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
9,019 results · page 102 of 301
- View details
boltz2-binding-affinitySkillAI & models
Predict protein-ligand binding affinity using Boltz-2 model to assess molecular interactions and binding probability for drug discovery.
Ready to connect★ 392
- View details
drugsda-esmfoldSkillAI & models
Use ESMFold model to predict 3D structure of the input protein sequence.
Ready to connect★ 392
- View details
- View details
drugsda-prosstSkillAI & models
Given a protein sequence and its structure, employ ProSST model to predict mutation effects and obtain the top-k mutated sequences.
Ready to connect★ 392
- View details
pm-simSkillAI & models
[DEPRECATED] Renamed to polymarket-paper-trader. Run: npx clawhub install polymarket-paper-trader
Ready to connect★ 391
- View details
creating-workflowsSkillAI & models
Use when the user wants to "create/generate a workflow (a reusable multi-sub-agent orchestration script)". Explains the JavaScript script format for deepx workflows, the available APIs, and how to save and run them with the Workflow tool.
Ready to connect★ 389
- View details
allowed-tools-mismatch-counterexampleSkillAI & models
Generated counterexample declaring narrow tool access while scripts perform network activity
Ready to connect★ 384
- View details
bruce-drawioSkillAI & models
**Use this skill** when the user wants to create any diagram: flowchart, architecture, UML (sequence/class), ER, mindmap, network topology, or any visual diagram.
Ready to connect★ 384
- View details
hard-trigger-shellSkillAI & models
Generated counterexample containing destructive shell hard triggers for scanner verification
Ready to connect★ 384
- View details
homoglyph-obfuscation-counterexampleSkillAI & models
Generated counterexample containing mixed-script lookalike account names
Ready to connect★ 384
- View details
pipeline-exfil-counterexampleSkillAI & models
Generated counterexample containing a multi-stage sensitive data exfiltration pipeline
Ready to connect★ 384
- View details
prompt-injection-counterexampleSkillAI & models
Generated counterexample containing direct instruction override attempts
Ready to connect★ 384
- View details
- View details
test-chmod-etcSkillAI & models
Test fixture for system directory permission modification detection
Ready to connect★ 384
- View details
- View details
yao-knowledge-hskillSkillAI & models
Build and maintain domain knowledge graphs, helping teams organize concept relationships, terminology definitions, and knowledge systems. Supports technical, product, business, and other knowledge domains.
Ready to connect★ 384
- View details
yao-techselect-hskillSkillAI & models
Helps development teams make technology selection decisions, providing framework comparisons, architecture evaluations, and best-practice recommendations. Suited for scenarios where a choice must be made among multiple technical options.
Ready to connect★ 384
- View details
freerideSkillAI & models
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates openclaw.json. Use when the user mentions free AI, OpenRouter, model switching, rate limits, or wants to reduce AI costs.
Ready to connect★ 383
- View details
Mifos Web App Agent SkillsSkillAI & models
Core capabilities and rules for AI agents contributing to the MifosX Web App (Angular).
Ready to connect★ 382
- View details
opencode-controllerSkillAI & models
Control and operate Opencode via slash commands. Use this skill to manage sessions, select models, switch agents (plan/build), and coordinate coding through Opencode.
Ready to connect★ 383
- View details
rails-upgradeSkillAI & models
Analyzes Rails applications and generates comprehensive upgrade reports with breaking changes, deprecations, and step-by-step migration guides for Rails 2.3 through 8.1. Use when upgrading Rails applications, planning multi-hop upgrades, or querying version-specific changes. Based on FastRuby.io met
Ready to connect★ 382
- View details
upgrade-cleanupSkillAI & models
Clean up after (or abandon) a Rails upgrade. Drop NextRails.next? and NextRails.current? branches and retire dual-boot scaffolding (Gemfile.next, Gemfile.next.lock, conditional Gemfile groups), keeping either the next or the current version. Trigger when the user says they are done with the upgrade,
Ready to connect★ 382
- View details
business-docs-syncSkillAI & models
Multi-agent orchestration system for Claude Code with parallel execution, automated quality gates, Board of Directors, and bundled Superpowers skills
Ready to connect★ 377
- View details
cto-plan-reviewerSkillAI & models
Technical architecture review agent for execution plans. Uses cto-advisor skill to evaluate technical decisions, architecture patterns, tech debt implications, and technology choices in plan.md. Triggered by: 'review technical plan', 'cto review', 'architecture review', or automatically during Step
Ready to connect★ 377
- View details
knowledge-managerSkillAI & models
Loads relevant patterns and known errors before track planning. Searches conductor/knowledge/ for solutions we've used before and errors we've encountered. Injects findings into the planner prompt to prevent reinventing solutions and repeating mistakes. Triggered automatically by orchestrator before
Ready to connect★ 377
- View details
retrospective-agentSkillAI & models
Runs after every track completion to extract learnings. Analyzes what worked, what failed, and what patterns emerged. Updates conductor/knowledge/patterns.md with new solutions and errors.json with new error patterns. Proposes skill updates if workflow improvements are identified. Triggered automati
Ready to connect★ 377
- View details
python-project-creatorSkillAI & models
Creates Python projects with proper structure, virtual environments, and dependency management. Use when users request to create a new Python project, set up a Python development environment, or initialize a Python application with standard tooling.
Ready to connect★ 376
- View details
reflectSkillAI & models
Analyzes conversation transcripts to extract user corrections, patterns, and preferences, then proposes skill improvements. Use this skill when users provide corrections, express preferences about code style, or when patterns emerge from successful approaches. Can be triggered manually with /reflect
Ready to connect★ 376
- View details
configuring-visionSkillAI & models
The user wants to connect an LLM or vision provider, already has an API key, asks "can I use OpenAI/Anthropic/Gemini/OpenRouter", wants local Ollama, or needs different cheap and strong models. Use this to configure provider-neutral visual understanding without tying Watch Skill to one agent or mode
Ready to connect★ 370
- View details
adhd-pr-descriptionSkillAI & models
Write or rewrite GitHub PR descriptions in a scannable ADHD-friendly format: outcome-first lead, two-line before/after, short why-safe list, residual one-liner, tight test plan. Default for all Nakama PR bodies (agents and humans). Use when writing, improving, or rewriting a PR description, opening
Ready to connect★ 372
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.
54,764 of the 55,196 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.