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.
Category: AI & models
8,700 results · page 14 of 290
- View details
agent-native-reviewerSkillAI & models
Reviews code to ensure agent-native parity -- any action a user can take, an agent can also take. Use after adding UI features, agent tools, or system prompts.
Ready to connect★ 17k
- View details
autoreviewSkillAI & models
Lets your agent run an automated code review before commits or shipping, using a selectable AI model.
Ready to connect★ 17k
- View details
continueSkillAI & models
Lets your agent pause mid-task to decide whether to continue, pivot, replan, or stop based on progress.
Ready to connect★ 17k
- View details
project-standards-reviewerSkillAI & models
Lets your agent review code changes against your project's own written standards and conventions.
Ready to connect★ 17k
- View details
auto-paper-improvement-loopSkillAI & models
Lets your agent automatically review and revise a generated paper, then recompile it, over two improvement rounds.
Ready to connect★ 16k
- View details
auto-review-loopSkillAI & models
Lets your agent run repeated self-reviews of its research work, fixing issues until they pass a review policy.
Ready to connect★ 16k
- View details
auto-review-loop-llmSkillAI & models
Lets your agent run an autonomous research review loop using any OpenAI-compatible LLM API.
Ready to connect★ 16k
- View details
auto-review-loop-minimaxSkillAI & models
Lets your agent run repeated rounds of automated review of its work using the MiniMax AI model.
Ready to connect★ 16k
- View details
citation-auditSkillAI & models
Lets your agent check that every citation in a paper is real, correctly attributed, and actually supports the claim it backs.
Ready to connect★ 16k
- View details
claims-draftingSkillAI & models
Lets your agent draft patent claims for an invention.
Ready to connect★ 16k
- View details
embodiment-descriptionSkillAI & models
Lets your agent write detailed embodiment sections for patent specifications.
Ready to connect★ 16k
- View details
experiment-auditSkillAI & models
Lets your agent audit experiment results for fake data, score manipulation, and phantom findings before you trust them.
Ready to connect★ 16k
- View details
experiment-planSkillAI & models
Lets your agent turn a research proposal into a detailed experiment roadmap with ablations, run order, and compute budget.
Ready to connect★ 16k
- View details
experiment-queueSkillAI & models
Lets your agent queue and run many ML training experiments in order over SSH, retrying ones that run out of memory.
Ready to connect★ 16k
- View details
figure-descriptionSkillAI & models
Lets your agent write formal descriptions of patent figures, labeling parts with reference numerals.
Ready to connect★ 16k
- View details
figure-specSkillAI & models
Lets your agent turn structured JSON descriptions into clean, editable architecture, workflow, and pipeline diagrams as SVG files.
Ready to connect★ 16k
- View details
grant-proposalSkillAI & models
Lets your agent draft structured grant proposals for funding bodies like NSF, ERC, and KAKENHI from your research ideas.
Ready to connect★ 16k
- View details
idea-creatorSkillAI & models
Lets your agent generate and rank research ideas when you give it a broad research direction.
Ready to connect★ 16k
- View details
idea-discoverySkillAI & models
Lets your agent run a full research pipeline that turns a broad research direction into validated, tested ideas.
Ready to connect★ 16k
- View details
idea-discovery-robotSkillAI & models
Lets your agent survey robotics research and generate simulation-first research ideas with novelty checks.
Ready to connect★ 16k
- View details
integrity-forensicsSkillAI & models
Lets your agent run a forensic integrity sweep on a research paper and turn the verdict into a policy gate.
Ready to connect★ 16k
- View details
interview-cheatsheetSkillAI & models
Lets your agent write a detailed Chinese interview-prep cheat sheet on an ML or LLM topic, with formulas, code, and practice questions.
Ready to connect★ 16k
- View details
invention-structuringSkillAI & models
Turns a rough invention idea into a formal, patent-ready invention disclosure.
Ready to connect★ 16k
- View details
kill-argumentSkillAI & models
Runs a two-step adversarial review where one agent attacks your paper and another defends it, surfacing weak points.
Ready to connect★ 16k
- View details
meta-applySkillAI & models
Lets your agent apply approved self-improvement patches to its own skill corpus after human sign-off.
Ready to connect★ 16k
- View details
novelty-checkSkillAI & models
Lets your agent check whether a research idea has already been done by searching recent literature.
Ready to connect★ 16k
- View details
overleaf-syncSkillAI & models
Lets your agent sync files between a local paper folder and an Overleaf project so edits stay up to date in both places.
Ready to connect★ 16k
- View details
paper-figureSkillAI & models
Lets your agent create publication-quality figures and tables from your experiment results.
Ready to connect★ 16k
- View details
paper-planSkillAI & models
Lets your agent turn experiment results and review conclusions into a structured outline for a research paper.
Ready to connect★ 16k
- View details
paper-writeSkillAI & models
Lets your agent draft a LaTeX research paper section by section from an outline.
Ready to connect★ 16k
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.
52,524 of the 52,958 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.