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 701 of 1,836
- View details
fill-icmje-coiSkillDocs & knowledge
Lets your agent batch-create ICMJE conflict of interest disclosure forms for each author of a manuscript.
Ready to connect★ 310
- View details
fill-protocolSkillDocs & knowledge
Lets your agent fill institutional Word form templates for research documents while keeping the original formatting intact.
Ready to connect★ 310
- View details
find-cohort-gapSkillDatabases & data
Lets your agent find research gaps in long-term cohort databases and get ranked study topic ideas.
Ready to connect★ 310
- View details
find-journalSkillDev tools
Recommends medical journals for a manuscript, with fit reasons and AI disclosure policies.
Ready to connect★ 310
- View details
fulltext-retrievalSkillDocs & knowledge
Lets your agent batch download open-access research PDFs by DOI and convert them to Markdown for analysis.
Ready to connect★ 310
- View details
generate-codebookSkillDatabases & data
Lets your agent create a codebook describing every variable in a tabular dataset like CSV or Excel.
Ready to connect★ 310
- View details
grant-builderSkillDev tools
Helps your agent draft grant and challenge proposals for radiology and medical AI projects with structured sections.
Ready to connect★ 310
- View details
intake-projectSkillFiles & storage
Lets your agent set up and organize a new radiology research project by classifying it, checking what's missing, and creating starter files.
Ready to connect★ 310
- View details
inversionSkillMedia
Lets your agent question hidden assumptions in a plan by flipping each one and exploring where the opposite could work.
Ready to connect★ 311
- View details
lateralSkillDev tools
Lets your agent apply lateral thinking techniques like provocation and inversion to break out of creative blocks.
Ready to connect★ 311
- View details
lit-syncSkillSearch
Lets your agent sync .bib research references into Zotero and create Obsidian literature notes.
Ready to connect★ 310
- View details
ma-scoutSkillDev tools
Lets your agent find and rank feasible research topics by profiling authors or questions and spotting gaps.
Ready to connect★ 310
- View details
make-figuresSkillDev tools
Lets your agent create publication-ready medical research figures like ROC curves, forest plots, and flow diagrams.
Ready to connect★ 310
- View details
manage-projectSkillFiles & storage
Lets your agent manage medical manuscript projects with structure scaffolding, progress tracking, checklists, and timelines.
Ready to connect★ 310
- View details
manage-refsSkillDocs & knowledge
Lets your agent validate, convert, and quality-check citations and cross-references in medical manuscripts.
Ready to connect★ 310
- View details
meta-analysisSkillSearch
Lets your agent run a systematic medical literature review, from search strategy through screening to statistical synthesis.
Ready to connect★ 310
- View details
mllm-evalSkillMonitoring & ops
Lets your agent design or audit an evaluation harness for testing LLMs on clinical tasks like report generation.
Ready to connect★ 310
- View details
model-cardSkillDatabases & data
Lets your agent draft standard documentation for a medical-imaging model, including a model card, dataset datasheet, and data-quality checks.
Ready to connect★ 310
- View details
model-scaffoldSkillMedia
Lets your agent generate a runnable PyTorch training repo for medical-imaging tasks like segmentation or classification.
Ready to connect★ 310
- View details
model-sourcingSkillFiles & storage
Lets your agent vet and record details of a specific model version, licence, and provenance before using it in a study.
Ready to connect★ 310
- View details
model-validationSkillMedia
Guides your agent to design or audit clinical-validation studies for medical-imaging models.
Ready to connect★ 310
- View details
obsidian-paper-vaultSkillDocs & knowledge
Lets your agent turn a folder of research PDFs into organized Obsidian notes with consistent formatting and cross-links.
Ready to connect★ 310
- View details
pocketmen-with-youSkillMedia
Lets your agent create an animated companion character from two or more of your reference images.
Ready to connect★ 311
- View details
polish-languageSkillDev tools
Lets your agent check medical manuscripts for English style issues like spelling drift, abbreviation reuse, and spacing.
Ready to connect★ 310
- View details
postSkillDev tools
Helps your agent write social posts and replies that avoid the predictable take everyone else already posted.
Ready to connect★ 311
- View details
preprocess-imagingSkillMedia
Lets your agent design and audit medical-imaging data preprocessing like resampling and normalization.
Ready to connect★ 310
- View details
present-paperSkillDocs & knowledge
Lets your agent turn papers or course material into presentation decks with slides and speaker scripts.
Ready to connect★ 310
- View details
profile-imagingSkillDatabases & data
Lets your agent analyze a medical-imaging dataset's spacing, orientations, intensities, and label contents before modeling.
Ready to connect★ 310
- View details
provocationSkillMedia
Lets your agent break creative blocks by proposing deliberately absurd ideas and extracting useful insights from them.
Ready to connect★ 311
- View details
publish-skillSkillAI & models
Lets your agent turn a personal skill into a shareable package with PII, license, and portability checks.
Ready to connect★ 310
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.