xai-auth
xAI Grok API authentication and setup. Use when configuring xAI API access, setting up API keys, or troubleshooting authentication issues.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-30 00:12
Agents & models
25,262 results
higgsfield-game-generation
Compatibility alias and read-only drift auditor for Higgsfield's retired or missing `higgsfield-game-generation` name. Use when, and only when, a prompt,…
solo-skills
Audit, selectively adapt, install, route, and maintain the Korean solopreneur skill pack from bam-bam-2/solo-skills. Use when the user names solo-skills,…
agent-configuration
Configure how AI coding agents are instructed, constrained, and shared across a project: instruction files, settings scope, hooks or permission guardrails,…
agent-development-principles
Compatibility alias for `agent-principles`. Use when an existing workflow, install surface, or exact-name request still references…
qz-browser-agent
Delegate browser research, automation, and data extraction to Qingzhou (qz) through its CLI. Use when a task needs real web pages, the user's browser session,…
collab-proof
Use when you want to understand what Claude contributed vs what you drove in a session. Triggers on: /collab-proof, session retrospective, ai contribution…
agent-md-maker
[Hyper] Use this skill when the user asks to create or refactor a repository AGENTS.md, split an overlong AGENTS.md into directly linked adjacent rules files,…
alterlab-skill-finder
The AlterLab front door and multi-agent launcher — routes a task to the right AlterLab skill(s) when the user invokes the suite without naming one, and for a…
context-assembly-scorer
Scores how well the current context represents the full conversation — detects information blind spots, stale summaries, and coverage gaps that cause the agent…
executing-plans
Executes plans task-by-task with verification. Use when implementing a plan.
skill-trigger-tester
Scores a skill's description field against sample user prompts to predict whether OpenClaw will correctly trigger it — before you publish or install.
tool-description-optimizer
Analyzes skill descriptions for trigger quality — scores clarity, keyword density, and specificity, then suggests rewrites that improve discovery accuracy.
vllm-bench-serve
Interactive online benchmark orchestrator for vLLM inference services using `vllm bench serve`. Supports single benchmarks, multi-case batch execution with…
timeboxed-iterating
Run a task iteratively over a user-specified duration by dispatching subagents. The orchestrator stays strictly linear and time-checked, but each iteration…
tinygrad
Deep learning framework development with tinygrad - a minimal tensor library with autograd, JIT compilation, and multi-device support. Use when writing neural…
visual-planner
This skill should be used when the user asks to "plan a workflow", "diagram an agent system", "visualize an architecture", "map out a pipeline", "create a flow…
skill-seekers
Generate LLM skills from documentation, codebases, and GitHub repositories
reviewing-ml-prior-art-survey
Use when reviewing an artifact produced by ml-prior-art-survey — an ML task vocabulary map, one angle's search output, one artifact's extract record, or the…
housekeeping
Organize and modernize AGENTS.md and CLAUDE.md context systems. Use when the user works on structuring, migrating, or curating agent instruction files and repo…
yy-create-rule
Create or update rule documents, and update the references in AGENTS.md. Used for: the user wants to create rules, record best practices, record bug fix experience, record architectural decisions. Not used to create skills, the AGENTS.md main file, or ordinary project documentation, nor to directly modify code to implement rules.
langchain
LangChain framework for LLM application development. Covers chains, agents, tools, RAG pipelines, vector stores, memory, and LangChain Expression Language…
subagents-management
Create, edit, list, move, and delete subagents and skills for coding agents (Claude Code, Codex CLI, OpenCode). Manage AGENTS.md instructions, custom subagent…
create-locked-down-skill
Create a restricted workflow directory with locked-down permissions for Claude Code, Codex CLI, Gemini CLI, and OpenCode. Use when asked to set up a new…