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
70,704 results · page 1619 of 2,357
- View details
seed-vig-skillSkillDatabases & data
Lets your agent run a full fatigue detection workflow on the SEED-VIG EEG dataset, from validation to classification.
Ready to connect★ 91
- View details
self-media-compliance-reviewSkillMedia
Lets your agent check videos, scripts, subtitles, and posts for platform rule violations before publishing.
Ready to connect★ 87
- View details
set-profileSkillAI & models
Lets your agent switch the model profile for GSD agents between quality, balanced, budget, or inherit.
Ready to connect★ 91
- View details
settingsSkillAI & models
Lets your agent change workflow settings and pick which AI model profile to use.
Ready to connect★ 91
- View details
setup-weaverse-projectSkillCommerce & finance
Lets your agent set up a Weaverse Hydrogen storefront locally and connect it to your Shopify store.
Ready to connect★ 91
- View details
shopify-hydrogenSkillDatabases & data
Lets your agent use a shopify claude skill covering Hydrogen cart, caching, SEO, and analytics APIs.
Ready to connect★ 91
- View details
skill-updaterSkillFiles & storage
Lets your agent turn a successful task into suggested updates to its own skill files, shown as diffs for your approval.
Ready to connect★ 91
- View details
skilladam-optimizeSkillAI & models
Lets your agent test, improve, and iteratively optimize an existing Agent Skill from a usage description.
Ready to connect★ 91
- View details
smri-skillSkillDev tools
Lets your agent process structural MRI brain scans: segmentation, registration, parcellation, thickness and volume analysis.
Ready to connect★ 91
- View details
spacenetSkillAI & models
Lets your agent classify patients vs controls from brain scans using a sparse, interpretable machine learning model.
Ready to connect★ 91
- View details
spec-phaseSkillDev tools
Helps your agent turn a vague feature idea into a clear written spec with testable requirements before coding starts.
Ready to connect★ 91
- View details
stabilizer-backend-changeSkillMedia
Guides your agent when editing video stabilization code like motion estimation or OpenCV backend selection.
Ready to connect★ 91
- View details
statistical-mlSkillAI & models
Lets your agent run logistic regression, mixed-effects models, and XGBoost on tabular CSV data.
Ready to connect★ 91
- View details
subject-subtypingSkillAI & models
Lets your agent run disease subtyping by clustering patients from neuroimaging features using K-means, GMM, NMF and more.
Ready to connect★ 91
- View details
super-boardSkillDev tools
GitHub-Project-driven autonomous pipeline. Five verbs — onboard, lint, status, run, stop — that take a Project board from empty to drained across Build → QA → Review → Done lanes (labels qa · bug · feature route each card), with graceful shutdown / resume. Use when the user says "super-board", "/sup
Ready to connect★ 91
- View details
super-buildSkillDev tools
Builder lane of the super-board pipeline — takes a `Ready` GitHub Project card into its own per-issue git worktree, makes the smallest safe change test-first (TDD, `ponytail` simplest-first, official docs first for third-party APIs, upgrades and auth/billing), opens a draft PR and hands it to QA and
Ready to connect★ 91
- View details
super-collectSkillFiles & storage
Find problems in one project and file them as tickets into its super-board Backlog — the board fixes them. Source plug-ins - sentry (app errors), posthog (exceptions, rage/dead clicks, failure events, web vitals, tracking gaps), github (issues not on the board), prs (recurring problems in merged PRs
Ready to connect★ 91
- View details
super-qaSkillWeb & browsing
Super QA canonical workflow for functional bug-bash, evidence capture, and fix-ready issue filing. Crawls routes from `docs/super-qa/queue.md` with Playwright, records screenshots/logs/HARs, files product-readable issues with clear type/priority/area labels, and continues until traversal is complete
Ready to connect★ 91
- View details
super-reviewSkillFiles & storage
Reviewer lane of the super-board pipeline and standalone PR/branch readiness review — forms its own hypotheses before reading the builder's summary, remembers prior findings and re-checks each with file:line proof, runs an adversarial truth-check on non-trivial diffs, and classes every finding (Gap,
Ready to connect★ 91
- View details
survival-modelsSkillAI & models
Lets your agent train survival models like Cox and DeepSurv on time-to-event data with censored outcomes.
Ready to connect★ 91
- View details
synthesize-agent-memory-landscapeSkillDocs & knowledge
Lets your agent write or update a cross-system memory landscape report from an existing review corpus.
Ready to connect★ 91
- View details
tcp-skillSkillDatabases & data
Lets your agent run a full processing pipeline for the Transdiagnostic Connectome Project brain imaging dataset.
Ready to connect★ 91
- View details
temporal-modelsSkillAI & models
Lets your agent use a temporal claude skill to train LSTM, GRU, TCN, or Transformer models on time-series data.
Ready to connect★ 91
- View details
theme-updateSkillCommerce & finance
Updates your Weaverse Pilot theme to the latest version while preserving your customizations and verifying the build.
Ready to connect★ 91
- View details
threadSkillDev tools
Lets your agent keep persistent context threads so work continues across sessions.
Ready to connect★ 91
- View details
ucla-cnp-skillSkillDatabases & data
Lets your agent run a full processing pipeline on the UCLA CNP brain imaging dataset, from validation to quality checks.
Ready to connect★ 91
- View details
ui-phaseSkillMedia
Lets your agent write a UI design specification document for frontend development phases.
Ready to connect★ 91
- View details
ui-refine-loopSkillFiles & storage
Unattended Impeccable check → fix loop on one page or component. It reads the target's code, grills Eric (at most 10 questions, "you pick" welcome) into a per-project taste and direction file, then runs bounded rounds. Each round a fresh checker runs Impeccable critique and audit (design review and
Ready to connect★ 91
- View details
ukb-skillSkillDev tools
Lets your agent run statistical and machine learning analyses on UK Biobank brain research data you already have.
Ready to connect★ 91
- View details
ultraplan-phaseSkillWeb & browsing
Lets your agent draft plans in the cloud while your terminal stays free, then review and import them back.
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.
68,574 of the 70,704 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.