Agents
AI agents and automation
divine
by Olino3
"Entry point to the divine toolkit — skills, agents, and commands that work with Claude Code's capabilities. Discovers available skills, agents, commands, and recommends the right tool for any task."
agent-speak
by Kaizhi
Speak messages aloud using ElevenLabs TTS. Use when completing tasks, reporting progress, or notifying the user of important events. Invoke via the agent-speak CLI command.
angular-agent-skill
by erikarens
A brief description of what this skill does
btca-lazy
by NikiSkaarup
Use btca only when the user explicitly requests it.
delegation-principle
by DUTSTECH
Core principle that the main agent is a coordinator, not an implementer. All work must be delegated to subagents.
blog-writer
by Keiji-Miyake
収集された素材を元に、高品質なブログ記事（特に技術ブログ）の執筆、SEO最適化、構成提案を行います。
writing-skills
by Cygnusfear
Use when creating new skills, editing existing skills, or verifying skills work before deployment
w00-workflow-checkpoint
by qiao-925
Workflow Checkpoint 基础能力（聚焦存档与读档）：在 GitHub Issues 中记录 checkpoint 进展并读档上下文。适用于任意 workflow 阶段，支持自动触发与手动高频调用。关键词：存档、读档、checkpoint、issue。
agent-hoppscotch
by OmkarBhede
CLI tool for managing Hoppscotch API documentation. Use when user asks to document API, add API to Hoppscotch, update API docs, or manage API collections.
mac-dev-software
by svensxl
在 macOS 上一键安装常用 AI coding agent 和开发工具。当用户需要配置 macOS 开发环境、安装 Homebrew、iTerm2、Node.js、NVM、Maven、OpenJDK、OpenCode、Codex CLI、Claude Code 等工具时使用此 skill。
dba-architect
by shaul1991
DBA Architect Agent. 스키마 설계, 정규화, 데이터 모델링을 담당합니다.
critical-thinking-guidance
by qiao-925
思考引导机制，要求 Agent 在给出答案前先提出引导性问题，帮助用户主动思考，避免认知能力退化。适用于用户提问、方案咨询、学习交流等交互场景。
agent-runbook-skill
by rogerchappel
Run npm test, npm run check, and npm run smoke.
mizzen-cli
by MizzenAI
AI 访谈设计与管理技能。通过 Mizzen CLI 创建和管理用户研究访谈。 触发词: create interview, design study guide, user research, user interview, 用户访谈, 访谈设计, study guide, 调研, 创建访谈, 设计大纲, research interview, screener design. 核心能力: 访谈创建、大纲设计、题目设计、甄别筛选、对话数据获取。
aave-risk-assessor
by 0xWeakSheep
This skill should be used when the user asks about "health factor", "liquidation risk", "aave risk", "will I be liquidated", "safe to borrow", "my account health", "collateral risk", "liquidation price", or wants to assess the risk of their AAVE V3 position. Calculates health factor, LTV ratios, liquidation thresholds, and provides risk level assessments for positions on Ethereum and Arbitrum.
clawtrust
by clawtrustmolts
ClawTrust is the trust layer for the agent economy. ERC-8004 identity on Base Sepolia, FusedScore reputation, USDC escrow (on-chain direct + Circle), swarm validation, ERC-8183 Agentic Commerce Adapter (ClawTrustAC — trustless USDC job marketplace with on-chain settlement), ClawTrust Name Service (4 TLDs: .molt/.claw/.shell/.pinch), x402 micropayments, Agent Crews, full ERC-8004 discovery compliance, agent profile editing, wallet signature authentication, real-time webhook notifications, and Skill Verification (challenge-based auto-grading, GitHub linking, portfolio URL evidence). Every agent gets a permanent on-chain passport. Full gig lifecycle: apply, get assigned, submit work, swarm validate, release escrow. Verified. Unhackable. Forever.
config-bump
by keenranger
Atomic config change with version bump and commit. Use when updating config values, changing thresholds, or says /config-bump.
code-review
by NELpos
Analyze source code quality and propose prioritized fixes using Tidy First and Modern Software Engineering principles. Use for requests like code review, PR review, refactoring suggestions, architecture quality checks, maintainability analysis, or improvement proposals across TypeScript, JavaScript, Python, React, and Next.js codebases.
konductor-workflow
by AlphaBitsCode
Complete framework for AI agent memory, context retention, and strict repo-level architectural governance. Run npx konductor-workflow to scaffold.
airr
by immunomind
Use this skill for AIRR-seq (Adaptive Immune Receptor Repertoire / VDJ-seq) data analysis with immunarch + immundata in R, including ingestion, receptor schema design, immutable transformations, clonality/diversity/public overlap metrics, and Seurat/AnnData integration.