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 363 of 1,808
- View details
aris-result-to-claimSkillDev tools
Lets your agent judge whether experiment results actually support your claims and what evidence is missing.
Ready to connect★ 1k
- View details
aris-run-experimentSkillCloud & infra
Lets your agent deploy and run machine learning experiments on local or cloud GPU servers.
Ready to connect★ 1k
- View details
aris-semantic-scholarSkillSearch
Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /aris-arxiv (preprints) with citation counts, venue metadata, and TLDR. Use when user says "search semantic scholar", "find IEEE papers", "find journal papers", "venue papers", "citation search", or wants
Ready to connect★ 1k
- View details
aris-serverless-modalSkillCloud & infra
Lets your agent run GPU jobs like training, fine-tuning, and inference on Modal's serverless cloud.
Ready to connect★ 1k
- View details
aris-training-checkSkillMonitoring & ops
Lets your agent periodically check training metrics to catch problems like NaN loss or idle GPUs early.
Ready to connect★ 1k
- View details
aris-vast-gpuSkillDev tools
Lets your agent rent, manage, and shut down rented GPU servers on vast.ai.
Ready to connect★ 1k
- View details
dataset-discoverySkillSearch
Lets your agent search HuggingFace, OpenML, GitHub, and papers to find datasets for a research task.
Ready to connect★ 1k
- View details
dr-clawSkillCommunication
Lets your agent triage project ideas and sessions and send event notifications via the drclaw CLI.
Ready to connect★ 1k
- View details
drclawSkillDev tools
Lets your agent look up projects, inspect coding sessions, track task progress, and report events.
Ready to connect★ 1k
- View details
ds-analysis-campaignSkillDev tools
Lets your agent run follow-up analyses like ablations, robustness checks, and error analysis after a main experiment.
Ready to connect★ 1k
- View details
ds-baselineSkillMonitoring & ops
Lets your agent attach, import, reproduce, repair, verify, compare, or publish a baseline and its metrics.
Ready to connect★ 1k
- View details
ds-decisionSkillDev tools
Lets your agent record explicit go, stop, branch, or reset decisions with reasons and evidence.
Ready to connect★ 1k
- View details
ds-experimentSkillDev tools
Lets your agent run a concrete implementation pass or main experiment for a chosen idea against an accepted baseline.
Ready to connect★ 1k
- View details
ds-figure-polishSkillMedia
Lets your agent create and refine polished charts and publication-ready figures through a render-inspect-revise loop.
Ready to connect★ 1k
- View details
ds-finalizeSkillDev tools
Lets your agent consolidate a quest's final claims, limitations, recommendations, and summary before archiving.
Ready to connect★ 1k
- View details
ds-full-pipelineSkillDev tools
Lets your agent run an end-to-end autonomous research pipeline from scouting ideas through experiments to a finalized report.
Ready to connect★ 1k
- View details
ds-ideaSkillDev tools
Lets your agent form concrete hypotheses, analyze limitations, and pick an idea relative to a baseline.
Ready to connect★ 1k
- View details
ds-intake-auditSkillAI & models
Lets your agent audit and reconcile existing project materials before picking the next step.
Ready to connect★ 1k
- View details
ds-optimizeSkillSearch
Lets your agent run algorithm-driven search quests managing candidate briefs and branch promotion.
Ready to connect★ 1k
- View details
ds-rebuttalSkillProductivity
Lets your agent turn reviewer feedback on a paper into a plan of experiments, manuscript changes, and a written rebuttal.
Ready to connect★ 1k
- View details
ds-reviewSkillDev tools
Lets your agent run a skeptical independent review of a draft paper or report before finalizing it.
Ready to connect★ 1k
- View details
ds-scoutSkillDatabases & data
Helps your agent frame research problems, scout literature, and clarify datasets and baselines.
Ready to connect★ 1k
- View details
ds-writeSkillDev tools
Lets your agent draft or refine research papers and reports based on gathered evidence.
Ready to connect★ 1k
- View details
gemini-deep-researchSkillAI & models
Lets your agent run deep, multi-source web research and get a synthesized report on complex questions.
Ready to connect★ 1k
- View details
inno-code-surveySkillDev tools
Lets your agent fetch missing code repositories and map academic concepts to their code implementations.
Ready to connect★ 1k
- View details
inno-experiment-analysisSkillAI & models
Lets your agent analyze experiment results, run statistics, compare models, and draft the results section of papers.
Ready to connect★ 1k
- View details
inno-experiment-devSkillDev tools
Lets your agent draft an implementation plan, write project code with feedback review, and run the experiment.
Ready to connect★ 1k
- View details
inno-figure-genSkillMedia
Lets your agent generate or edit images from text descriptions or existing pictures.
Ready to connect★ 1k
- View details
inno-grant-proposalSkillDev tools
Lets your agent write, revise, and polish grant proposals for US and Chinese funding agencies.
Ready to connect★ 1k
- View details
inno-idea-evalSkillDev tools
Lets your agent score research ideas on clarity, novelty, validity, feasibility and significance using multiple reviewer perspectives.
Ready to connect★ 1k
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.