Token导航 LogoToken导航

Agent Skill · 研究检索

redc(redc 搜索)

redc 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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。

redc 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 13,584。

总安装 9,253周安装 378GitHub Stars 1下载 2,964核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.3

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:redc(redc 搜索)
来源仓库:https://github.com/no-github/redc
安装命令:
openclaw skills install redc
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 redc

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词快速定位候选结果时使用。主要应用于红队基础设施多云自动化部署,支持阿里云、AWS、腾讯云等平台。可跨多云环境部署、管理和监控云实例,提升运维效率。安装命令为 openclaw skills install redc,需确认权限范围和维护状态。

使用前请核实是否会触发联网、命令执行或文件读写等敏感操作。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install redc;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

redc 怎么安装?

在终端执行 openclaw skills install redc。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

redc 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

redc 需要什么权限?

权限级别是接触敏感数据。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。

redc 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

redc 用的人多吗?

公开数据是累计安装 9,253 次,近一周安装 378 次,下载 2,964 次,GitHub 1 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

redc 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
redc

redc 搜索 · 本页

9,2531接触敏感数据MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
redc
description
Red team infrastructure multi-cloud automated deployment tool. Deploy, manage, and monitor cloud instances across Alibaba Cloud, AWS, Tencent Cloud, Volcengine, Huawei Cloud, and more via MCP. Credentials are read from environment variables — only configure the single provider you intend to use. Always inspect templates before applying.
version
1.0.3
metadata
openclaw
requires
env
bins
emoji
🔴
homepage
https://github.com/wgpsec/redc
os

RedC — Red Team Infrastructure Multi-Cloud Automated Deployment

RedC is an open-source red team infrastructure multi-cloud automated deployment tool. It uses Terraform under the hood to manage cloud resources across 6+ cloud providers.

GitHub: https://github.com/wgpsec/redc Template Registry: https://redc.wgpsec.org

Security & Credentials

Credential Model

RedC reads cloud provider credentials from environment variables or a local config.yaml file managed by the redc CLI. Credentials are only passed to Terraform, which communicates directly with cloud provider APIs over HTTPS. No credentials are sent to the redc project, the template registry, or any third-party service.

The metadata declares ALICLOUD_ACCESS_KEY and ALICLOUD_SECRET_KEY as the example required env vars because Alibaba Cloud is the most commonly used provider. However, you should substitute these with the credentials for whichever single provider you actually use. The full list of provider-specific env vars that RedC/Terraform may read:

ProviderEnvironment VariablesNotes
Alibaba CloudALICLOUD_ACCESS_KEY, ALICLOUD_SECRET_KEY, ALICLOUD_REGIONDeclared in metadata
AWSAWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_DEFAULT_REGIONSet only if using AWS
Tencent CloudTENCENTCLOUD_SECRET_ID, TENCENTCLOUD_SECRET_KEYSet only if using Tencent
VolcengineVOLCENGINE_ACCESS_KEY, VOLCENGINE_SECRET_KEYSet only if using Volcengine
Huawei CloudHW_ACCESS_KEY, HW_SECRET_KEYSet only if using Huawei
AzureARM_CLIENT_ID, ARM_CLIENT_SECRET, ARM_TENANT_ID, ARM_SUBSCRIPTION_IDSet only if using Azure

You do NOT need to set all of these. Only configure the env vars for the single provider you intend to deploy to. RedC will not attempt to read or use credentials for providers you are not deploying to.

Credential Best Practices

  • Use scoped, short-lived credentials with minimal permissions (e.g., only ECS/EC2 create/delete, no IAM/billing access).
  • Test in isolated/throwaway cloud accounts to avoid impacting production resources.
  • Do NOT paste long-lived root/owner keys into chat — configure them via redc CLI or environment variables before using this skill.
  • Prefer scoped IAM roles or temporary security tokens (e.g., AWS STS AssumeRole) over static AK/SK pairs.

Binary Verification

  • Download redc only from official GitHub releases: https://github.com/wgpsec/redc/releases — verify SHA256 checksums listed in each release.
  • Download terraform only from HashiCorp: https://developer.hashicorp.com/terraform/downloads — verify PGP signatures.

Template Safety — IMPORTANT

Templates define the actual cloud infrastructure that will be created. They may contain:

  • remote-exec provisioners that run arbitrary scripts on created instances
  • user_data / cloud-init scripts that execute on instance boot
  • Security group rules that open network ports (e.g., 0.0.0.0/0 ingress)
  • local-exec provisioners that run commands on your local machine

Before applying any template, you MUST:

  1. Inspect the template source — Run get_template_info to view the template's main.tf, variables.tf, and other files. Read them to understand what resources will be created.
  2. Use plan_case first — This runs terraform plan to show a preview of all resources that will be created, modified, or destroyed. Review the plan output before proceeding to start_case.
  3. Audit registry templates — The official template repository is fully open-source at https://github.com/wgpsec/redc-template. Compare pulled templates against the source to ensure they have not been tampered with.
  4. Do NOT blindly apply — Never run start_case without first reviewing the plan. This skill will always use plan_case before start_case to give you a chance to review.

MCP Server Exposure

  • The built-in MCP server defaults to stdio transport (local only, no network exposure).
  • The sse mode binds to a configurable address — always restrict it to 127.0.0.1 and do not expose it to untrusted networks.

When to Use This Skill

Use this skill when the user wants to:

  • Deploy cloud infrastructure (ECS, EC2, CVM, proxy pools, C2 servers, etc.)
  • Manage running cloud instances (start, stop, destroy)
  • Execute commands on remote servers via SSH
  • Check cloud account balances and billing
  • Estimate deployment costs
  • Schedule automated start/stop for cloud resources
  • Manage multi-cloud provider profiles and credentials
  • Use redc-compose for multi-service orchestrated deployments

Supported Cloud Providers

ProviderTemplate PrefixDescription
Alibaba Cloud (阿里云)aliyun/ECS, proxy, VPC, etc.
AWSaws/EC2, proxy, etc.
Tencent Cloud (腾讯云)tencent/CVM, lighthouse, etc.
Volcengine (火山引擎)volcengine/ECS, etc.
Huawei Cloud (华为云)huaweicloud/ECS, etc.
Azureazure/VM, etc.

Architecture

RedC has two modes:

  1. CLI mode (redc binary) — command-line operations
  2. GUI mode (redc-gui) — desktop application with built-in MCP server

The MCP server exposes all tools below. It can run in stdio or sse mode.


Tools

1. list_templates

List all available redc templates/images installed locally.

Command:

redc list

MCP Tool: list_templates

Returns template names, descriptions, versions, and supported providers.


2. search_templates

Search for templates in the official registry by keywords.

Command:

redc search <query>

MCP Tool: search_templates

  • query (string, required): Search query (e.g., "aliyun", "proxy", "ecs")
  • registry_url (string, optional): Registry base URL (default: https://redc.wgpsec.org)

3. pull_template

Download a template from the registry.

Command:

redc pull <template_name>

MCP Tool: pull_template

  • template_name (string, required): Template name (e.g., "aliyun/ecs" or "aliyun/ecs:1.0.1")
  • registry_url (string, optional): Registry base URL
  • force (boolean, optional): Force re-download even if template exists

4. list_cases

List all cases (scenes/deployments) in the current project with their status.

Command:

redc ps

MCP Tool: list_cases

Returns case ID, name, status (created/running/stopped/error/terminated), template type, and creation time.

Status values:

  • created — case planned but not yet applied
  • running — infrastructure is live
  • stopped — infrastructure destroyed, state preserved
  • error — deployment failed
  • terminated — spot instance was reclaimed

5. plan_case

Plan a new case from a template (preview resources without creating them).

Command:

redc plan <template_name> [--name <case_name>] [--var key=value ...]

MCP Tool: plan_case

  • template_name (string, required): Template name (e.g., "aliyun/ecs")
  • case_name (string, optional): Case name (auto-generated if not provided)
  • vars (string, optional): Environment variables for the template

6. start_case

Start (apply) a case — creates the cloud infrastructure.

Command:

redc up <case_id>

MCP Tool: start_case

  • case_id (string, required): Case ID to start

7. stop_case

Stop (destroy) a case — tears down the cloud infrastructure.

Command:

redc down <case_id>

MCP Tool: stop_case

  • case_id (string, required): Case ID to stop

8. kill_case

Remove a case completely (destroy infrastructure + delete all local state).

Command:

redc rm <case_id>

MCP Tool: kill_case

  • case_id (string, required): Case ID to remove

9. get_case_status

Get detailed status of a specific case.

MCP Tool: get_case_status

  • case_id (string, required): Case ID to check

10. get_case_outputs

Get terraform outputs for a case (IP addresses, passwords, instance IDs, etc.).

MCP Tool: get_case_outputs

  • case_id (string, required): Case ID to get outputs

11. exec_command

Execute a command on a remote server via SSH.

MCP Tool: exec_command

  • case_id (string, required): Case ID
  • command (string, required): Shell command to execute

12. get_ssh_info

Get SSH connection information for a case (host, port, user, password/key).

MCP Tool: get_ssh_info

  • case_id (string, required): Case ID

13. upload_file

Upload a local file to a remote case server via SCP/SFTP.

MCP Tool: upload_file

  • case_id (string, required): Case ID
  • local_path (string, required): Local file path
  • remote_path (string, required): Remote destination path

14. download_file

Download a file from a remote case server to local machine.

MCP Tool: download_file

  • case_id (string, required): Case ID
  • remote_path (string, required): Remote file path
  • local_path (string, required): Local destination path

15. get_template_info

Get detailed information about a locally installed template (metadata, variables, files).

MCP Tool: get_template_info

  • template_name (string, required): Template name (e.g., "aliyun/ecs")

16. delete_template

Delete a locally installed template.

MCP Tool: delete_template

  • template_name (string, required): Template name to delete

17. get_config

Get current redc configuration (project path, proxy settings, etc.).

MCP Tool: get_config


18. validate_config

Validate cloud provider configuration (check if credentials, region, instance type are valid).

MCP Tool: validate_config

  • provider (string, required): Cloud provider name (e.g., "aliyun", "aws", "tencentcloud")
  • region (string, optional): Region ID (e.g., "cn-hangzhou")
  • instance_type (string, optional): Instance type (e.g., "ecs.t6-c1m1.large")

19. get_cost_estimate

Estimate deployment cost for a template (hourly and monthly cost breakdown by resource).

MCP Tool: get_cost_estimate

  • template_name (string, required): Template name

20. get_balances

Query cloud account balances for configured providers.

MCP Tool: get_balances

  • providers (string, optional): Comma-separated provider names (e.g., "aliyun,aws"). Empty = all providers.

21. get_resource_summary

Get a summary of cloud resources across all configured providers (instance counts, running status, etc.).

MCP Tool: get_resource_summary


22. get_predicted_monthly_cost

Get predicted total monthly cost based on currently running resources.

MCP Tool: get_predicted_monthly_cost


23. get_bills

Get cloud billing information for configured providers.

MCP Tool: get_bills

  • providers (string, optional): Comma-separated provider names. Empty = all.

24. get_total_runtime

Get total runtime of all running cases.

MCP Tool: get_total_runtime


25. compose_preview

Preview a redc-compose deployment: list services, dependencies, providers, and replicas without deploying.

MCP Tool: compose_preview

  • file (string, optional): Compose file path (default: redc-compose.yaml)
  • profiles (string, optional): Comma-separated profiles (e.g., "prod,attack")

26. compose_up

Start a redc-compose deployment (deploys all services in dependency order).

MCP Tool: compose_up

  • file (string, optional): Compose file path
  • profiles (string, optional): Comma-separated profiles

27. compose_down

Destroy a redc-compose deployment (destroys all services in reverse dependency order).

MCP Tool: compose_down

  • file (string, optional): Compose file path
  • profiles (string, optional): Comma-separated profiles

28. list_deployments

List all custom deployments in the current project.

MCP Tool: list_deployments


29. start_deployment

Start a custom deployment by ID.

MCP Tool: start_deployment

  • deployment_id (string, required): Custom deployment ID

30. stop_deployment

Stop a custom deployment by ID.

MCP Tool: stop_deployment

  • deployment_id (string, required): Custom deployment ID

31. list_projects

List all redc projects.

MCP Tool: list_projects


32. switch_project

Switch to a different redc project.

MCP Tool: switch_project

  • project_name (string, required): Project name to switch to

33. list_profiles

List all cloud provider profiles (credential sets).

MCP Tool: list_profiles


34. get_active_profile

Get the currently active cloud provider profile.

MCP Tool: get_active_profile


35. set_active_profile

Switch the active cloud provider profile.

MCP Tool: set_active_profile

  • profile_id (string, required): Profile ID to activate

36. schedule_task

Schedule a future task for a case (start or stop at a specific time).

MCP Tool: schedule_task

  • case_id (string, required): Case ID
  • case_name (string, required): Case name
  • action (string, required): Action to perform ("start" or "stop")
  • scheduled_at (string, required): Time in RFC3339 format (e.g., "2025-01-15T10:30:00Z")

37. list_scheduled_tasks

List all pending scheduled tasks.

MCP Tool: list_scheduled_tasks


38. cancel_scheduled_task

Cancel a pending scheduled task.

MCP Tool: cancel_scheduled_task

  • task_id (string, required): Task ID to cancel

Common Workflows

Deploy a proxy pool

# 1. Pull the template
redc pull aliyun/proxy

# 2. Plan the case (preview)
redc plan aliyun/proxy --var node=5 --var port=8388 --var password=MySecurePass

# 3. Start it
redc up <case_id>

# 4. Check outputs (IPs, passwords)
redc output <case_id>

Check running infrastructure

# List all cases
redc ps

# Get cost summary
# (via MCP) get_predicted_monthly_cost, get_balances

Orchestrated multi-service deployment

# redc-compose.yaml
services:
  proxy:
    template: aliyun/proxy
    variables:
      node: 3
      port: 8388
  c2:
    template: aws/ec2
    depends_on:
      - proxy
redc compose up
redc compose down

Summary

ActionCLI CommandMCP Tool
List templatesredc listlist_templates
Search registryredc search <q>search_templates
Pull templateredc pull <name>pull_template
List casesredc pslist_cases
Plan caseredc plan <tmpl>plan_case
Start caseredc up <id>start_case
Stop caseredc down <id>stop_case
Remove caseredc rm <id>kill_case
Get outputsredc output <id>get_case_outputs
SSH exec—exec_command
Cost estimate—get_cost_estimate
Account balance—get_balances
Compose upredc compose upcompose_up
Compose downredc compose downcompose_down
Schedule task—schedule_task

平台分布

OpenClaw

81.32%
按下载量换算2,410

安全审计

VirusTotal

可疑

ClawScan

可疑

Static analysis

通过

权限和风险

接触敏感数据

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills