Menu
When agent config parameters need querying or modification → read/write YAML configuration files.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
When prompt, tool, or agent logic changes need regression testing → run eval benchmarks to detect regressions or improvements.
When a task can be parallelized (bulk code review, multi-module refactor, batch analysis) → split into subtasks running in isolated git worktrees via multiple workers.
When the user wants to research academic papers → search ArXiv, extract PDFs, summarize/review/Q&A, generate experiment code.
When you need to interact with web pages using the user's logged-in browser → control Chrome via @playwright/cli daemon, reusing cookies/session with persistent tabs.
When user needs AnyGenIO content generation → unified CLI for task execution with progressive disclosure.
When you need to persist files (reports, docs, evidence) beyond the session → create/query/delete durable artifacts.
| name | config-management |
| description | When agent config parameters need querying or modification → read/write YAML configuration files. |
| triggers | {"intent_patterns":["config|配置|设置|setting|参数","改.*配置|change.*config|修改.*参数|update.*setting","查看.*配置|show.*config|当前.*设置|current.*setting","token.*limit|模型.*切换|switch.*model|persona.*设置","开启|enable|关闭|disable|打开.*功能|turn.*on|turn.*off","yaml.*配置|环境变量|env.*var|超时|timeout"],"context_signals":{"keywords":["config","配置","设置","setting","参数","yaml","enable","disable","开启","关闭","切换","修改"]},"confidence_threshold":0.6} |
| priority | 5 |
| requires_tools | ["bash"] |
| max_tokens | 200 |
| cooldown | 30 |
查询和修改 agent YAML 配置文件。
python3 skills/config-management/run.py get --key llm.model
python3 skills/config-management/run.py set --key llm.model --value gpt-4o
python3 skills/config-management/run.py list