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
55,055 results · page 714 of 1,836
- View details
data-quality-checkSkillDev tools
Lets your agent check a dataset for missing values, duplicates, and coverage gaps before analysis.
Ready to connect★ 299
- View details
datasetsSkillDatabases & data
Lets your agent list all connected datasets with status, table counts, and last analysis date.
Ready to connect★ 299
- View details
distribution-profilerSkillDev tools
Lets your agent analyze a data column's statistical distribution and get recommended tests, stats, and A/B guidance.
Ready to connect★ 299
- View details
evaluate-graderSkillAI & models
Lets your agent compare a model grader against human labels and inspect disagreements, bias, and scoring stability.
Ready to connect★ 299
- View details
experiment-briefSkillDev tools
Lets your agent draft a structured brief for an experiment or A/B test when you mention wanting to test something.
Ready to connect★ 299
- View details
forecastSkillMonitoring & ops
Lets your agent generate time-series forecasts of metrics like revenue or DAU with seasonality detection and confidence intervals.
Ready to connect★ 299
- View details
google-doc-exportSkillMedia
Lets your agent create well-formatted Google Docs with headings, charts, and images without layout issues.
Ready to connect★ 299
- View details
google-slides-exportSkillDocs & knowledge
Lets your agent build neatly formatted Google Slides presentations without common API errors.
Ready to connect★ 299
- View details
guardrailsSkillDocs & knowledge
Makes your agent pair every success metric with guardrail metrics and check for trade-offs before calling improvements wins.
Ready to connect★ 299
- View details
historySkillSearch
Lets your agent search and browse your past analyses from an archive.
Ready to connect★ 299
- View details
improve-contextSkillDev tools
Lets your agent diagnose context problems in analyses, test small fixes, and report whether to keep or undo them.
Ready to connect★ 299
- View details
ioaSkillCommunication
Lets your agent send and read messages in shared spaces to coordinate with other AI agents.
Ready to connect★ 299
- View details
knowledge-bootstrapSkillDatabases & data
Lets your agent set up session context by loading instructions and listing available data at the start of a session.
Ready to connect★ 299
- View details
log-correctionSkillMonitoring & ops
Lets your agent remember your corrections and rules so future analyses don't repeat the same mistake.
Ready to connect★ 299
- View details
metric-specSkillDocs & knowledge
Lets your agent write complete, unambiguous metric definitions covering formulas, filters, and guardrails.
Ready to connect★ 299
- View details
metricsSkillSearch
Lets your agent look up, search, and explain metric definitions like formulas and validation status for your dataset.
Ready to connect★ 299
- View details
monitor-evalsSkillMonitoring & ops
Lets your agent review AI evaluation history to find regressions and decide whether to continue, investigate, or roll back.
Ready to connect★ 299
- View details
patternsSkillSearch
Lets your agent browse and search recurring patterns found across past data analyses.
Ready to connect★ 299
- View details
question-framingSkillMonitoring & ops
Helps your agent turn vague analytical questions into a structured plan with goals, metrics, and hypotheses before any data work.
Ready to connect★ 299
- View details
question-routerSkillMonitoring & ops
Lets your agent classify data questions by complexity and route them to the right analysis path, from quick lookups to full investigations.
Ready to connect★ 299
- View details
reliabilitySkillDatabases & data
Lets your agent run one analytics task through several trials to measure how consistent the results are.
Ready to connect★ 299
- View details
resume-pipelineSkillDev tools
Lets your agent restart a previously interrupted analysis from its saved local artifacts and state.
Ready to connect★ 299
- View details
run-pipelineSkillDev tools
Lets your agent plan and run multi-step analysis workflows where separate workers produce and hand off files automatically.
Ready to connect★ 299
- View details
runsSkillDev tools
Lets your agent browse, inspect, compare, and clean up past analysis pipeline runs.
Ready to connect★ 299
- View details
score-analysisSkillDev tools
Lets your agent score one analysis against separate evidence checks and recommend act, investigate, abstain, or incomplete.
Ready to connect★ 299
- View details
setup-dev-contextSkillDatabases & data
Guides your agent through an interview to record your team's database, schema, and SQL conventions in a config file.
Ready to connect★ 299
- View details
setup-slackSkillWeb & browsing
Lets your agent connect your own Slack account, verify the workspace and channel, and post one previewed message after your approval.
Ready to connect★ 299
- View details
srm-checkSkillDev tools
Lets your agent check whether an A/B test's treatment and control groups are properly randomized before trusting the results.
Ready to connect★ 299
- View details
stress-testSkillMedia
Lets your agent review an analysis plan for methodological flaws like bad baselines and survivorship bias before you run it.
Ready to connect★ 299
- View details
switch-datasetSkillDatabases & data
Lets your agent switch the active dataset to a different data source for analysis.
Ready to connect★ 299
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.