terminal-recovery

Agent Skills › odysseus-dev/odysseus › terminal-recovery

terminal-recovery

GitHub

用于从失败的终端命令中恢复，通过证据驱动的故障诊断、最小化只读探测和受限重试来定位并解决命令执行问题。

resources/skills/agent/terminal-recovery/SKILL.md odysseus-dev/odysseus

触发场景

终端命令执行失败命令超时或输出不完整

安装

npx skills add odysseus-dev/odysseus --skill terminal-recovery -g -y

更多选项

非标准路径

npx skills add https://github.com/odysseus-dev/odysseus/tree/dev/resources/skills/agent/terminal-recovery -g -y

不安装直接使用

npx skills use odysseus-dev/odysseus@terminal-recovery

指定 Agent (Claude Code)

npx skills add odysseus-dev/odysseus --skill terminal-recovery -a claude-code -g -y

安装 repo 全部 skill

npx skills add odysseus-dev/odysseus --all -g -y

预览 repo 内 skill

npx skills add odysseus-dev/odysseus --list

SKILL.md

Frontmatter

{
    "name": "terminal-recovery",
    "tags": [
        "terminal",
        "shell",
        "debugging",
        "recovery"
    ],
    "owner": "",
    "source": "builtin",
    "status": "published",
    "created": "2026-08-30T00:00:00Z",
    "version": "1.0.0",
    "category": "agent",
    "confidence": 1,
    "description": "Recover from failed terminal commands using evidence-driven diagnosis and bounded retries"
}

When to Use

Use when a command fails, times out, produces incomplete output, or behaves differently from what the task requires.

Procedure

Read the command, exit status, standard output, and standard error before choosing a response.
Confirm the working directory, relevant files, executable availability, permissions, and environment assumptions with minimal read-only probes.
Classify the failure as syntax, missing dependency, wrong path, permissions, resource pressure, timeout, service state, or task logic.
Change one relevant condition and retry the narrowest command that can test the diagnosis.
For a long-running command, use the returned session identifier to poll or provide input instead of launching duplicates.
After recovery, run the original acceptance check and inspect the resulting files or service state.

Pitfalls

Do not rerun an unchanged failing command repeatedly.
Do not install packages or change global configuration before confirming they are missing and necessary.
Do not launch a second server or training job before checking for an existing process and port or device conflicts.
Do not treat partial output or a zero exit status as proof that the requested state was produced.

Verification

The diagnosed cause is supported by command output or environment state.
The corrected command exits as expected.
The requested artifact, process, or state passes an independent acceptance check.