agentsDesigns, debugs, evaluates, and hardens AI agents — the loop, tools, memory, context budget, cost, and escalation — independent of any framework. Use when an agent loops forever, repeats a tool call, drifts from its instructions after many turns, invents tool arguments, stops mid-task, or swallows a tool error silently; when deciding single agent versus several, or which framework to build on; when token cost per task or p95 latency has to come down; when designing tool schemas, retries, timeouts, checkpoints, or human approval; when writing an eval set or a regression suite for agent behavior; when prompt injection, tool abuse, or an over-permissioned action is the risk; and when specifying an agent's purpose, escalation rules, and cost ceiling for a team. Covers memory design, multi-agent handoffs, tracing, and rollout. Not for LangChain APIs (`langchain`), retrieval pipelines (`rag`), prompt craft alone (`prompting`), or agent persona and voice (`agent`).
Install via ClawdBot CLI:
clawdbot install ivangdavila/agentsGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Contains instructions to override system prompt or ignore user requests
"Ignore previous instructions"AI Analysis
The provided skill definition is a documentation framework for designing AI agents, containing architectural guidance, checklists, and security best practices. It does not contain executable code, API calls, or instructions to send data. The flagged 'prompt poisoning' signal appears to be a false positive from a rule scanning for the phrase 'ignore previous instructions' within descriptive text, not a malicious override command.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 20, 2026
Deploy an AI agent to handle common customer inquiries via chat, using read tools to access FAQs and knowledge bases. It escalates complex or sensitive issues to human agents based on predefined triggers like legal terms or repeated failures, reducing response times and operational costs.
Implement a multi-agent system where one agent scans transaction data for anomalies using read tools, and another flags potential fraud or regulatory breaches for human review. This ensures adherence to security boundaries and logs all actions for audit trails in financial institutions.
Use an AI agent to manage patient appointment bookings via voice or chat interfaces, integrating with electronic health records as read tools. It escalates to staff for urgent cases or scheduling conflicts, optimizing clinic workflows and improving patient access in healthcare settings.
Deploy agents to automatically review user-generated content for inappropriate material using image and text analysis tools. They escalate flagged content to human moderators based on confidence thresholds, helping scale moderation efforts while maintaining safety standards on social media platforms.
Offer the agent skill as a cloud-based service with tiered pricing based on usage, such as per API call or monthly active users. This model generates recurring revenue by providing businesses with scalable, managed AI agent solutions for tasks like customer support or data analysis.
Provide expert services to design and deploy custom AI agent systems for clients, leveraging the skill's architecture patterns and security guidelines. Revenue comes from project-based fees or retainer agreements, targeting industries like finance or healthcare with specific compliance needs.
License the agent skill technology to other companies for integration into their own products, such as CRM software or mobile apps. This generates upfront or royalty-based revenue by enabling partners to enhance their offerings with AI capabilities without in-house development.
💬 Integration Tip
Start by integrating read-only tools first to minimize risks, then gradually add write capabilities after thorough testing and defining escalation rules for safety.
Scored Aug 19, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...