parallel-task-spark
π―Skillfrom am-will/codex-skills
|Parallel task executor that orchestrates subagents for concurrent task processing.
Overview
Parallel Task Spark (Sparky) is a skill from the CodexSkills collection that serves as an orchestrator for subagents, parsing plan files and delegating tasks to parallel Sparky subagents based on task dependencies. It launches tasks in waves, ensuring correct execution order while maximizing parallelism, and updates plan documents with completion logs after each task.
Key Features
- Wave-Based Parallel Execution - Launches unblocked tasks in parallel waves, respecting dependency chains between tasks
- Plan File Parsing - Reads and parses markdown plan files to extract task IDs, names, dependencies, acceptance criteria, and validation steps
- Subagent Orchestration - Delegates each task to a dedicated Sparky-role subagent with full task context and instructions
- Automatic Plan Updates - Subagents update the plan document with work logs, modified files, and error notes upon task completion
- Selective Task Execution - Supports running specific task subsets from a plan, automatically including required dependencies
Who is this for?
This skill is for developers using multi-agent orchestration who need fine-grained parallel task execution with automatic progress tracking. It is ideal for teams running complex implementation plans where multiple independent tasks can be worked on simultaneously by AI subagents, with each task's completion status logged directly in the plan file.
Same repository
am-will/codex-skills(19 items)
Installation
npx vibeindex add am-will/codex-skills --skill parallel-task-sparknpx skills add am-will/codex-skills --skill parallel-task-spark~/.claude/skills/parallel-task-spark/SKILL.mdSKILL.md
More from this repository10
Collection of agent skills for planning, documentation access, frontend development, and browser automation, featuring multi-agent orchestration with planner, parallel tasks, and LLM council capabilities.
Context7 documentation fetcher skill for retrieving current library documentation via Context7 API, proactively looking up APIs for React, Next.js, Supabase, and other libraries instead of relying on outdated knowledge
Frontend design skill for creating distinctive, production-grade web interfaces with high design quality, avoiding generic AI aesthetics through bold creative choices and exceptional attention to detail
Creates comprehensive, phased implementation plans with sprints and atomic tasks for planning features, breaking down work, and building structured roadmaps.
Collection of agent skills for planning, documentation access, frontend development, and browser automation, featuring multi-agent orchestration with planner, parallel tasks, and LLM council capabilities.
Reads and searches GitHub repository documentation via the gitmcp.io MCP service, converting GitHub URLs to documentation endpoints.
Detailed implementation planning skill that creates phased plans with sprints and atomic tasks, covering codebase research, requirements clarification, and structured implementation phases for bugs, features, or tasks
Collection of agent skills for planning, documentation access, frontend development, and browser automation, featuring multi-agent orchestration with planner, parallel tasks, and LLM council capabilities.
Queries the OpenAI developer documentation MCP server via CLI (curl/jq) to search, browse, and fetch authoritative docs for the OpenAI API, SDKs, ChatGPT Apps SDK, Codex, and MCP integrations with up-to-date official guidance.
A collection of Codex/agent skills for planning, documentation access, frontend development, and browser automation, including parallel task execution, LLM council multi-agent orchestration, Context7 doc fetching, and Gemini Computer Use browser control.