Skip to content
Security
Skill

/confirm-action

Ask the user to confirm before taking a significant action. Use before containment, remediation, or other impactful operations to ensure analyst approval. Presents options and waits for response.

BOOST
From plugin
ai-runbooks
12830 skills
Install
$ npx -y skills add dandye/ai-runbooks --skill confirm-action --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/confirm-action

Context preview

The summary Claude sees to decide when to auto-load this skill.

Ask the user to confirm before taking a significant action. Use before containment, remediation, or other impactful operations to ensure analyst approval. Presents options and waits for response.

SKILL.md

confirm-action.SKILL.md
type: Skill
name: confirm-action
description: "Ask the user to confirm before taking a significant action. Use before containment, remediation, or other impactful operations to ensure analyst approval. Presents options and waits for response."
personas: [all]
generated:
  by: human:mlutx
  at: 2026-01-12T17:23:43-06:00

Confirm Action Skill

Ask the user a confirmation question before proceeding with a significant action.

Inputs

  • `QUESTION_TEXT` - The specific question to ask (e.g., "Isolate endpoint WORKSTATION-01?", "Proceed with account disable for jsmith?")
  • *(Optional)* `RESPONSE_OPTIONS` - Predefined options for the user:
  • Default: `["Yes", "No"]`
  • Custom examples: `["Disable Account", "Reset Password", "Monitor Only"]`

Workflow

Step 1: Present Question

Display the question to the user with available options.

Step 2: Wait for Response

Collect the user's selection or custom input.

Step 3: Return Response

Provide the response back to the calling workflow for decision branching.

Outputs

| Output | Description | |--------|-------------| | `USER_RESPONSE` | The user's answer to the confirmation question |

When to Use

**Always confirm before:**

  • Isolating/quarantining endpoints
  • Disabling user accounts
  • Blocking IPs/domains at firewall
  • Terminating processes
  • Deleting files
  • Escalating to incident response
  • Closing cases as false positive (for high-severity alerts)

**May skip confirmation for:**

  • Adding comments to cases
  • Running enrichment queries
  • Generating reports
  • Read-only operations

Example Confirmations

**Containment:**

Question: "Isolate endpoint WORKSTATION-01 from the network?"
Options: ["Yes - Isolate", "No - Continue Monitoring", "Escalate First"]

**Account Action:**

Question: "User jsmith shows signs of compromise. What action?"
Options: ["Disable Account", "Force Password Reset", "Monitor Only", "Escalate to IR"]

**Case Closure:**

Question: "Close case 1234 as False Positive?"
Options: ["Yes - Close FP", "No - Keep Open", "Escalate to Tier 2"]
Read more
Ships withai-runbooks

This repository provides security operations runbooks and role-based guides for AI-assisted cybersecurity workflows.

Get the whole plugin

Other skills on ai-runbooks.