agent-developmentDesign and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts. Covers Task tool delegation, model selection, memory limits, and declarative instruction design. Use when: creating custom agents, designing agent descriptions for auto-delegation, troubleshooting agent memory issues, or building agent pipelines.
Install via ClawdBot CLI:
clawdbot install veeramanikandanr48/agent-developmentGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/jezweb/claude-skillsUses known external API (expected, informational)
api.anthropic.comAudited Apr 16, 2026 · audit v1.0
Generated Mar 1, 2026
An e-commerce company wants to build a custom agent to automate product listing updates and inventory management. This involves creating an agent with strong delegation triggers for tasks like data entry and quality checks, using the Write and Edit tools for file modifications, and ensuring declarative instructions for consistency across team members.
A software development firm needs an agent to automate code reviews and run tests in CI/CD pipelines. The agent requires a strong description pattern for auto-delegation on code analysis tasks, tool access limited to Read, Grep, and Bash for script execution, and self-documenting prompts to capture bug fix patterns for future sessions.
A marketing agency aims to create an agent for generating and optimizing web content with SEO best practices. This involves using the Opus model for creative quality, declarative instructions for content guidelines, and memory limit fixes to handle large document processing without crashes during batch operations.
A financial institution seeks an agent to analyze transaction data and generate compliance reports. The agent must have a strong trigger pattern for data auditing tasks, tool access restricted to Read, Glob, and Grep for security, and integration with Task sub-agents over remote APIs to ensure high-quality, cross-referenced outputs.
An online education platform wants an agent to curate and update learning materials. This requires designing the agent with proactive use keywords for content management, using the Sonnet model for balanced quality, and encoding file path conventions in the prompt to maintain consistency across multiple content creators.
Offer pre-built agent templates with strong description patterns and tool configurations as a subscription service. Customers can customize these templates for their specific use cases, reducing development time and ensuring best practices in delegation and memory management.
Provide expert services to design and implement custom AI agents for enterprises. This includes creating declarative prompts, optimizing tool access, and fixing memory issues, with revenue generated through project-based fees or retainer agreements for ongoing support and improvements.
Develop and sell training courses and certifications on agent development best practices. Cover topics like delegation mechanisms, model selection, and self-documentation principles, targeting developers and businesses looking to upskill their teams in AI agent deployment.
💬 Integration Tip
Integrate this skill by starting with declarative prompts for clear task goals, using Task sub-agents over remote APIs to leverage full tool access, and applying memory limit fixes to prevent crashes during parallel agent runs.
Scored Apr 19, 2026
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4) Establishing review and quality gates, (5) Managing async communication and artifact sharing between agents.
A unified OpenClaw skill that merges self-improvement and proactivity: learn from corrections, maintain active state, recover context fast, and keep work mov...
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Automatically assess task complexity and adjust reasoning level. Triggers on every user message to evaluate whether extended thinking (reasoning mode) would improve response quality. Use this as a pre-processing step before answering complex questions.
Associative memory with spreading activation for persistent, intelligent recall. Use PROACTIVELY when: (1) You need to remember facts, decisions, errors, or...