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 82 of 301
- View details
agent-auditSkillAI & models
Validates agent configurations for model selection, tool permissions, focus areas, and approach quality. Use when reviewing, auditing, improving agents, or learning agent best practices.
Ready to connect★ 607
- View details
agent-builderSkillAI & models
Build custom AI agents in Claude Code from a user's problem statement. This skill analyzes the user's use case, asks smart clarifying questions, researches the internet for similar agents (GitHub repos, blogs, Claude Code community patterns), and then architects and builds production-ready Claude Co
Ready to connect★ 607
- View details
agent-compliance-auditorSkillAI & models
Validates agent definitions against the Antigravity audit rubric.
Ready to connect★ 607
- View details
agent-creationSkillAI & models
/============================================================================/
Ready to connect★ 607
- View details
agent-creatorSkillAI & models
'Purpose: Guide creation of Claude Code agents following Anthropic official
Ready to connect★ 607
- View details
agent-curatorSkillAI & models
Deep curation of a single agent definition through structured human conversation. Coordinates knowledge research, persona refinement, tooling optimization, and instruction quality improvement. One agent at a time, with due care.
Ready to connect★ 607
- View details
agent-deckSkillAI & models
Terminal session manager for AI coding agents. Use when user mentions "agent-deck", "session", "sub-agent", "MCP attach", or needs to (1) create/start/stop/restart/fork sessions, (2) attach/detach MCPs, (3) manage groups/profiles, (4) get session output, (5) configure agent-deck, (6) troubleshoot is
Ready to connect★ 607
- View details
agent-define-skillSkillAI & models
Purpose: Define an Agent's (Subagent) responsibilities, areas of expertise, and configuration
Ready to connect★ 607
- View details
agentic-rolloutSkillAI & models
Assess an agent, bridge it into Relax, check launch readiness, and demonstrate resident Agentic rollout with evidence. Use when evaluating an agent app before integration, connecting an external agent with --use-agentic-rollout, auditing model-visible context linearity or SessionForest export, check
Ready to connect★ 606
- View details
claude-watchSkillAI & models
Bridge your Claude Code session to the Claude Watch app on Apple Watch
Ready to connect★ 606
- View details
model-integrationSkillAI & models
Guide for integrating a new model into the Relax training pipeline. Use when adding a new model architecture, writing Megatron-to-HF weight converters, implementing custom TP all-gather/chunk logic, debugging weight sync issues, or adapting models for colocate or fully-async mode. Covers Megatron ba
Ready to connect★ 606
- View details
qv-addon-pr-createSkillAI & models
Generate PR descriptions for addon packages (non-SDK inference addons, decoder, OCR). Use when creating a PR description or user asks to "prepare PR description" for an addon package.
Ready to connect★ 601
- View details
qv-agent-stack-syncSkillAI & models
Plan and prepare the QVAC agent-stack release cascade across @qvac/sdk, @qvac/cli, @qvac/ai-sdk-provider, @qvac/opencode-plugin, and @qvac/openclaw-plugin. Use for /qv-agent-stack-sync --plan, --prepare-cascade, or --promote; syncing CLI to a newer SDK; or checking OpenCode/OpenClaw/provider compati
Ready to connect★ 601
- View details
qv-sdk-e2e-createSkillAI & models
Plans and scaffolds e2e tests in packages/sdk/e2e for a new or changed public SDK API. Use when adding or modifying SDK functionality that is exposed to consumers. Enforces happy / sad / error coverage, deterministic model-output assertions, desktop/mobile/Electron consumer coverage, smoke-suite sel
Ready to connect★ 601
- View details
qv-sdk-lockstep-syncSkillAI & models
Stamp the @qvac/inference version onto @qvac/sdk and regenerate tetherto-qvac-sdk so a release-* cut ships one shared version.
Ready to connect★ 601
- View details
qv-sdk-update-modelsSkillAI & models
Regenerates SDK model constants from the live QVAC registry and opens a [mod] PR. Use when registry models landed and packages/sdk models.ts needs syncing, or when invoking /qv-sdk-update-models. Optional cascade refreshes ai-sdk-provider and sdk-python generated catalogs.
Ready to connect★ 601
- View details
repo-stats-autoupdateSkillAI & models
Keeps README badge + inline counts in sync with the real number of skills, agents, graph nodes/edges, communities, converted pipelines, and test inventory. Runs automatically on every commit via a git pre-commit hook. Use when the README drifts from reality or before publishing a release.
Ready to connect★ 585
- View details
skill-routerSkillAI & models
Repo-aware recommendation manager for ctx. Scans the active repository, identifies stack and workflow signals, recommends a capped set of skills, agents, and MCP servers, and unloads helpers that no longer match the current work after user confirmation. Harnesses are recommended by the custom-model
Ready to connect★ 585
- View details
toolboxSkillAI & models
Pre/post dev toolbox — named bundles of skills/agents loaded before development work and councils of experts invoked after. Run /toolbox or the toolbox.py CLI to list, activate, initialize, export, import, and validate toolboxes. Invoke at the start or end of a dev session, when setting up a new rep
Ready to connect★ 585
- View details
Convert C# model classes to Java POJOsSkillAI & models
Converts C# model classes (DTO/POCO) into Java classes (POJOs), mapping .NET serialization attributes to Jackson annotations and correctly handling nullable types.
Ready to connect★ 581
- View details
deep-research-agentSkillAI & models
Comprehensive research agent for in-depth investigation. Use when users ask for deep research, comprehensive analysis, market research, academic surveys, competitive analysis, technology trends, or any topic requiring 100+ source verification. Triggers on requests like "investigate", "research", "an
Ready to connect★ 581
- View details
evo_4 configuration for advanced generationSkillAI & models
Uses the evo_4 XML framework to configure the model with advanced writing, reasoning, and ideation capabilities, enabling stylistic variations, symbolic logic, and unconstrained output.
Ready to connect★ 581
- View details
Lagrangian Modeling of a Mass-Spring SystemSkillAI & models
Model and analyze a chain of oscillators (masses connected by springs) by computing energies, the Lagrangian, and the equations of motion, and performing a modal analysis, using SymPy with specific constraints (for loops, no numpy).
Ready to connect★ 581
- View details
Mechanics Grading Tutor AgentSkillAI & models
Acts as an AI grader for mechanics/physics exercises. It evaluates the validity of the student's answer and guides the problem-solving approach without ever giving the final solution, formulas, or numerical values.
Ready to connect★ 581
- View details
Structuring a literature review in three parts (Conceptual, Theoretical, Empirical)SkillAI & models
Organize the content of a literature review chapter according to a strict three-subsection structure: conceptual review (basic principles), theoretical review (models and approaches), and empirical review (study findings).
Ready to connect★ 581
- View details
brandalfSkillAI & models
Guides creation, revision, and review of Warp- or Oz-branded assets. Use when working on launch pages, docs, HTML/CSS components, UI mockups, prompts, social assets, copy, presentations, or any other branded deliverable that should look and sound unmistakably Warp or Oz.
Ready to connect★ 578
- View details
councilSkillAI & models
Run a model-diverse subagent council to investigate the same problem from multiple perspectives, compare findings, and produce a final recommendation. Use this skill whenever the user asks for a council, second opinions, multiple agents/models to evaluate one question, parallel investigation, red-te
Ready to connect★ 578
- View details
cross-critiqueSkillAI & models
Run a second round on a contested question by circulating each subagent's independent proposal to the other authors and asking for structured pros and cons, then synthesize. Use this skill whenever you have multiple independent proposals or opinions on a contested decision — architecture tradeoffs,
Ready to connect★ 578
- View details
reproduce-bug-reportSkillAI & models
Launch Oz cloud agents with computer use to reproduce UI-focused bug reports, capture visual evidence (a screen recording by default), and report reproduction findings. Use when investigating a specific interactive or visual bug from an issue, ticket, support report, or prompt.
Ready to connect★ 578
- View details
respond-to-pr-comments-in-blocklistSkillAI & models
Interactively walk a user through PR review comments one at a time, collect a per-comment decision, then post agent-authored replies on GitHub and resolve the review threads once the user approves a preview. Use only when the user wants to reply to or resolve review threads on GitHub. Skip when the
Ready to connect★ 578
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.