auto-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/auto-improvement-orchestratorGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Apr 17, 2026
A team developing multiple AI skills needs to run end-to-end improvement cycles on their skill packages. They use the orchestrator to automatically generate improvements, score them, evaluate with task suites, execute changes, and apply quality gates with automatic retry on failures.
A technical documentation team needs to improve documentation skills with low-risk changes. The orchestrator's adaptive complexity feature allows them to skip the evaluator stage for docs/reference/guardrail categories, streamlining the improvement process while maintaining quality gates.
An organization maintaining dozens of AI skills needs to apply systematic improvements across multiple skills simultaneously. The orchestrator's batch processing capability allows them to coordinate the full pipeline across multiple targets with consistent quality control and failure recovery.
A DevOps team integrates the orchestrator into their continuous integration pipeline to automatically improve skills when tests fail. The baseline evaluation feature identifies failing tasks and injects them as feedback to the generator, creating a self-healing improvement loop.
A quality assurance team uses the orchestrator to enforce 7-layer quality gates on all skill changes. The gate stage receives evaluation artifacts when available and makes final keep/revert decisions, ensuring only high-quality improvements are accepted.
Offer a platform where developers can upload their AI skills and use the orchestrator service to automatically improve them. Charge based on the number of improvement cycles run, with tiered pricing for different retry limits and evaluation complexity levels.
Provide enterprises with a managed service that uses the orchestrator to maintain and improve their AI skill portfolio. Include consulting on task suite design, feedback injection strategies, and quality gate configuration for regulatory compliance.
Operate a marketplace for AI skills where all listed skills must pass through the orchestrator's improvement pipeline. Charge listing fees and take commissions on sales, with the orchestrator ensuring all skills meet quality standards through automated testing and improvement cycles.
💬 Integration Tip
Always provide both --target and --state-root parameters, and use --task-suite only when LLM-based evaluation is needed; omit it for documentation-only changes to skip the evaluator stage.
Scored Apr 19, 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.