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
63,139 results · page 1420 of 2,105
- View details
asteroidSkillProductivity
"Route Asteroid tasks to the right sub-skill for pretrained
Ready to connect
- View details
atomic-agentsSkillAI & models
"Use Atomic Agents to build schema-driven agents, integrate tools
Ready to connect
- View details
attention-gated-networksSkillDev tools
"Guides Attention-Gated Networks PyTorch medical imaging workflows
Ready to connect
- View details
attention-is-all-you-need-pytorchSkillDev tools
"Use jadore801120 attention-is-all-you-need-pytorch for Transformer
Ready to connect
- View details
audio-diffusion-pytorchSkillMedia
"Use audio-diffusion-pytorch for PyTorch waveform diffusion
Ready to connect
- View details
audit-and-fixSkillAI & models
Audit an existing codebase, then autonomously implement the fixes it judges worth making against your next goal — composing deep-dive → triage → prompt-pack → build-loop to turn "here's what's wrong" into verified, receipted local commits + an honest ledger. ALWAYS invoke when the user says any of "
Ready to connect
- View details
audit-contextSkillDocs & knowledge
Evaluates ambient context artifacts (CLAUDE.md, memory, local skills, settings hooks) for compatibility with swarm governance. Returns a classified report so users can address interference before launching a team.
Ready to connect
- View details
audit-snapshotSkillAI & models
Use this skill at Step 12 of the v2 SOP, after a change has passed compliance review (Step 10) and any remediation (Step 11), to produce the AUDIT_BUNDLE.tar.gz that satisfies HIPAA / PIPL / 数据安全法 / 健康医疗数据 安全指南 6-year replayability requirements. Packages prompt history, code diff, compliance artifac
Ready to connect
- View details
audit-snapshot-microSkillMonitoring & ops
Use this skill at Step μ5 of the 5-step micro SOP to produce a lightweight MICRO_AUDIT.json (vs the full AUDIT_BUNDLE.tar.gz). Records diff hash, test result, MICRO_TAG, and writes to mcp-audit-log under event_type `micro_change_seal`. Chinese trigger examples: "micro 归档", "Step μ5", "轻量审计冻结". Do NO
Ready to connect
- View details
- View details
- View details
auto-sklearnSkillSearch
"Route auto-sklearn AutoML estimator, data validation, search,
Ready to connect
- View details
- View details
autogluonSkillProductivity
"Route AutoGluon repo tasks across tabular ML, time-series
Ready to connect
- View details
autogptSkillCloud & infra
"Route AutoGPT Platform self-hosting, backend, frontend, and legacy
Ready to connect
- View details
autogradSkillDev tools
"Routes Autograd install, differentiation, wrapper, extension, and
Ready to connect
- View details
autokerasSkillProductivity
"Use AutoKeras for Keras-based AutoML task APIs, custom AutoModel
Ready to connect
- View details
automl-gsSkillDev tools
"Routes automl_gs tabular AutoML searches and the generated runtime
Ready to connect
- View details
autopsySkillDev tools
Full codebase health assessment. Use when diagnosing project health or starting a rescue workflow on legacy code — OR when evaluating an external GitHub repo for dependency / fork / contribution decisions (--external mode). Analyzes complexity, dependencies, dead code, tech debt, and git hotspots. P
Ready to connect
- View details
autotrain-advancedSkillDev tools
"Routes AutoTrain Advanced installation, CLI, config, training,
Ready to connect
- View details
- View details
aws-sdk-pandasSkillFiles & storage
"Routes AWS SDK for pandas (awswrangler) workflows across S3
Ready to connect
- View details
- View details
baSkillSearch
Business Analyst agent. Use when starting a new feature requiring requirements elicitation BEFORE plan or cook. Asks probing questions, identifies hidden requirements, maps stakeholders, defines scope boundaries, and produces a structured Requirements Document that plan and cook consume.
Ready to connect
- View details
back-of-the-envelopeSkillFiles & storage
This skill should be used when the user needs to "estimate QPS", "back-of-the-envelope" (BOTEC) numbers, "how much storage / bandwidth", "how many servers", "peak load", "capacity planning", or wants the standard latency / throughput / availability numbers to ground a design (latency table, QPS rate
Ready to connect
- View details
background-matting-v2SkillProductivity
"Routes BackgroundMattingV2 tasks for background matting inference,
Ready to connect
- View details
baichuan-7bSkillAI & models
"Operate Baichuan-7B model loading, architecture inspection,
Ready to connect
- View details
basic-tsSkillDatabases & data
"Routes BasicTS time-series training, dataset, model, and pipeline
Ready to connect
- View details
bauhaus-visualSkillMedia
Breaks the Bauhaus visual language into media modules and, after identifying the user's intent, compiles them into a single deterministic prompt ready to use directly with an image model. Use when the user mentions Bauhaus-style covers, article illustrations, section/event posters, Bauhaus prompts,
Ready to connect
- View details
bayesian-optimizationSkillProductivity
"Route BayesianOptimization package tasks for black-box Bayesian
Ready to connect
Popular skills lists
- Best Claude skills for what are
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for how to use
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for how to create
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
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.
63,068 of the 63,139 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 workspace 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.