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 1441 of 2,169
- View details
hylo-quote-extractSkillDocs & knowledge
Lets your agent pull key verbatim quotes from a Hylo note and save each as a short note linked back to the source.
Ready to connect★ 89
- View details
hylo-recapSkillDocs & knowledge
Lets your agent compare a note or draft against your Hylo knowledge base to find related and conflicting ideas.
Ready to connect★ 89
- View details
hylo-writingSkillDocs & knowledge
Lets your agent write an article beat by beat from your knowledge base, checking each step with you.
Ready to connect★ 89
- View details
hyper-cliSkillAI & models
Lets your agent run Hyper marketing tools from a terminal, including inspecting tool schemas and switching accounts.
Ready to connect★ 92
- View details
issue-intakeSkillDev tools
Lets your agent turn a messy inbound request into a structured intake document with a defined next step.
Ready to connect★ 93
- View details
json-outputSkillDev tools
Lets your agent turn its inputs into a JSON object using the cli-tool adapter.
Ready to connect★ 93
- View details
knowledge-routerSkillDev tools
Lets your agent route a question through a knowledge catalog to find the right source, owner, and follow-up.
Ready to connect★ 93
- View details
lead-routerSkillDev tools
Lets your agent sort a validated lead into outreach, nurture, or hold, and record why that choice was made.
Ready to connect★ 93
- View details
least-privilegeSkillDev tools
Lets your agent check permission evidence against granted scopes and propose the narrowest access grant that fits.
Ready to connect★ 93
- View details
ledgerSkillDev tools
Lets your agent search a receipt ledger and verify the receipt chain to answer audit questions.
Ready to connect★ 93
- View details
list-hygiene-judgeSkillDev tools
Lets your agent decide and record safe contact-consent changes using engagement, bounce, and consent evidence before sending emails.
Ready to connect★ 93
- View details
loop-operator-contextSkillDev tools
Lets your agent load advisory operating context for the loop claude skill example.
Ready to connect★ 93
- View details
loop-orchestrationSkillDev tools
Lets your agent run a loop claude skill that chains governed turns with budgets, receipts, and stop rules.
Ready to connect★ 93
- View details
macos-controlSkillMedia
Lets your agent control Mac apps by clicking buttons, typing text, scrolling, taking screenshots, and running AppleScript.
Ready to connect★ 94
- View details
managed-agent-intakeSkillProductivity
Lets your agent draft a governed triage summary for incoming agent tasks.
Ready to connect★ 93
- View details
marketplace-invokeSkillDev tools
Lets your agent invoke a marketplace Claude skill resource through an approved adapter and get receipt-backed confirmation.
Ready to connect★ 93
- View details
mcp-approval-graphSkillDev tools
Lets your agent practice a graph approval round trip served by a Rust tool.
Ready to connect★ 93
- View details
mcp-echoSkillCommunication
Lets your agent echo a message back as a simple test of local server connectivity.
Ready to connect★ 93
- View details
meeting-followupSkillCommunication
Turns a meeting transcript into decisions, action items, and draft follow-up tasks.
Ready to connect★ 93
- View details
meta-ads-librarySkillWeb & browsing
Lets your agent research competitor Facebook and Instagram ads from the Meta Ads Library by keyword.
Ready to connect★ 92
- View details
mock-chargeSkillDev tools
Lets your agent create simulated local provider charges for repeatable test runs.
Ready to connect★ 93
- View details
mock-paySkillCommerce & finance
Lets your agent simulate a payment locally so tests run predictably without sending real money.
Ready to connect★ 93
- View details
mock-refundSkillDev tools
Lets your agent simulate a refund locally so tests run deterministically.
Ready to connect★ 93
- View details
monte-carlo-analyze-root-causeSkillDatabases & data
Lets your agent investigate data incidents and trace root causes using Monte Carlo observability data.
Ready to connect★ 92
- View details
monte-carlo-asset-healthSkillAI & models
Lets your agent check the health and status of a data table using Monte Carlo.
Ready to connect★ 92
- View details
monte-carlo-context-detectionSkillMonitoring & ops
Lets your agent route data quality questions and alerts to the right Monte Carlo workflow.
Ready to connect★ 92
- View details
monte-carlo-incident-responseSkillMonitoring & ops
Lets your agent triage and fix data incidents, finding root causes and preventing repeat failures.
Ready to connect★ 92
- View details
monte-carlo-instrument-agentSkillFiles & storage
Sets up tracing for your AI agent in a Python codebase, proposing edits as diffs and asking before changing files.
Ready to connect★ 92
- View details
monte-carlo-manage-macSkillFiles & storage
Lets your agent create, edit, validate, and import Monte Carlo monitor YAML files as code.
Ready to connect★ 92
- View details
monte-carlo-monitoring-advisorSkillMonitoring & ops
Helps your agent analyze which data tables lack monitoring and set up data-quality checks.
Ready to connect★ 92
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.