Menu
Use when evaluating whether an open-source project fits our needs.
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
Use when Hermes Agent needs X/Twitter search, public signal research, monitoring, or approval-gated account actions through the Hermes Tweet plugin.
Router Learning System — 越用越聰明嘅任務路由引擎。 每個 task 有最佳 path，Router 自動記錄經驗、動態調整、跳過爛 path。
Use when signaling work status across autonomous sessions.
Use when needing to standardize descriptions across many skill files at once — change format, fix wording, or enforce a convention like 'Use when...' prefix.
Use before making irreversible changes (deleting files, destructive git operations, large refactors). Use when you need the ability to roll back if something goes wrong. Use at the start of any task that modifies multiple files.
Use when the context window is getting full and tasks need breaking down.
| name | open-source-adaptation-pattern |
| description | Use when evaluating whether an open-source project fits our needs. |
| metadata | {"hermes":{"platform":["cursor","codex","claude-code"]}} |
| domain | ecosystem |
| subdomain | agent-comparison |
| tokens | {"scan":105,"load":1485,"category":"standard"} |
檢查工具生態是否兼容。唔兼容就跳第2層。
如果唔可以直接用，睇佢嘅核心理念係咪通用嘅。通用理念就可以借鑒。
將理念轉化為自己生態嘅實現方式，唔好1:1抄襲。
大 project 通常由多個子組件組成，唔同組件可能有唔同嘅可用性層次。要逐個分析，唔好一刀切：
除咗 README 表面，一定要睇：
當工具聲稱可以「慳錢/加速/壓縮」時，必須做實際 workload 測試先好決定留唔留：
聲稱：壓縮 tool output 60-95% token，唔影響質量 實際測試結果：
protected:recent_code）Step 1: 用真實數據整 3 個 test case（得意見、短 output、長 prose）
Step 2: 每個 case 用工具處理，量度效果（壓縮率/準確度/速度）
Step 3: 對比聲稱效果 vs 實際效果
Step 4: 判斷「啱唔啱我哋用」先決定安裝
Step 5: 如果唔啱用就 uninstall（pip3 uninstall / brew uninstall）