From atum-workflows
Execute complex features or parallel investigations with fresh context per sub-task. Use for 3+ file changes, long sessions, parallel debug, or any task needing consistent quality.
npx claudepluginhub arnwaldn/atum-plugins-collection --plugin atum-workflowsThis skill uses the workspace's default tool permissions.
Execute complex features or parallel investigations by decomposing them into atomic sub-tasks, each running in a subagent with a fresh context window.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Dispatches code-reviewer subagent to evaluate code changes via git SHAs after tasks, major features, or before merging, with focused context on implementation and requirements.
Execute complex features or parallel investigations by decomposing them into atomic sub-tasks, each running in a subagent with a fresh context window.
Feature implementation:
Parallel investigation/debug:
When this skill is invoked:
Read the user's feature request from: $ARGUMENTS (or ask if not provided)
Launch the fresh-executor agent to handle the decomposition and execution:
Use the Agent tool with:
- subagent_type: "fresh-executor"
- prompt: The full feature request with any context the user provided
- description: "Fresh execute: [brief summary]"
/fresh-execute Add JWT authentication with login, signup, and password reset endpoints to the Flask API
The agent will:
When facing multiple independent failures, dispatch one agent per problem domain:
/fresh-execute Fix 6 failing tests across agent-abort.test.ts, batch-completion.test.ts, and race-conditions.test.ts
The agent will:
Each agent needs: