Creating Expert
Create new domain expert with expertise file and workflows. Use when adding new technology or domain area.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-14 00:15
Agents & models
26,292 results
Meta Prompt
Generate prompt variations from templates. Use when creating new commands, skills, or workflows.
Skill Creating
Used to create a new skill. Used when a user wants to create a new skill
software-strategist
Use this agent when you need strategic guidance on software architecture, product direction, technology decisions, or when evaluating trade-offs between user…
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
build-with-claude
Guide a developer through building their Solana MVP step by step using Claude Code. Use when a user says "help me build this", "start the MVP", "guide me…
navigate-skills
Meta skill — browse all installed solana-new skills, repos, and MCPs to find the right tool for any task
rcs-agent-onboarding
Guides RCS/RBM onboarding for Sent customers by preparing agent identity, launch evidence, carrier-approval handoff, SMS fallback, and post-launch…
resume-task
Restores an interrupted agentflow task from its journal and the current tree, then names the actual stage to continue. Use when work stopped midway across…
cross-examine
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to…
deep-probe
Conduct a chain of follow-up questions on the user's proposal or design, investigating each branch of the decision tree one by one until both parties reach consensus. Triggered when the user wants to stress-test a proposal, be deeply questioned about a design approach, or mentions keywords such as "help me review it," "follow up on it," or "pick holes in it."
fast-browser-use
Fastest browser automation with anti-bot bypass and DOM extraction. Navigate pages, capture screenshots, manage sessions, and harvest data from infinite scroll…
kimi-find-skills
Search and discover skills for the agent. Use when the user expresses intent to find a skill, search for a skill, or needs a skill to solve a specific problem.…
kimi-skills-finder
Help users search for and discover Skills. Use when users intend to find or search for skills, or need a skill to solve a specific problem. Trigger words include "find skills", "search skills", "look for skills", or when users describe a problem and request skill recommendations. Also triggers when users ask about available skills or skill discovery.
legal-risk-analyzer
Legal risk assessment assistant that assesses legal risk based on the "severity × likelihood" framework, providing risk scores, levels (green/yellow/orange/red), and specific action recommendations (from accept and monitor to escalate to the head of legal or engage external counsel). Suitable for scenarios where users ask about contract risk, transaction risk, issue grading, or whether escalation to senior legal/external counsel is needed, and triggered when users mention risk assessment, risk level, legal risk analysis, or similar keywords.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends agent's…
skill-creator-swarm
Guide for creating effective skills. Use when users want to create a new skill or update an existing skill that extends an agent's capabilities with…
fable-ruki-agenty
Fable hand-agents — a manual orchestration mode where Fable does not write code, but writes specs into the bodies of GH issues and hands out ready-made tasks to subagents on Sonnet. Invoked…
ris-prioritize
Use when ranking a list of requirements, features, or backlog items using RICE / ICE / MoSCoW / Kano. Built-in decision tree picks the right framework based on…
fable-ruki-agenty
Fable hand-agents — a manual orchestration mode where Fable does not write code but writes specs into the bodies of GH issues and hands off ready-made tasks to subagents on Sonnet. Invoked…
skill-creator-v2
Create, improve, evaluate, harden, and package production-grade Codex/Claude skills and skill groups. Use when the user wants to turn a workflow into a…
he-plan
Plan a change before implementation, resolve material user decisions and prepare repository-grounded UX references. Use a compact plan for small changes; route…
writing-great-skills
Write, revise or review an agent skill (SKILL.md package).
llm-serving-auto-benchmark
Framework-independent LLM serving benchmark skill for comparing SGLang, vLLM, TensorRT-LLM, or another serving framework. Use when a user wants to find the…