Agents
AI agents and automation
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.
ask-effective-llm-coder
by NavanithanS
Best practices for LLM-assisted coding. Declarative workflows, simplicity, tenacity.
wide-column
by Semprini
Use this skill when the user asks for wide-column reporting schemas, denormalized columnar marts, one-table analytics models, or join-minimized read models from MD-DDL.
skill-creator
by observerw
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' capabilities with specialized knowledge, workflows, or tool integrations.
skill-validator
by jorgealves
Validates agent skill definitions against agentskills.io and AGENTS.md rules. Use when creating or modifying skills to ensure they are machine-readable and documentation-complete.
aegis-escalation-cascade
by starwreckntx
Tier escalation and human override cascade protocol for AI-to-Human governance bridge.
improving-skills
by taisukeoe
Improve existing agent skills based on user feedback and best practices. Use when the user wants to fix, enhance, or refactor an existing skill. Gathers user feedback first, then applies technical analysis and implements improvements.
workflow-logging
by penkzhou
工作流过程日志格式规范和写入模式。定义 JSONL 和文本两种格式的日志结构、事件类型、级别定义和写入方法。
knowledge-patterns
by penkzhou
PR Review 修复模式库。在处理 PR Review 评论时自动查阅，寻找已知问题模式和解决方案。
coordinator-patterns
by penkzhou
master-coordinator 和 review-coordinator 共享的通用模式，包括 Phase 验证、错误处理、TodoWrite 管理和状态说明。所有 coordinator agents 应引用此 skill 以保持一致性。
codex-law-enforcement
by starwreckntx
Enforce the four Codex Laws governing all agent interactions: CONSENT, INVITATION, INTEGRITY, GROWTH.
elements-of-style
by penkzhou
Strunk 写作规则，用于提升文档质量。适用于所有面向人类读者的文本：文档、报告、注释、提交信息等。
codex-law-governor
by starwreckntx
Govern agent behavior through enforcement of the Codex Laws framework.
browser-use Skill for Claude Code
by dalbit-mir
dpa.network contact@dpa.network Matrix Telegram
writing-skills
by as4584
Use when creating new skills, editing existing skills, or verifying skills work before deployment
diverse-content-gen
by rfxlamia
"Agent workflow for generating highly diverse creative content using Verbalized Sampling (VS) technique. Use when user requests multiple variations, brainstorming, creative ideas, or when standard prompting produces repetitive outputs. Increases diversity by 1.6-2.1× while maintaining quality. Works for: blog posts, social media captions, stories, campaign ideas, product descriptions, taglines, and open-ended creative tasks."
ralph-eats-beads
by rawwerks
Autonomous AI coding loop using bd for task management with parallel tmux subagents. Ships features while you sleep.
Continuous Calibration, Continuous Development (CCCD)
by Coowoolf
105 Product Management Skills extracted from Lenny's Podcast - For use with Claude Code / Cursor / Windsurf
behavioral-profile-calibration
by starwreckntx
Calibrate behavioral profiles for consistent agent operation.
docs-seeker
by wollfoo
"Search technical documentation using executable scripts to detect query type, fetch from llms.txt sources (context7.com), and analyze results. Use when user needs: (1) Topic-specific documentation (features/components/concepts), (2) Library/framework documentation, (3) GitHub repository analysis, (4) Documentation discovery with automated agent distribution strategy Dùng khi tìm tài liệu, hướng dẫn, docs, documentation, api docs, tham khảo."
Google ADK Python Skill
by wollfoo
Remember: ADK treats agent development like traditional software engineering - use version control, write tests, and follow engineering best practices.
ai-teammate-model
by Coowoolf
Use when designing AI agent products, defining roadmaps for agentic workflows, or evaluating how to evolve AI from passive tool to proactive partner in software development
prompt-injection-scanner
by jorgealves
Audits agent skill instructions and system prompts for vulnerabilities to prompt hijacking and indirect injection. Use when designing new agent skills or before deploying agents to public environments where users provide untrusted input.
commerce-pm
by violetio
Commerce product management