Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →bluelovers/agent-detect-shell
檢測 AI Agent 運行環境資訊，包括 Shell 類型、平台架構、可用工具等。 防止 Agent 在未知環境下隨機嘗試指令，減少重複錯誤。
Passed 21 of 23 test cases with the skill, and 17 of 23 without it.
and 3 more in the full report
4 fixed19 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.6-flash on 10/2/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
In the single-line environment detection snippet (Option 1 without Node.js/Bun), what expression is echoed when falling back to the Bash environment?
| Checked | Without skill | With skill |
|---|---|---|
| Outputs Bash=$0 for the fallback environment string. | Missed | Passed |
The instructions your model reads when the skill loads.
當 Agent 發現指令錯誤時，提供冷靜思考與環境判斷的標準流程，避免在未知環境下隨機嘗試指令而導致重複錯誤。
When agents encounter command errors, this skill provides a standard process for calm thinking and environment assessment, avoiding random command attempts and repeated errors in unknown environments.
核心原則 / Core Principles
- 冷靜思考原則 / Calm Thinking Principle：錯誤發生時先停止並思考環境狀況
- 環境檢測優先 / Environment Detection First：使用檢測工具判斷當前環境
- 語法適應性 / Syntax Adaptability：根據 Shell 類型選擇正確語法
- 終端術語統一 / Terminal Terminology Unification：理解不同終端術語可能指相同概念
當 Agent 執行指令失敗時，應遵循以下思考流程：
指令執行失敗
│
▼
1. 冷靜停止 - 不要立即重試
│
▼
2. 思考環境判斷
│ ├─ 我現在處於什麼終端環境？
│ ├─ 這個環境支援什麼語法？
│ └─ 我是不是用了錯誤的語法？
│
▼
3. 使用環境檢測技能
│
▼
4. 根據檢測結果調整指令
│
test cases passed, vs 17 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.