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
54,221 results · page 309 of 1,808
- View details
sigma_ingestSkillDocs & knowledge
Lets your agent pull documented data model and workbook knowledge from staged Sigma specs into a wiki.
Ready to connect★ 2k
- View details
slSkillMonitoring & ops
Lets your agent query pre-defined business metrics like ARR, churn, retention, LTV, and MAU from a semantic layer.
Ready to connect★ 2k
- View details
sl_captureSkillDocs & knowledge
Teaches your agent how to add reusable measures, segments, and joins to a shared data catalog.
Ready to connect★ 2k
- View details
wiki_captureSkillDocs & knowledge
Lets your agent store durable business knowledge like preferences, metric definitions, and conventions in a wiki.
Ready to connect★ 2k
- View details
adjudicate-reviewSkillAI & models
Lets your agent check reviewer findings against the source before applying fixes so wrong suggestions don't corrupt correct work.
Ready to connect★ 2k
- View details
audit-reproducibilitySkillAI & models
Lets your agent check that numbers in a research paper match the actual R, Stata, or Python analysis outputs.
Ready to connect★ 2k
- View details
blast-radiusSkillFiles & storage
Lets your agent find and test every consumer of shared code before and after you change it.
Ready to connect★ 2k
- View details
capture-environmentSkillAI & models
Lets your agent snapshot a research coding environment and generate lockfiles so results can be replicated.
Ready to connect★ 2k
- View details
checkpointSkillFiles & storage
Lets your agent save a snapshot of its current work so it can resume or hand off later.
Ready to connect★ 2k
- View details
coauthor-briefSkillDocs & knowledge
Lets your agent generate a handoff brief summarizing project changes, current state, open questions, and setup steps for collaborators.
Ready to connect★ 2k
- View details
compile-latexSkillFiles & storage
Lets your agent compile a LaTeX slide deck into a PDF using XeLaTeX and BibTeX.
Ready to connect★ 2k
- View details
compress-sessionSkillFiles & storage
Lets your agent save a structured summary of the current conversation, including decisions and next actions, before it gets compressed.
Ready to connect★ 2k
- View details
context-statusSkillAI & models
Lets your agent check how much context has been used and whether auto-compact is approaching.
Ready to connect★ 2k
- View details
create-lectureSkillFiles & storage
Lets your agent generate a new Beamer lecture .tex file from papers with consistent notation.
Ready to connect★ 2k
- View details
credible-claimsSkillProductivity
Gives your agent a disciplined way to write research briefs and record evidence for claims.
Ready to connect★ 2k
- View details
data-analysisSkillDatabases & data
Lets your agent explore and clean datasets, run regressions, and produce summary tables and figures in R.
Ready to connect★ 2k
- View details
data-management-planSkillFiles & storage
Lets your agent draft a funder-compliant data management plan covering data description, storage, sharing, and archiving.
Ready to connect★ 2k
- View details
deep-auditSkillAI & models
Lets your agent stress-test a proof, paper, codebase, or set of claims by finding and fixing concrete defects.
Ready to connect★ 2k
- View details
deploySkillDocs & knowledge
Render Quarto `.qmd` slides to HTML and sync to `docs/` for GitHub Pages. Use when user says "deploy", "publish the slides", "ship to pages", "push the lecture live", "render and publish", or after Quarto edits that need to go public. NOT for local Quarto render only — use `quarto render` directly f
Ready to connect★ 2k
- View details
devils-advocateSkillDocs & knowledge
Lets your agent challenge your slides with 5-7 critical questions about ordering, prerequisites, and cognitive load.
Ready to connect★ 2k
- View details
differential-auditSkillAI & models
Lets your agent rigorously compare two implementations of the same task, like a code port or refactor, to verify they produce matching results.
Ready to connect★ 2k
- View details
disclosure-checkSkillMonitoring & ops
Lets your agent screen analysis outputs built on confidential data for disclosure risks like small cells, dominance, and PII.
Ready to connect★ 2k
- View details
extract-tikzSkillDocs & knowledge
Lets your agent pull TikZ diagrams out of Beamer slides and convert them into standalone SVG files.
Ready to connect★ 2k
- View details
mex-inboxSkillDocs & knowledge
Lets your agent draft additions or corrections to shared project knowledge for team review.
Ready to connect★ 2k
- View details
mex-relaySkillDocs & knowledge
Lets your agent prepare and manage handoff notes so a teammate can pick up work later.
Ready to connect★ 2k
- View details
new-diagramSkillAI & models
Lets your agent create TikZ diagrams from templates and refine them until they pass review.
Ready to connect★ 2k
- View details
new-skillSkillAI & models
Lets your agent create a new skill file that follows the repo's template and conventions.
Ready to connect★ 2k
- View details
oracle-reviewSkillAI & models
Lets your agent send a paper, proof, or replication package to an external AI model for an independent review.
Ready to connect★ 2k
- View details
pedagogy-reviewSkillAI & models
Lets your agent review a lecture deck for teaching quality, checking flow, examples, and pacing.
Ready to connect★ 2k
- View details
permission-checkSkillFiles & storage
Lets your agent diagnose why Claude Code is or isn't asking for permission before running commands.
Ready to connect★ 2k
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.
53,789 of the 54,221 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.