Best use case
always-on is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
always on skill for handoffs
Teams using always-on should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/always-on/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How always-on Compares
| Feature / Agent | always-on | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
always on skill for handoffs
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Always On Skill ## How to use Do not stop working on this issue until there are no further subagents to run.
Related Skills
always-init
Universal task initializer that automatically loads PAI context for all user requests. Ensures complete context availability (contacts, preferences, protocols) before responding to any task. (project, gitignored)
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
partner-revenue-desk
Operating model for tracking, attributing, and accelerating partner-sourced revenue.
parallel-data-enrichment
Structured company and entity data enrichment using Parallel AI Task API with core/base processors. Returns typed JSON output. No binary install — requires PARALLEL_API_KEY in .env.local.
parallel-agents
Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.
paper-writing-assistant
Assist in drafting research papers and meeting notes, enforcing academic rigor and formatting.
pandas-data-manipulation-rules
Focuses on pandas-specific rules for data manipulation, including method chaining, data selection using loc/iloc, and groupby operations.
pagent
Guide for using pagent - a PRD-to-code orchestration tool. Use when users ask how to use pagent, run agents, create PRDs, or transform requirements into code.
page-annotator
AI驱动的网页标注工具，支持高亮元素和添加文字批注。智能防重复、自动滚动、碰撞检测。兼容 GitHub 等严格 CSP 网站。适用场景：(1) 标记网页元素进行讲解 (2) 添加文字批注和注释 (3) 代码审查和设计评审 (4) 教学演示和用户引导 (5) Bug 报告和问题标记
package-json-modification-protection
Protects lines with the specific 'Do not touch this line Cursor' comment within package.json.
orchestrator
Multi-agent orchestrator that delegates all work to specialized subagents. Enforces parallelism, tracks progress, and coordinates agent teams for complex tasks.
orchestrator-conductor
This skill should be used when the user asks to "orchestrate agents", "run /orchestrate", "manage parallel agents", "coordinate multiple agents", "decompose this task", or needs patterns for multi-agent workflows with parallel execution and task decomposition.