Speckit Swarm
Skill by heldinhow
Why use this skill?
Boost productivity with Speckit Swarm, an OpenClaw skill that uses multi-agent orchestration and parallel task decomposition to automate complex software development workflows.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/heldinhow/speckit-swarmWhat This Skill Does
Speckit Swarm is an advanced agent orchestration system designed for the OpenClaw ecosystem. It implements a sophisticated 'oh-my-opencode' inspired architecture that allows the AI to handle complex, multi-stage development tasks by breaking them into parallel chunks. By using the 'Ultrawork' (ulw) mechanism, the skill automatically detects when a user needs heavy lifting and triggers a multi-agent workflow. The system relies on specialized personas—Sisyphus, Hephaestus, Oracle, Librarian, and Explore—each optimized for different stages of the software development lifecycle, from architectural design and deep coding to rapid file scouting.
Installation
To install Speckit Swarm directly into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/heldinhow/speckit-swarm
Ensure you have the latest OpenClaw runtime installed, as this skill utilizes parallel_spawn and advanced session management features.
Use Cases
This skill is ideal for developers tackling large-scale refactors, complex feature implementations, or deep system debugging. Use the 'Ultrawork' mode for tasks that involve multiple modules or require extensive research before implementation. It is particularly effective for teams looking to automate routine but complex coding tasks without manual oversight.
Example Prompts
- "ulw refactor the entire authentication middleware and update all dependent API routes to use the new session store."
- "sessions_spawn task: 'Investigate memory leaks in the data-processing worker' model: 'minimax-m2.5' thinking: 'high' persona: 'oracle'"
- "ulw build a comprehensive unit test suite for the new billing module including edge cases and integration scenarios."
Tips & Limitations
When using 'ulw', ensure your task description is descriptive enough for the Task Planner to create accurate sub-chunks. While the system is highly autonomous, the Sisyphus orchestrator acts as the primary brain; consider providing clear end-goals to prevent scope creep. Note that intensive parallel tasks may consume more tokens or processing time than standard serial requests. Always verify outputs when utilizing the deep worker (Hephaestus) for critical production code changes.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-heldinhow-speckit-swarm": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, code-execution