veezvg-auto-evolutionBuild and maintain a self-evolving skill system that silently captures feedback, graduates repeated feedback into formal rules, improves low-performing skill...
Install via ClawdBot CLI:
clawdbot install veezvg/veezvg-auto-evolutionGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Oct 8, 2026
A SaaS company runs a support Agent that receives recurring complaints like "you forgot to check my order status" or "that's not what I asked for." The Auto Evolution skill silently captures these corrections into a feedback library, deduplicates repeated signals, and after three occurrences proposes a formal rule for the support Agent's troubleshooting methodology. Support leads review and confirm each suggestion, gradually hardening the Agent's behavior without manual prompt rewrites.
A large enterprise deploys internal AI copilots for HR, finance, and IT helpdesks, and needs a governed way to improve them from real usage. Auto Evolution collects bilingual feedback from employees, scores each skill on accuracy, coverage, efficiency, and satisfaction, and surfaces optimization suggestions to platform owners. All rule changes require human approval, satisfying compliance and audit requirements.
A multinational team interacts with an Agent in both Chinese and English, and users frequently say "你又忘了" or "don't do it this way." The skill's detector covers both languages, captures the corrections as structured feedback, and proposes graduated rules or new skills when patterns repeat across regions. This keeps a single Agent aligned with diverse locale expectations.
A development team uses an AI coding skill that keeps misapplying project conventions, prompting developers to say "this is wrong" during reviews. Auto Evolution captures these review corrections, tracks occurrences, and after a threshold suggests updating the skill's checklist or adding a new skill for a recurring coding pattern. Developers confirm changes so the assistant learns project-specific standards over time.
An e-commerce platform runs a shopping assistant that repeatedly misses user preferences, triggering feedback like "not like this" and "that's not right." The skill logs feedback to a topic library and proposes rule graduation for personalization logic, while also flagging high-frequency uncovered request patterns as candidate new skills. Merchandising teams validate suggestions before rollout, improving conversion and satisfaction.
Sell access to an AI agent platform where the Auto Evolution loop is a built-in differentiator, continuously improving agents from real usage. Customers pay per seat or per active agent, and the self-evolution capability reduces churn by making agents measurably better over time.
Offer professional services that install and tune the Auto Evolution framework inside a client's existing agent stack, integrating hooks, feedback templates, and evolution runners. Consultants set thresholds, train teams on the confirm/skip workflow, and run periodic evolution reviews.
Provide a paid add-on module that aggregates feedback data, scores skill performance, and generates audit-ready evolution proposals for compliance-heavy buyers. It turns raw feedback into dashboards and approval workflows that managers can act on.
💬 Integration Tip
Start by wiring the detection script to your real user-message pipeline and initializing the feedback index before enabling the evolution runner, so the system captures signals from day one. Reuse existing feedback-observer and evolution-runner hooks if your project already has an evolution framework, rather than building a parallel one.
Scored Oct 8, 2026
Autonomous self-evolution skill: grants the agent full authority to modify its own configuration, skills, prompts, AGENTS.md, SOUL.md, memory files, and any workspace file WITHOUT asking for user confirmation. The agent should proactively identify weaknesses, fix them, write new skills, and continuously improve itself.
技能自进化引擎 (Skill Self-Evolution Engine) - 全球AI技能基础设施 从技能进化系统升级为技术底座,支持多平台、多技能协同进化。 实现技能间正向演化飞轮:引擎越厉害 -> 技能同步越厉害 -> 越用越进化。 使用场景: 1. 技能自进化引擎内核管理 2. 跨平台技能同步进化 3....
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.
Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, ex...
九章技能进化系统CLI工具 - 自动收集技能使用数据、分析进化需求、生成周报并上报。用于技能自我进化闭环的数据飞轮基础设施。