genshijin-crew
Solid原始人スタイル subagent への委譲判断ガイド。`genshijin-investigator` (コード位置特定)、 `genshijin-builder` (1-2ファイル編集)、`genshijin-reviewer` (diff レビュー) を inline作業 or vanilla `Explore` の代わりにスポーンするタイミングを示す。subagent 出力は原始人圧縮 → 主コンテキストに戻る tool-result が約60%縮小 → 長セッション持続。 Trigger: 「subagent 委譲」「genshijin-crew 使用」「investigator/builder/reviewer 起動」「コンテキスト節約」「圧縮 agent 出力」。
Install
Quality Score: 89/100
Skill Content
Details
- Author
- InterfaceX-co-jp
- Repository
- InterfaceX-co-jp/genshijin
- Created
- 3 months ago
- Last Updated
- 2 days ago
- Language
- JavaScript
- License
- MIT
Integrates with
Bundled in these plugins
Similar Skills
Semantically similar based on skill content — not just same category
mini-research
成本可預期的輕量多來源網路研究——用「一個比較項目派一個 subagent」平行深查,15 個項目以內直接跑、超過 15 才停下來問使用者,最後彙整成一張帶來源的比較表。這是內建 /deep-research 的省成本替代:刻意砍掉「每條主張多票對抗式查證」那個會讓 agent 暴增到上百的乘數,換取可預期、可負擔的花費。**觸發時機**:使用者想「比較大量項目」「調查多個選項」「做選型/競品/工具比較」「survey 一批東西並整理成表」,又在意成本、明講或暗示「不要用太多 agent」「/deep-research 太貴」「輕量一點」「成本可控」時,一定要用這個 skill。凡是「比較 N 個 X 並整理」「幫我調查這幾個然後做成表格」這類需求,即使沒點名,也優先考慮它。**不要用在**:單一主題的線性深讀(直接用 WebSearch/WebFetch inline 即可,不必派 subagent)、需要最高嚴謹度事實查核的正式報告(那才用 /deep-research 的多票查證)。
cavecrew
Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".
cavecrew
Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".