.agents/skills/task-orchestration/SKILL.md
Orchestrate the complete development workflow for implementing sub-tasks from a task list. Use for end-to-end feature implementation with quality controls.
npx skillsauth add aspiers/ai-config task-orchestrationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Orchestrate the complete development workflow for implementing sub-tasks from a task list.
Use this skill when:
.ai/[feature_name]/tasks.mdDon't use this skill:
feature_name - Locates the relevant task list at .ai/[feature_name]/tasks.mdsubtask_number - The specific sub-task number to implementIf feature_name is not provided:
.ai/*/tasks.mdIf subtask_number is not provided:
CRITICAL: Follow this exact sequence. NO EXCEPTIONS!
Implement: Use the task-implementer skill to implement the selected sub-task
Lint: Use the code-linter skill to run all appropriate linters according to repository guidelines
Test: Use the test-runner skill to run all appropriate tests according to repository guidelines
Fix Issues: If linting or testing fails, attempt to fix the issues. Do NOT proceed until both pass
Mark Complete: Update the task list by changing [ ] to [x] for the completed sub-task. If all sub-tasks under a parent task are complete, also mark the parent task as complete
Stage Changes: Use the git-stager skill to stage relevant changes, ensuring to include the updated tasks.md file
User Review: Ask the user to review changes and approve with "good" or "vibe". If user responds with "vibe", skip this step for future iterations in the session
Commit: ONLY after user approval, use the git-committer skill to commit with a proper message
Continue: Select the next incomplete sub-task and repeat from step 1
This orchestrator works closely with:
task-implementation - For actual code implementationcode-linting - For code quality checkstest-running - For test executiongit-staging - For staging changesgit-commit - For creating commitsdevelopment
Run tests according to repository guidelines. Use after linting passes, before staging changes.
development
Implement a single sub-task from a task list. Use when working on feature development with existing task lists.
data-ai
Generate a detailed task list from a PRP. Use after a PRP is created and ready for implementation planning.
development
Create subagent definitions for Claude Code and OpenCode that delegate to skills. Use when creating new subagents or refactoring existing ones to follow the delegation pattern.