$ ~/registry/skill/microsoft-extensions-copilot-assets-prompts-skills-create-hook

SKILL

create-hook

Name: create-hook
Author: microsoft

Create hook JSON files for policy enforcement and agent lifecycle automation.

Stars

★ 193,531

Source

GitHub

Updated

2026-10-11

// securityLow risk

Prompt only, no code
Open source
Community-trusted· 193.5k

Running security audit…

Credentials
Network egress
Code execution
Data access
Supply chain

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "create-hook" skill from askskill:
1. Download https://raw.githubusercontent.com/microsoft/vscode/main/extensions/copilot/assets/prompts/skills/create-hook/SKILL.md
2. Save it as ~/.claude/skills/create-hook/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// examples

Pre-commit Policy Check Hook

Prompt

Generate a hook.json for an agent system that checks for sensitive information and missing required metadata before commit; block the action if validation fails and return clear error messages.

Expected

A hook.json for pre-commit validation with trigger timing, validation rules, blocking conditions, and error messages.

Post-task Auto Notification

Prompt

Create a hook.json that automatically sends a notification to a specified webhook after an agent task completes, including a result summary, execution duration, and status fields.

Expected

A post-task hook.json defining the notification target, message payload structure, and trigger conditions.

Session Startup Initialization Flow

Prompt

Generate a hook.json that automatically loads default context, checks required environment variables, and records initialization logs when an agent session starts.

Expected

A session-start hook configuration with initialization steps, environment checks, and logging actions.

// docs

Related skill: agent-customization. Load and follow hooks.md for template and principles.

Guide the user to create a hook in .github/hooks/.

Extract from Conversation

First, review the conversation history. If the user has been expressing concerns about agent behavior (e.g., "don't run this command", "always check before doing X", "inject this context"), generalize that into a hook. Extract:

Actions that should be blocked or gated
Context that should be injected at certain points
Automation needs at session start/end or tool use

Clarify if Needed

If no clear policy need emerges from the conversation, clarify:

What event should trigger this hook? (e.g. PreToolUse, SessionStart, Stop)
Should it block, warn, or inject context?
Does it need a companion script?

Iterate

Draft the hook JSON (and any scripts) and save them.
Identify the most ambiguous or weak parts and ask about those.
Once finalized, summarize what the hook enforces, suggest ways to test it, and propose related customizations to create next.

Remember to follow the agent-customization guidelines to create highly effective hooks.