improvement-learner当需要检查 skill 质量评分、自动优化 SKILL.md 结构、追踪评估分数变化趋势、或「评分低了想知道哪里扣分」时使用。6维结构评估 + HOT/WARM/COLD 三层记忆 + Pareto front。不用于候选语义打分(用 improvement-discriminator)或全流程编排(用 impr...
Install via ClawdBot CLI:
clawdbot install lanyasheng/improvement-learnerGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
exec(Audited Apr 16, 2026 · audit v1.0
Generated Apr 17, 2026
A platform where developers create and share AI agent skills. The Improvement Learner is used to automatically evaluate and optimize skill documentation (SKILL.md) for quality, ensuring high standards across the skill library. It helps maintain consistency and reliability by running self-improvement loops to enhance accuracy, coverage, and security without manual reviews.
Large companies deploying custom AI agents for internal workflows use the Improvement Learner to audit and improve proprietary skills. It tracks quality scores over time, identifies weaknesses like security leaks or incomplete documentation, and ensures skills meet corporate standards before deployment in production environments.
Universities or training programs teaching AI development incorporate the Improvement Learner to help students refine their skill projects. It provides detailed feedback on 9 evaluation dimensions, guiding learners to improve accuracy, knowledge density, and trigger quality in a structured, automated manner.
Open-source communities managing AI agent skill repositories use the Improvement Learner to automate quality checks and updates. It runs in CI pipelines with --mock mode for fast scoring, ensuring contributions meet standards and preventing regressions in skill performance over multiple iterations.
Consultants offering AI optimization services leverage the Improvement Learner to analyze and enhance client skills. It diagnoses specific issues like low accuracy or leakage, provides actionable insights for improvements, and tracks progress to demonstrate value through measurable score increases.
Offer the Improvement Learner as a cloud-based service where users pay a monthly fee to access skill evaluation and self-improvement features. Revenue comes from tiered pricing based on usage, such as number of skills assessed or LLM token consumption, with premium plans for advanced analytics and historical tracking.
Sell perpetual or annual licenses to large organizations for on-premises deployment of the Improvement Learner. Revenue is generated through upfront license fees and ongoing support contracts, targeting companies needing high security, customization, and integration with internal AI systems.
Release the core Improvement Learner as open-source software to build community adoption, while offering premium features like enhanced memory layers, priority support, or advanced CLI tools for a fee. Revenue streams include donations, sponsorships, and paid add-ons for commercial users.
💬 Integration Tip
Integrate via CLI scripts in CI/CD pipelines for automated skill quality checks, using --mock mode for fast feedback and LLM mode for detailed evaluations in production.
Scored Apr 19, 2026
Book guitar-lessons services through Lokuli MCP. Use when user needs to find and book guitar-lessons. Triggers on requests like "book a guitar-lessons", "find guitar-lessons near me", or any guitar-lessons service request.
Generate study materials. Use when creating study plans, quizzes, flashcards, tracking progress, or scheduling review sessions.
When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'ment...
Loads any thinker's, leader's, philosopher's, or organization's complete mental operating system directly into the AI — so the AI reasons FROM inside that co...
Query empty classrooms at BUPT (Beijing University of Posts and Telecommunications) Xitucheng campus. Use when the user needs to find available/empty classro...
Use when designing a new CLI, reviewing an existing CLI, or resolving uncertainty about a CLI's role, user type, interaction form, statefulness, risk profile...