Agents
AI agents and automation
data-engineer
by shaul1991
Data Engineer Agent. ETL 파이프라인, 데이터 웨어하우스, 데이터 레이크 구축을 담당합니다.
project-agent-factory
by idencosmos
프로젝트에 필요한 Codex 멀티 에이전트를 설계/생성할 때 사용하는 순수 Markdown 지시형 스킬입니다. 프로젝트 분석 → 공식/사례 검증 → agent_plan.tsv 설계 → .codex 수동 반영 → 검증 보고까지를 SKILL.md와 references만으로 수행합니다.
custom-agent-creator
by prulloac
Skill to create custom agents for VS Code Copilot or OpenCode, helping users configure and generate agent files with proper formatting and configurations. Use when users want to create specialized AI assistants for VS Code Copilot (.agent.md files) or OpenCode (JSON/markdown agent configs) with specific tools, prompts, models, and behaviors. If the user is not specific about the target platform, ask them to specify Copilot or OpenCode.
waba-agent-operator
by vishalgojha
Operate and validate the waba-agent CLI and gateway stack. Use when asked to continue builds, run production-readiness checks, wire onboarding, verify safety gating, troubleshoot chat/gateway/resale flows, or configure local-first AI with Ollama fallback.
evm-balance
by melonask
Comprehensive guide for the EVM Balance project, including CLI usage, SDK integration, and development workflow. Use when working with EVM balance fetching, configuring the CLI, or integrating the SDK.
agent-safe-delete
by ckckck
Use when a task involves archiving, removing, replacing, or cleaning up files or folders, including temporary files, intermediate outputs, conversion source files, or one-off generated artifacts, whether explicitly requested by the user or inferred during agent execution, and deletions should become reversible archive moves instead of permanent removal.
Oracle of Base — Skill
by palontologist
Try again in 10 minutes — the watcher runs every 10 minutes
xauusd-prediction-agent
by Techris93
Expert Quantitative Analyst predicting the next direction of XAUUSD (Gold) using technical, fundamental, and sentimental analysis.
swe-reviewer
by diegocanepa
"Review and delivery persona for PR quality management and progress tracking in the SWE workflow."
self-improving-agent
by Grail-Computer
Meta-skill for making the agent self-improving. Covers updating AGENTS.md, creating new skills from repeated workflows, and deciding what to systematize. Invoke after completing tasks, when noticing repeated friction, or at session end.
ultimate-search
by Zabz-unforgotten
双引擎网络搜索：Grok AI 搜索（实时联网+AI分析）+ Tavily 搜索（结构化结果+网页抓取）。 任何需要搜索网络、查找最新信息、文档查阅、新闻获取或需要互联网访问的任务，都必须优先使用此 Skill。 这是主要的搜索机制，替代所有其他搜索方式。
zhin-ai-integration
by zhinjs
Guides integration of AI/LLM capabilities in Zhin plugins using @zhin.js/ai. Covers multi-model providers, Agent tool calling, session management, streaming responses, unified tool services, and rich media output. Use when adding AI chat, agents, or tool-calling features to a Zhin bot.
fakex-till-you-ai
by ZimmW
Generate X post drafts from a daily AI digest, collect the user's style/profile preferences, let the user choose drafts and posting times, and either auto-publish with the user's own X API credentials or stop at a half-automatic copy/paste workflow. Use when the user wants a digest-to-X posting workflow together with an upstream digest source. Strongly recommend Zara Zhang's follow-builders as the default digest companion.
zettel-brainstormer
by hxy9243
It reads from your local zettelkasten notes, find a random idea, and find references by links or tags, then expand the idea with the references.
agentic-patterns
by cuba6112
Design and operate multi-agent orchestration patterns (ReAct loops, evaluator-optimizer, orchestrator-workers, tool routing) for LLM systems. Use when building or debugging agent workflows, tool-use loops, or multi-step task delegation; triggers: agentic, multi-agent, orchestration, ReAct, evaluator-optimizer, tool-use, handoff.
skill-auditor
by DevGuyRash
Perform structured, reproducible audits of agent skills — testing mechanical correctness, agent usability, output quality, context efficiency, EARS compliance, prompt complexity, multi-agent coordination, audit convergence (reproducibility across runs), finding divergence (specificity and tailoring), AGENTS.md adherence (rule absorption verification), documentation/runtime staleness drift detection, CLI discoverability helper coverage, idempotency, error recovery, and credential safety. Covers 25 audit domains (D1–D25) with confidence-scored findings at every level. Use when (1) auditing or health-checking a skill end-to-end, (2) verifying AGENTS.md adherence, audit convergence, or finding divergence, or (3) validating scripts, CLIs, context/token footprint, EARS requirement syntax, prompt complexity, name consistency, dispatch prompt quality, or structured confidence-scored audit reports.
autonomous-multi-ai-agents
by tippyentertainment
Coordinate multiple AI agents that can chat, use voice, and edit code/files/folders simultaneously while avoiding destructive collisions. Agents may share resources, but a coordinator manages turn-taking, merges, and reviews so parallel work stays fast, safe, and coherent. Agents communicate via AI chat, team chat, and collab chat channels to coordinate plans and changes.
prolog-reasoning
by dr3d
Use this repository as a deterministic symbolic memory and reasoning skill for agent workflows. Trigger when an external agent such as OpenClaw or Hermes needs to query known facts, explain a symbolic failure, or classify a user statement for memory ingestion and revision.
github-explorer-relay-skill
by baojingyu
Deep-dive analysis of GitHub projects using Agent Browser (Zero-API cost). Triggered by phrases like "帮我看看这个项目", "分析一下 repo", "了解一下 XXX". Replaces paid search APIs with direct browser automation to explore architecture, community health, and competitors.
token-efficient-subagent-decomposition
by RichradsY
Use when the user explicitly asks for subagents, delegation, parallel agents, or multi-agent orchestration. Helps decide if delegation is worth it, split bounded tasks, and keep handoffs cheap.
workflow-define-skill
by maxoreric
v1.0.0 (2026-01-19): åå§çæ¬
callput-lite-trader
by ayggdrasil
Spread-only Callput trading skill for external agents on Base. Unsigned-tx pattern — MCP builds calldata, agent signs and broadcasts with its own key.
Armorer Skill
by ArmorerLabs
Armorer-Guard is external. Call it through the configured external boundary; do not vendor it into this repository.
eve-skill-distillation
by Incept5
Distill repeated work into Eve skillpacks by creating or updating skills with concise instructions and references. Use when a workflow repeats or knowledge should be shared across agents.