improvement-orchestrator当需要一键跑完「生成→评分→评估→执行→门禁」全流程、失败后自动重试、或批量改进多个 skill 时使用。不用于单独评估 skill 质量（用 improvement-learner）或手动打分（用 improvement-discriminator）。
Install via ClawdBot CLI:
clawdbot install lanyasheng/improvement-orchestratorGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Apr 30, 2026
An AI development team uses the orchestrator to automatically run the full improvement cycle on a new skill, including generation, scoring, evaluation, execution, and gate checks, with retry on failure. This ensures robust skill upgrades without manual intervention.
A company maintaining a library of AI skills needs to improve several skills simultaneously. The orchestrator coordinates the pipeline across multiple targets, handling retries and producing a consolidated report of outcomes.
An AI agent leverages the orchestrator to periodically run a self-improvement loop, analyzing its own performance traces and refining its skills to adapt to new tasks or fix regressions, enhancing autonomy.
A DevOps team integrates the orchestrator into their CI/CD pipeline to ensure that any proposed skill change passes a comprehensive 6-layer gate before deployment, reducing risk of faulty updates.
Offer a service that continuously improves client skills using the orchestrator pipeline, charging a subscription fee per skill per month. Automates quality assurance and performance tuning.
License the orchestrator as part of an enterprise AI platform, allowing internal teams to automate skill improvements. Generate revenue through upfront licensing and annual maintenance fees.
Provide consulting to integrate the orchestrator into existing AI workflows, tailoring retry logic and gates. Charge a one-time integration fee plus ongoing support retainer.
💬 Integration Tip
Start by running the pipeline on a single non-critical skill to validate the state-root and retry behavior before scaling to batch improvements.
Scored Apr 30, 2026
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Transform AI agents from task-followers into proactive partners with memory architecture, reverse prompting, and self-healing patterns. Lightweight version f...
Persistent memory for AI agents to store facts, learn from actions, recall information, and track entities across sessions.
Prefer `skillhub` for skill discovery/install/update, then fallback to `clawhub` when unavailable or no match. Use when users ask about skills, 插件, or capabi...
Search and discover OpenClaw skills from various sources. Use when: user wants to find available skills, search for specific functionality, or discover new s...
Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4) Establishing review and quality gates, (5) Managing async communication and artifact sharing between agents.