psychosis dataset, organizing it into BIDS and running MRI pipelines.
Ready to connect★ 91
- View details
hcppipeline-toolSkillDev tools
Lets your agent run official Human Connectome Project preprocessing pipelines on structural, functional, and diffusion MRI data.
Ready to connect★ 91
- View details
hcpya-skillSkillDatabases & data
Lets your agent download and process HCP Young Adult brain imaging data, organizing it and running structural, functional, and diffusion MRI pipelines.
Ready to connect★ 91
- View details
hermes-skill-factorySkillDev tools
Use when you want to auto-generate reusable skills from repeated workflows. Watches your Hermes sessions, detects patterns, and proposes SKILL.md + plugin.py pairs on demand.
Ready to connect★ 91
- View details
hermesoneSkillDev tools
Install, update, and manage the Hermes One desktop app via the `hermesone` npm package. Use when a user wants to set up Hermes One, install or upgrade it from the command line, check the installed version, preview a release before installing, pin a specific version, or drive the installer programmat
Ready to connect★ 91
- View details
hierarchicalSkillAI & models
Lets your agent run hierarchical clustering to split brain imaging data into data-driven regions for parcellation.
Ready to connect★ 91
- View details
iam-recommendations-fetcherSkillSecurity
Fetches raw IAM recommendations and associated security insights from Google Cloud for a specified target scope (Organization, Folder, or Project). Use when you need to retrieve security recommendations before analyzing or applying them. Don't use for applying/acting on recommendations (use the reco
Ready to connect★ 91
- View details
ibgnnSkillCommunication
Lets your agent train and run a brain-imaging neural network that predicts traits like age or disorder from fMRI data.
Ready to connect★ 91
- View details
icaSkillAI & models
Lets your agent run ICA decomposition on resting-state fMRI to find brain networks, component maps, and time series.
Ready to connect★ 91
- View details
ima-sdk-basicsSkillWeb & browsing
Use this skill for Interactive Media Ads (IMA) SDK client-side ad insertion when you are requesting video ads client-side into websites, apps, TVs or other platforms with VAST or VMAP. Do not use for Dynamic Ad Insertion (DAI), SSAI, or SGAI (use the `ima-sdk-dai-basics` skill instead).
Ready to connect★ 91
- View details
imaging-genetics-modelsSkillProductivity
Lets your agent run imaging-genetics analyses like GWAS-style variant association, kinship-aware models, and polygenic scores.
Ready to connect★ 91
- View details
ingest-docsSkillDev tools
Lets your agent scan a repo's docs and build a consolidated planning setup, flagging conflicts between them.
Ready to connect★ 91
- View details
intelSkillFiles & storage
Lets your agent query, inspect, or refresh codebase intelligence files stored in .planning/intel/.
Ready to connect★ 91
- View details
ipswSkillDev tools
Lets your agent analyze Apple firmware files and binary images using the ipsw command-line tool.
Ready to connect★ 90
- View details
ixi-skillSkillDatabases & data
Lets your agent download and process the IXI MRI dataset, organizing scans into BIDS format.
Ready to connect★ 91
- View details
jiaojieSkillProductivity
Lets your agent create or resume saved handoff packages so work can continue in another chat, model, or device.
Ready to connect★ 90
- View details
kanban-codex-laneSkillProductivity
Use when a Hermes Kanban worker wants to run Codex CLI as an isolated implementation lane while Hermes keeps ownership of task lifecycle, reconciliation, testing, and handoff.
Ready to connect★ 91
- View details
kanban-orchestratorSkillAI & models
Decomposition playbook + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orc
Ready to connect★ 91
- View details
kanban-workerSkillAI & models
Pitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.
Ready to connect★ 91
- View details
kg-link-predictionSkillAI & models
Lets your agent train knowledge graph embeddings and predict missing links in a graph using models like ComplEx, R-GCN, GraphSAGE, and GAT.
Ready to connect★ 91
- View details
knowledge-graph-builderSkillDatabases & data
Lets your agent build knowledge graph structures from scientific papers and databases, then find hidden connections and research gaps.
Ready to connect★ 91
- View details
lggnnSkillAI & models
Lets your agent train the LG-GNN graph neural network to predict phenotypes like gender or age from fMRI brain graphs.
Ready to connect★ 91
- View details
macos-computer-useSkillAI & models
Drive the macOS desktop in the background — screenshots, mouse, keyboard, scroll, drag — without stealing the user's cursor, keyboard focus, or Space. Works with any tool-capable model. Load this skill whenever the `computer_use` tool is available.
Ready to connect★ 91
- View details
mcp-clientSkillFiles & storage
Lets your agent connect to external tool servers, list their available tools, and call them on demand.
Ready to connect★ 91
- View details
meg-skillSkillDev tools
Lets your agent process MEG brain-imaging data: preprocessing, time-frequency analysis, connectivity, and source localization.
Ready to connect★ 91
Popular skills lists
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
- Best Claude skills for superpowers
- Best Claude skills for obsidian
- Best Claude skills for frontend design
- All best lists
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.
62,835 of the 65,055 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 workspace 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.