self-improvement-vicCaptures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Install via ClawdBot CLI:
clawdbot install chungvic/self-improvement-vicGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/peterskoett/self-improving-agent.gitAudited Apr 18, 2026 · audit v1.0
Generated May 13, 2026
When a command or operation fails unexpectedly, log the error to .learnings/ERRORS.md. For example, a deployment script fails due to missing permission, and the agent logs a sanitized summary to avoid repeating the same mistake.
When a user corrects the agent (e.g., 'No, that's wrong'), log the correction to .learnings/LEARNINGS.md with category 'correction'. This prevents the agent from repeating the same error in future tasks.
When a user asks for a capability that doesn't exist, log the request to .learnings/FEATURE_REQUESTS.md. This helps prioritize future development based on actual user needs.
When an external API or tool fails, log the integration details to .learnings/ERRORS.md. For instance, if a payment gateway times out, the agent logs a redacted summary to track recurring issues.
When a better approach is discovered for a recurring task, log it to .learnings/LEARNINGS.md with category 'best_practice'. For example, finding a more efficient database query pattern for report generation.
Offer a subscription-based service that uses the self-improvement skill to continuously enhance an AI assistant's performance for developers, improving code quality and reducing debugging time.
Provide consulting to companies on integrating the self-improvement skill into their AI workflows, helping them build more resilient and adaptive AI agents that learn from user interactions.
Create a platform where developers can share and monetize skill packs like Self-Improvement Plus. Revenue comes from listing fees or a commission on sales.
💬 Integration Tip
Start by initializing the .learnings directory with the provided bash commands in your project root, then configure automatic reminders via the OpenClaw hook for seamless continuous improvement.
Scored May 13, 2026
对用户提供的任何学术论文（PDF附件或URL）进行双模式深度研读。当用户请求分析、研读、解读或总结一篇学术论文时，使用此技能。一次性生成两份报告：Part A 面向研究者的深度专业解析，Part B 面向快速理解的核心逻辑与价值提炼。
Create personalized triathlon, marathon, and ultra-endurance training plans. Use when athletes ask for training plans, workout schedules, race preparation, or coaching advice. Can sync with Strava to analyze training history, or work from manually provided fitness data. Generates periodized plans with sport-specific workouts, zones, and race-day strategies.
Evidence-based endurance coaching protocol (v11.35). Use when analyzing training data, reviewing sessions, generating pre/post-workout reports, planning work...
Trigger Alter macOS app actions via x-callback-urls. Catalog of 84+ actions including ask-anything, translate, summarize, grammar correction, and more.
Bring Neal Stephenson's "Young Lady's Illustrated Primer" from The Diamond Age to life. Transform your AI from a helpful butler into a subversive tutor — one that adapts to your life stage, holds you accountable to who you're becoming, and has permission to challenge you. Use when setting up growth goals, accountability systems, life transitions, "who I want to become", personal development, or when someone wants their AI to challenge them rather than just help them.
Adds equilibrium-constrained reasoning to OpenClaw, ensuring all operations maintain balance for coherent, self-validating, and consistent AI responses.