recallTeaches agents to check before they guess. Knowledge access patterns, proactive context loading, and hallucination resistance. Install before taking the Know...
Install via ClawdBot CLI:
clawdbot install crewhaus/recallGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://crewhaus.ai/certifyAudited Apr 17, 2026 · audit v1.0
Generated Aug 11, 2026
An AI agent that assists developers by checking project documentation, code, and existing patterns before answering questions, reducing errors and improving code consistency.
A support agent that proactively loads product documentation and user data to provide accurate, context-aware responses, reducing hallucination and improving customer satisfaction.
An agent that verifies medical guidelines, patient records, and drug interactions from trusted sources before answering clinical queries, enhancing safety and compliance.
An agent that checks up-to-date market data, client portfolios, and regulatory documents before giving financial advice, minimizing misinformation and building trust.
An agent that consults case law, statutes, and client files before answering legal questions, ensuring accuracy and reducing the risk of citing outdated or irrelevant information.
Charge a recurring fee for access to the AI agent, often tiered by usage or features.
Charge per query, per token, or per API call, allowing customers to pay for what they use.
Sell custom licenses to large organizations for internal deployment and customization.
💬 Integration Tip
Start by integrating the skill into your agent's startup routine, ensuring it reads relevant context files and scans available skills before responding to user queries.
Scored Aug 11, 2026
Structured reasoning through sequential thinking — break complex problems into steps, solve each independently, verify consistency, synthesize conclusions wi...
LLM-driven epistemic reasoning engine. Evaluates claims against evidence, outputs calibrated confidence and structured belief state (VERIFIED/CONTESTED/UNCER...
Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (>90 days), enriches context duri...
Turn scattered local sources into a source-constrained evidence notebook for incident, release, and maintainer decisions.
三级记忆管理系统 (Three-Tier Memory Management)。用于管理 AI 代理的短期、中期、长期记忆。包括:(1) 滑动窗口式短期记忆,(2) 自动摘要生成中期记忆,(3) 向量检索长期记忆 (RAG)。当需要管理对话历史、优化上下文、构建个人知识库、或实现记忆持久化时使用此 Skill。
Store secrets, long-term memory, daily logs, and anything custom in your Convex backend instead of local files