When one task finishes, another can start automatically. This skill defines how to link skills together using simple trigger hooks. Developers can set hooks that run before, after, or on error of a skill's workflow.
There are three modes for triggers. Auto runs a follow-up task right away when the host supports it. Background records a non-blocking task that does not change files silently. Ask first asks the user before starting the next skill. Conditions can also be checked before triggering.
This setup helps create smooth, safe chains of actions. For example, after a planning skill finishes, it can trigger a self-improvement skill in the background, which then asks to create a pull request. The session logger runs automatically to track progress.
Global
mkdir -p ~/.claude/skills/auto-triggerProject
mkdir -p .claude/skills/auto-triggerSource Repository
Lark Drivelarksuite/cli
Organize Lark cloud files import export manage permissions and versions
Lark Eventlarksuite/cli
Stream Lark events in real time with simple CLI commands
Lark Workflow Meeting Summarylarksuite/cli
Turn your Lark meeting notes into organized weekly summaries with ease
Lark Approvallarksuite/cli
Easily manage Lark approval instances and tasks from your command line
Implementmattpocock/skills
Implement PRD or issue tasks with TDD tests typechecking and review
Executing Plansobra/superpowers
Load a plan review critically then execute each task with verifications
Subagent Driven Developmentobra/superpowers
Execute plans with fresh subagents per task and thorough reviews for fast iteration
Churn Preventioncoreyhaines31/marketingskills
Reduce customer churn with smart cancel flows and failed payment recovery