Token导航 LogoToken导航TokenDH.com
效率敏感数据clawhub未标认证来源可访问clear审计通过

triggercmdtriggercmd 控制

Agent Skill

triggercmd 用于补充效率相关能力,适合在 OpenClaw 中需要让 Agent 承接效率相关任务时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

21,528

周安装

897

GitHub Stars

2

下载量

7,176
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:triggercmd(triggercmd 控制)
来源仓库:https://github.com/rvmey/triggercmd
安装命令:
openclaw skills install triggercmd
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install triggercmd

简介

通过 TRIGGERcmd REST API 列出和运行命令,远程控制 TRIGGERcmd 计算机。

SKILL.md

name
triggercmd
description
Control TRIGGERcmd computers remotely by listing and running commands via the TRIGGERcmd REST API.
homepage
https://www.triggercmd.com
metadata

TriggerCMD Skill

Use this skill to inspect and run TRIGGERcmd commands on any computer that is registered with the account tied to the local API token.

Authentication

The skill supports two authentication methods (checked in order):

  1. Environment Variable (recommended): Set TRIGGERCMD_TOKEN to your personal API token

- Export it in your shell: export TRIGGERCMD_TOKEN='your-token-here' - Or prefix individual commands: TRIGGERCMD_TOKEN='your-token-here' <command>

  1. Token File: Store token at ~/.TRIGGERcmdData/token.tkn

- The file should contain only the raw token text (no quotes, spaces, or trailing newline) - Must be permission-restricted: chmod 600 ~/.TRIGGERcmdData/token.tkn - To create: mkdir -p ~/.TRIGGERcmdData && read -s TOKEN && printf "%s" "$TOKEN" > ~/.TRIGGERcmdData/token.tkn && chmod 600 ~/.TRIGGERcmdData/token.tkn

Obtaining your token:

  1. Log in at https://www.triggercmd.com
  2. Navigate to your profile/settings page
  3. Copy the API token (keep it secure and never share it)

Security Warning: Never print, log, or paste your token in shared terminals or outputs.

Common Environment Helpers

# Get token from environment variable or file (checks env var first)
if [ -n "$TRIGGERCMD_TOKEN" ]; then
  TOKEN="$TRIGGERCMD_TOKEN"
elif [ -f ~/.TRIGGERcmdData/token.tkn ]; then
  TOKEN=$(cat ~/.TRIGGERcmdData/token.tkn)
else
  echo "Error: No token found. Set TRIGGERCMD_TOKEN env var or create ~/.TRIGGERcmdData/token.tkn" >&2
  exit 1
fi

AUTH_HEADER=("-H" "Authorization: Bearer $TOKEN")
BASE_URL=https://www.triggercmd.com/api

Use the snippets above to avoid repeating the authentication logic in each command.

list_commands

Lists every command in the account across all computers.

curl -sS "${BASE_URL}/command/list" "${AUTH_HEADER[@]}" | jq '.records[] | {computer: .computer.name, name, voice, allowParams, id, mcpToolDescription}'

Formatting tips:

  • For quick human output, pipe through jq -r '.records[] | "\(.computer.name): \(.name) (voice: \(.voice // "-"))"'.
  • Include allowParams when suggesting follow-up commands so the user knows whether parameters are allowed.
  • When asked for a summary, group by .computer.name and present bullet points per computer.

run_command

Run a specific command on a specific computer using the computer name and command name.

# Use jq to safely construct JSON payload and prevent injection
PAYLOAD=$(jq -n \
  --arg computer "$COMPUTER" \
  --arg command "$COMMAND" \
  --arg params "$PARAMS" \
  '{computer: $computer, command: $command, params: $params}')

curl -sS -X POST "${BASE_URL}/run/trigger" \
  "${AUTH_HEADER[@]}" \
  -H "Content-Type: application/json" \
  -d "$PAYLOAD"
  • $COMPUTER should be the computer name (e.g., "MyLaptop")
  • $COMMAND should be the command name (e.g., "calculator")
  • Omit the --arg params "$PARAMS" and params: $params from the jq command when the command does not accept parameters.
  • Using jq -n with --arg ensures all values are properly escaped and prevents JSON injection attacks.
  • Successful responses return a confirmation plus any queued status info. Surface both to the user.

Error Handling

  • Missing token file: Explain how to create ~/.TRIGGERcmdData/token.tkn and remind them to keep it private.
  • Invalid token (401/403): Ask the user to regenerate the token and overwrite the file.
  • Computer not found: Show the available computer names (case-insensitive match).
  • Command not found: List the commands for the requested computer; highlight commands with allowParams: true when relevant.
  • API/network issues: Include the HTTP status and response body to aid debugging.

Testing workflow

  1. Verify authentication is configured:
   [ -n "$TRIGGERCMD_TOKEN" ] || [ -f ~/.TRIGGERcmdData/token.tkn ] || echo "Error: No token configured"
  1. Test API connectivity (using the helper variables above):
   curl -sS "${BASE_URL}/command/list" "${AUTH_HEADER[@]}" | jq -r '.records[0].computer.name // "No commands found"'
  1. Dry-run a command by listing IDs, then run with known-safe commands (e.g., toggling a harmless script) before invoking anything destructive.

Security Notes

  • Never print, log, or expose the token value. Do not include it in command outputs or error messages.
  • If using the token file method, ensure ~/.TRIGGERcmdData/token.tkn has permissions set to 600 (readable only by owner).
  • Prefer the TRIGGERCMD_TOKEN environment variable for temporary sessions or when you don't want to persist the token on disk.
  • Confirm with the user before running commands with side effects unless they explicitly asked for it.
  • Respect per-device safety constraints; if you are unsure what a command does, ask before triggering it.
  • If authentication fails, do not suggest commands that would expose the token; instead direct the user to regenerate it via the TRIGGERcmd website.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

87.79%
按下载量换算6,300

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

未展示

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills