Auto Skill Hunter
Auto Skill Hunter continuously expands an agent's capability stack with task-relevant skills, then explains why each selected skill is worth trying.
When to Use
Use this skill when at least one of the following is true:
- - The user asks for a task that current skills cannot solve reliably.
- Similar issues keep appearing across recent sessions.
- The user explicitly asks to discover/install better skills.
- The agent needs proactive capability growth on a timer.
High-Value Outcomes
- - Faster discovery of practical skills for real unresolved tasks.
- Lower manual browsing effort on ClawHub.
- Better skill stack diversity through complementarity scoring.
- Safer adoption via bounded install count and runnable checks.
Usage
CODEBLOCK0
Common Commands
CODEBLOCK1
Core Workflow
- 1. Extract unresolved problems and topic signals from recent chat/session memory.
- Search ClawHub with trending feeds and query endpoints.
- Score candidates with multi-factor ranking:
- issue relevance
- profile and personality fit (
USER.md + personality state)
- complementarity with already installed skills
- quality signals such as stars/downloads (when available)
- 4. Install top candidates with a runnable entry and self-test fallback.
- Produce a concise recommendation report with strengths, scenarios, and selection reasons.
Best-Fit Scenarios
- - A user asks for a task that current skills cannot solve well.
- Recent sessions show repeated failures or unresolved tickets.
- The agent needs proactive capability growth without manual curation.
- The team wants a lightweight "discover -> test -> keep/remove" loop.
Operating Modes
- - Auto patrol mode:
--auto for periodic capability growth. - Targeted mode:
--query "..." when a specific user problem is known. - Safe preview mode:
--dry-run before enabling real installs.
Recommended Execution Policy
- - Start with
--dry-run in new environments. - Use
--max-install 1~2 to avoid noisy bulk installs. - Re-run with a focused
--query when no candidate passes threshold. - Keep only skills that survive at least one real task run.
Scheduled Trigger Recommendation
For continuous value, run Auto Skill Hunter on a timer:
- - Every 30 min for high-change or fast-moving projects
- Every 60 min for normal workflows
- Every 120 min for stable environments
This cadence keeps capability coverage fresh and reduces reaction lag when new user needs appear.
Suggested Cron-Style Routine
CODEBLOCK2
Installation Policy
- - Defaults to max 2 installations per run (configurable with
--max-install or env). - Skips already-installed skills.
- Falls back to scaffold mode when remote clone fails.
Safety and Quality Guardrails
- - Never overwrite existing skill folders.
- Prefer small, frequent patrols over large one-shot installs.
- Keep report output concise and action-oriented.
- Disable outbound reporting during local tests with
SKILL_HUNTER_NO_REPORT=1.
Auto Skill Hunter
Auto Skill Hunter 持续扩展智能体的能力栈，添加与任务相关的技能，并解释为何每个选中的技能值得尝试。
使用时机
当以下任一条件成立时，可使用此技能：
- - 用户提出的任务当前技能无法可靠解决。
- 近期会话中反复出现类似问题。
- 用户明确要求发现/安装更好的技能。
- 智能体需要按定时计划主动增长能力。
高价值成果
- - 更快发现解决实际未完成任务所需的实用技能。
- 减少在 ClawHub 上的手动浏览工作量。
- 通过互补性评分实现更优的技能栈多样性。
- 通过限制安装次数和可运行检查实现更安全的采纳。
使用方法
bash
node skills/skill-hunter/src/hunt.js
常用命令
bash
1) 全自动巡逻
node skills/skill-hunter/src/hunt.js --auto
2) 针对特定未解决问题进行定向搜索
node skills/skill-hunter/src/hunt.js --query 无法可靠获取网页内容并总结关键见解
3) 仅预览（不写入/安装）
node skills/skill-hunter/src/hunt.js --dry-run
4) 限制每次运行的安装数量
node skills/skill-hunter/src/hunt.js --max-install 2
核心工作流程
- 1. 从最近的聊天/会话记忆中提取未解决的问题和主题信号。
- 使用热门动态和查询端点搜索 ClawHub。
- 通过多因素排序对候选技能进行评分：
- 问题相关性
- 配置文件和个性匹配度（USER.md + 个性状态）
- 与已安装技能的互补性
- 质量信号，如星标数/下载量（可用时）
- 4. 安装排名靠前的候选技能，包含可运行入口和自我测试回退。
- 生成简洁的推荐报告，包含优势、使用场景和选择理由。
最佳适用场景
- - 用户提出的任务当前技能无法很好解决。
- 近期会话显示重复失败或未解决的工单。
- 智能体需要主动增长能力，无需手动管理。
- 团队希望建立轻量级的发现 -> 测试 -> 保留/移除循环。
运行模式
- - 自动巡逻模式：--auto 用于定期能力增长。
- 定向模式：--query ... 当已知特定用户问题时使用。
- 安全预览模式：--dry-run 在启用实际安装前使用。
推荐执行策略
- - 在新环境中以 --dry-run 模式开始。
- 使用 --max-install 1~2 避免嘈杂的批量安装。
- 当没有候选技能通过阈值时，使用聚焦的 --query 重新运行。
- 仅保留至少通过一次真实任务运行的技能。
定时触发建议
为获得持续价值，可按定时计划运行 Auto Skill Hunter：
- - 每 30 分钟 用于高变化或快速推进的项目
- 每 60 分钟 用于正常的工作流程
- 每 120 分钟 用于稳定的环境
此节奏可保持能力覆盖的新鲜度，并在出现新用户需求时减少响应延迟。
建议的 Cron 风格例行任务
bash
高变化项目
/30 * node /path/to/workspace/skills/skill-hunter/src/hunt.js --auto --max-install 1
正常项目
0
node /path/to/workspace/skills/skill-hunter/src/hunt.js --auto --max-install 2
安装策略
- - 默认每次运行最多安装 2 个技能（可通过 --max-install 或环境变量配置）。
- 跳过已安装的技能。
- 当远程克隆失败时，回退到脚手架模式。
安全与质量护栏
- - 绝不覆盖现有技能文件夹。
- 优先选择小规模、频繁的巡逻，而非一次性大规模安装。
- 保持报告输出简洁且以行动为导向。
- 在本地测试期间使用 SKILLHUNTERNO_REPORT=1 禁用对外报告。
