quick-task — for Claude Code quick-task, agentic-coding-tools, community, for Claude Code, ide skills, codex:rescue, $ARGUMENTS, vendor <name>, gemini, timeout <seconds>

v1.0.0
GitHub

Об этом навыке

Подходящий сценарий: Ideal for AI agents that need inspired by the /codex:rescue command from codex-plugin-cc. Локализованное описание: Collection of tools to simplify agentic coding # Quick Task Delegate a small ad-hoc task (bug investigation, quick fix, code explanation, small refactor) directly to any configured vendor. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Возможности

Inspired by the /codex:rescue command from codex-plugin-cc.
$ARGUMENTS - The task prompt to send to the vendor
--vendor <name — Dispatch to a specific vendor (e.g., codex, claude, gemini). Default: first
--timeout <seconds — Override default timeout (default: 300s / 5 minutes)
At least one vendor CLI installed and configured in agents.yaml

# Core Topics

for Claude Code codex:rescue $ARGUMENTS vendor <name> gemini timeout <seconds>
jankneumann jankneumann
[4]
[1]
Updated: 4/24/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 10/11

This page remains useful for teams, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution Quality floor passed for review
Review Score
10/11
Quality Score
66
Canonical Locale
en
Detected Body Locale
en

Подходящий сценарий: Ideal for AI agents that need inspired by the /codex:rescue command from codex-plugin-cc. Локализованное описание: Collection of tools to simplify agentic coding # Quick Task Delegate a small ad-hoc task (bug investigation, quick fix, code explanation, small refactor) directly to any configured vendor. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Зачем использовать этот навык

Рекомендация: quick-task helps agents inspired by the /codex:rescue command from codex-plugin-cc. Collection of tools to simplify agentic coding # Quick Task Delegate a small ad-hoc task (bug investigation, quick fix

Подходит лучше всего

Подходящий сценарий: Ideal for AI agents that need inspired by the /codex:rescue command from codex-plugin-cc.

↓ Реализуемые кейсы использования for quick-task

Сценарий использования: Applying Inspired by the /codex:rescue command from codex-plugin-cc
Сценарий использования: Applying $ARGUMENTS - The task prompt to send to the vendor
Сценарий использования: Applying --vendor <name — Dispatch to a specific vendor (e.g., codex, claude, gemini). Default: first

! Безопасность и ограничения

  • Ограничение: Vendor must have a quick dispatch mode defined
  • Ограничение: Print the vendor's raw stdout directly. Do NOT parse as JSON or structured findings.
  • Ограничение: Do NOT parse as JSON or structured findings

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

After The Review

Decide The Next Action Before You Keep Reading Repository Material

Killer-Skills should not stop at opening repository instructions. It should help you decide whether to install this skill, when to cross-check against trusted collections, and when to move into workflow rollout.

Install Path

Start With Installation And Validation

If this skill is worth continuing with, the next step is to confirm the install command, CLI write path, and environment validation.
Trusted Recheck

Cross-Check Against Trusted Picks

If you are still comparing multiple skills or vendors, go back to the trusted collection before amplifying repository noise.
Workflow

Move To Workflow Collections For Team Rollout

When the goal shifts from a single skill to team workflows, approvals, and repeatable execution, move into workflow collections.
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is quick-task?

Подходящий сценарий: Ideal for AI agents that need inspired by the /codex:rescue command from codex-plugin-cc. Локализованное описание: Collection of tools to simplify agentic coding # Quick Task Delegate a small ad-hoc task (bug investigation, quick fix, code explanation, small refactor) directly to any configured vendor. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

How do I install quick-task?

Run the command: npx killer-skills add jankneumann/agentic-coding-tools/quick-task. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for quick-task?

Key use cases include: Сценарий использования: Applying Inspired by the /codex:rescue command from codex-plugin-cc, Сценарий использования: Applying $ARGUMENTS - The task prompt to send to the vendor, Сценарий использования: Applying --vendor <name — Dispatch to a specific vendor (e.g., codex, claude, gemini). Default: first.

Which IDEs are compatible with quick-task?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for quick-task?

Ограничение: Vendor must have a quick dispatch mode defined. Ограничение: Print the vendor's raw stdout directly. Do NOT parse as JSON or structured findings.. Ограничение: Do NOT parse as JSON or structured findings.

↓ How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add jankneumann/agentic-coding-tools/quick-task. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use quick-task immediately in the current project.

! Reference-Only Mode

This page remains useful for installation and reference, but Killer-Skills no longer treats it as a primary indexable landing page. Read the review above before relying on the upstream repository instructions.

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

quick-task

Install quick-task, an AI agent skill for AI agent workflows and automation. Review the use cases, limitations, and setup path before rollout.

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Quick Task

Delegate a small ad-hoc task (bug investigation, quick fix, code explanation, small refactor) directly to any configured vendor. Bypasses OpenSpec entirely — no change-id, no proposal, no worktree.

Inspired by the /codex:rescue command from codex-plugin-cc.

Arguments

$ARGUMENTS - The task prompt to send to the vendor

Optional flags:

  • --vendor <name> — Dispatch to a specific vendor (e.g., codex, claude, gemini). Default: first available.
  • --timeout <seconds> — Override default timeout (default: 300s / 5 minutes)

Prerequisites

  • At least one vendor CLI installed and configured in agents.yaml
  • Vendor must have a quick dispatch mode defined

Steps

1. Parse Arguments

Extract the task prompt, optional --vendor flag, and optional --timeout flag from arguments.

2. Complexity Check

If the prompt exceeds 500 words OR references more than 5 file paths, emit a warning:

⚠ This task looks complex. Consider using /plan-feature for larger tasks.
Proceeding anyway...

The warning does NOT block execution.

3. Discover Available Vendors

python
1# Use the same discovery as review dispatch
2from review_dispatcher import ReviewOrchestrator
3
4orch = ReviewOrchestrator.from_coordinator() or ReviewOrchestrator.from_agents_yaml()
5reviewers = orch.discover_reviewers(dispatch_mode="quick")
6available = [r for r in reviewers if r.available]

If --vendor is specified, filter to matching vendor. If no vendors available, exit with error.

4. Dispatch Task

python
1results = orch.dispatch_and_wait(
2    review_type="quick",
3    dispatch_mode="quick",
4    prompt=task_prompt,
5    cwd=Path.cwd(),
6    timeout_seconds=timeout,
7)

5. Display Result

Print the vendor's raw stdout directly. Do NOT parse as JSON or structured findings.

If the vendor returned non-zero exit code, display error and stderr.

Output

  • Vendor stdout displayed inline (no files created)
  • No OpenSpec artifacts created
  • No git commits or worktree changes

Design Notes

  • Uses quick dispatch mode (read-write, no worktree isolation) — see Design Decision D3
  • Returns freeform text, not structured JSON — see Design Decision D4
  • This skill is intentionally minimal: prompt in → result out

Связанные навыки

Looking for an alternative to quick-task or another community skill for your workflow? Explore these related open-source skills.

Показать все

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

★ 333.8k
⑂ 0
Искусственный интеллект

widget-generator

Logo of f
f

Создание настраиваемых плагинов виджетов для системы ленты новостей prompts.chat

★ 149.6k
⑂ 0
Искусственный интеллект

flags

Logo of vercel
vercel

Фреймворк React

★ 138.4k
⑂ 0
Браузер

pr-review

Logo of pytorch
pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

★ 98.6k
⑂ 0
Разработчик