paveg/interrupt
dot_claude/skills/interrupt/SKILL.md
Delegate an interrupt task to a background agent in an isolated worktree. The main session continues uninterrupted. The agent implements, commits, pushes, and creates a PR. Use when a quick fix or small task needs to happen without losing current context.
$ install --global
skillsauthnpx skillsauth add paveg/dots interruptInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 16, 2026, 4:50 AM4.5s1 file scanned
SKILL.md
- name:
- interrupt
- description:
- |
- argument-hint:
- Task description (e.g., "fix the null check in auth middleware")
Interrupt Task
Delegate a task to a background agent running in an isolated git worktree. Your current session stays uninterrupted.
Phase 1: Validate & Prepare
Input: $ARGUMENTS
- If
$ARGUMENTSis empty or vague, ask the user to clarify the task - Confirm you are in a git repository
- Generate a branch name from the task description:
- Slugify: lowercase, replace spaces/special chars with hyphens, max 50 chars
- Prefix with
fix/orfeat/based on task nature
- Show the user: branch name, base (current HEAD), and task summary
- Proceed without waiting for confirmation (speed matters for interrupts)
Phase 2: Launch Background Agent
Launch an Agent with these parameters:
isolation: "worktree"— runs in a fresh worktree copyrun_in_background: true— does not block the main sessiondescription— short summary (3-5 words)
The agent prompt MUST include:
- The full task description
- Instruction to: implement the fix, make atomic commits, push the branch, create a PR via
gh pr create - Instruction to keep changes minimal and focused
- The base branch to target for the PR (usually
main)
Example agent prompt structure:
You are working in an isolated git worktree. Your task:
{task description}
Steps:
1. Understand the codebase context (read CLAUDE.md, explore relevant files)
2. Create a new branch: {branch-name}
3. Implement the fix/feature with minimal, focused changes
4. Commit with a descriptive message
5. Push the branch: git push -u origin {branch-name}
6. Create a PR: gh pr create --title "{title}" --body "{body}"
7. Report the PR URL as your final output
Phase 3: Confirm & Continue
After launching the agent:
- Tell the user the background task is running
- Mention the branch name for reference
- Remind them they'll be notified when it completes
- Suggest
wt lsto see active worktrees if they want to check on it - Resume the previous conversation context — the whole point is zero interruption
When the background agent completes:
- Report the PR URL to the user
- Suggest cleanup:
wt rm {name}or let the worktree auto-cleanup
Related Skills
paveg/empirical-prompt-tuning
development
VerifiedTrustedCommunity
Iteratively improve agent-facing text instructions (skills, slash commands, task prompts, CLAUDE.md sections, code-generation prompts) by having a bias-free executor run them and evaluating from both sides (executor self-report + caller-side metrics). Repeat until improvement plateaus. Use immediately after creating or significantly revising a skill/prompt, or when unexpected agent behavior is suspected to stem from ambiguous instructions.
3SKILL.mdUpdated Apr 21, 2026
paveg/x-post-craft
development
VerifiedTrustedCommunity
Create viral X/Twitter posts based on the official X algorithm (Phoenix/Grok). Generates and improves posts optimized for maximum engagement. Use when (1) creating X posts for products, services, or information, (2) improving existing post drafts, (3) designing thread structures for long content.
3SKILL.mdUpdated Apr 16, 2026
paveg/ui-design-standards
development
VerifiedTrustedCommunity
UI design quality standards and principles for frontend implementation and code review. Use when (1) implementing UI from design specs or mockups, (2) reviewing frontend/UI code, (3) creating new UI components, (4) building user interfaces for web or mobile apps. Complements frontend-design skills with quality enforcement.
3SKILL.mdUpdated Apr 16, 2026
paveg/trend-arbitrage
testing
VerifiedTrustedCommunity
End-to-end workflow for finding content, app, service, or product opportunities where search demand is high but quality supply is low (trend arbitrage). Use when: finding content gaps, keyword opportunities, niche research, analyzing whether a topic or idea is worth pursuing, or competitive gap analysis.
3SKILL.mdUpdated Apr 16, 2026