skill-miner

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Skill Miner

Overview

概述

Mine real agent usage for new skill opportunities. The goal is to find repeated workflows, extract the reusable technique, and turn strong candidates into draft skills with evidence.

挖掘Agent的实际使用场景以寻找新技能的开发机会。目标是找出重复工作流，提取可复用的技术，并将优质候选内容转化为带有证据支撑的技能草稿。

When To Use

适用场景

A user wants to scan past coding-agent sessions for repeated workflows.
The user suspects they keep asking agents to do similar tasks manually.
A team wants a backlog of candidate skills based on actual work rather than brainstorming.
Existing memories, session logs, or project notes contain recurring procedures that have not been packaged.

Do not use to tune an existing skill; use

skill-personalizer

. Do not use to publish a private skill publicly; use

skill-generalizer

用户希望扫描过往编码Agent会话，寻找重复工作流。
用户怀疑自己一直在手动让Agent执行类似任务。
团队希望基于实际工作而非头脑风暴，建立技能候选需求池。
现有记忆、会话日志或项目笔记中包含尚未被封装的重复流程。

请勿用于优化现有技能；如需优化，请使用

skill-personalizer

。请勿用于将私有技能公开发布；如需发布，请使用

skill-generalizer

。

Workflow

工作流程

Locate real evidence: session JSONL, memory summaries, repo notes, repeated scripts, and recent project folders.
Run
```
scripts/scan_sessions.py
```
for a first-pass sanitized cluster report when local session files or exported transcripts are available.
Cluster repeated work by intent, trigger phrasing, tools used, files touched, and verification pattern.
Filter out one-off tasks, ordinary coding knowledge, and project-specific instructions better suited for
```
AGENTS.md
```
.
Score candidates by recurrence, friction, risk, portability, and future value.
For each strong candidate, draft a concise skill name, trigger description, workflow outline, bundled-resource needs, and validation prompts.
Recommend whether each candidate should stay personal, become a public skill via
```
skill-generalizer
```
, or be skipped.
If the user asks to proceed, create the selected skill folders and verify frontmatter/layout.

查找真实证据：会话JSONL文件、记忆摘要、仓库笔记、重复脚本以及近期项目文件夹。
当存在本地会话文件或导出的记录时，运行
```
scripts/scan_sessions.py
```
生成初步的清理后聚类报告。
按意图、触发语、使用工具、涉及文件和验证模式对重复工作进行聚类。
过滤掉一次性任务、常规编码知识以及更适合放入
```
AGENTS.md
```
的项目特定指令。
按重复频率、操作难度、风险、可移植性和未来价值对候选技能进行评分。
针对每个优质候选，草拟简洁的技能名称、触发描述、工作流大纲、所需捆绑资源以及验证提示。
建议每个候选技能应保留为个人技能、通过
```
skill-generalizer
```
转为公开技能，或直接跳过。
如果用户要求继续推进，创建选定技能的文件夹并验证前置内容/布局。

Evidence Rules

证据规则

Quote or summarize enough source evidence to justify each candidate.
Do not expose sensitive transcript content unless the user explicitly asks for raw evidence.
Avoid turning every repeated task into a skill; prefer workflows where guidance changes future behavior.
Treat broad intent clusters as navigation hints, not skill drafts.
Check sampled positives and near misses before trusting a regex-based workflow candidate.
If session access is incomplete, label findings as partial and list what was scanned.

引用或总结足够的源证据以证明每个候选技能的合理性。
除非用户明确要求原始证据，否则不得泄露敏感记录内容。
避免将每个重复任务都转化为技能；优先选择那些指导内容能改变未来行为的工作流。
将宽泛的意图聚类视为导航提示，而非技能草稿。
在信任基于正则表达式的工作流候选之前，检查抽样的匹配项和接近匹配项。
如果会话访问不完整，需将发现标记为部分结果，并列出已扫描的内容。

References

参考资料

Read discovery-rubric.md before doing a full session-history scan or creating candidate skill drafts.

Use

scripts/scan_sessions.py --help

for the deterministic scanner. It supports native Codex/Claude/Gemini-style local evidence,

--export

inputs for other agents, and

--patterns

for personalized workflow definitions. Treat its output as evidence for review, not as an automatic decision to create skills.

在进行完整的会话历史扫描或创建候选技能草稿之前，请阅读discovery-rubric.md。

使用

scripts/scan_sessions.py --help

获取确定性扫描工具的帮助信息。它支持原生Codex/Claude/Gemini风格的本地证据、用于其他Agent的

--export

输入以及用于个性化工作流定义的

--patterns

参数。请将其输出视为供审核的证据，而非创建技能的自动决策依据。