parallel-execution
Executes independent development streams in parallel using isolated Git worktrees when safe.
Install
mkdir -p .claude/skills/parallel-execution-aultramen && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/19195" && unzip -o skill.zip -d .claude/skills/parallel-execution-aultramen && rm skill.zipInstalls to .claude/skills/parallel-execution-aultramen
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use when a plan or issue board has 2+ independent execution streams whose time saving exceeds coordination overhead. Dispatches agents in isolated git worktrees only after required delivery gates pass.Key capabilities
- →Execute independent tasks simultaneously
- →Dispatch agents in isolated Git worktrees
- →Verify independence of execution streams
- →Integrate work after successful independent verification
- →Prevent auto-resolution of conflicts
- →Ensure full tests and checks after integration
How it works
This skill dispatches agents to execute independent tasks in isolated Git worktrees after passing mandatory gates for selection, UI scale-out, and independence. It integrates the work only after successful verification and prevents auto-resolution of conflicts.
Inputs & outputs
When to use parallel-execution
- →Parallel feature development
- →Concurrent bug fixes
- →Scaling UI and backend tasks simultaneously
About this skill
Parallel Execution
Overview
Execute independent tasks simultaneously in isolated Git worktrees when the saved time justifies coordination overhead.
Announce: "I'm using the parallel-execution skill to run independent tasks in parallel."
Core principle: Parallel only works when tasks are truly independent. One shared file = sequential.
Reference Router
- Decide whether parallelism is allowed and worthwhile: prerequisites and selection
- Analyze files, group dependencies, preview worktrees, dispatch, integrate, and verify: process
- Counter unsafe shortcuts or optimistic independence claims: red flags
Load the full process only after the selection gate passes. Every parallel stream must use an isolated worktree or equivalent isolated workspace; if isolation is unavailable, execute sequentially.
Mandatory Gates
- Selection gate: Require a Git repository, 2+ independent execution streams,
clean state,
gitWorkflow.allowWorktree: true, and time savings greater than coordination overhead. No unresolved blocker or dependency may remain. - UI scale-out gate: For UI-bearing streams, the first vertical slice must be
verified against the real provider, the experience baseline must be
VALIDATED, every stream must pin the same contract version, and mock-only evidence cannot satisfy the gate. - Independence gate: Inspect actual target files and semantic dependencies
pairwise. Shared files, schemas, generated artifacts, migrations, lockfiles,
sequential contracts, or integration ordering stay in one sequential stream
with a single writer. Schedule only
Blocked by: Noneor verified dependencies. - Preview gate: Route remote, base, branch, clean-state, and worktree commands through
git-workflow-operation. Each parallel stream uses its own branch and workspace; never modify the main worktree during parallel work. - Dispatch gate: Give each agent its workspace, branch, ordered tasks, FSD/issue authority, verification contract, and required orchestration skill. Tasks inside one dependency group remain sequential.
- Approval gate: Never remove a worktree until its resolved target path is validated and the user approves. Preview merge, rebase, cleanup, push, and PR operations before mutation.
- Conflict gate: Never auto-resolve conflicts. A conflict invalidates the independence assumption; resolve manually and rerun the full suite.
- Integration gate: Inspect every branch, integrate using the FSD strategy,
then run full tests, contract/fixture/provider/consumer checks, and
verification-before-completion. Do not claim completion without merged-system integration verification.
Integration
Used by executing-plans in swarm mode. Use git-workflow-operation, subagent-orchestration, and verification-before-completion for workspace safety, task execution, and final integration.
When not to use it
- →When tasks are not truly independent
- →When isolation is unavailable for execution streams
- →When time savings do not exceed coordination overhead
Prerequisites
Limitations
- →Requires tasks to be truly independent
- →One shared file means sequential execution
- →Cannot auto-resolve conflicts
How it compares
This skill enables parallel execution of independent tasks in isolated environments with strict verification gates, reducing sequential development time compared to a single-stream approach.
Compared to similar skills
parallel-execution side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| parallel-execution (this skill) | 0 | 11d | No flags | Advanced |
| github-workflow-automation | 11 | 2mo | Review | Advanced |
| github-actions-templates | 7 | 3mo | No flags | Intermediate |
| hooks-automation | 3 | 3mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
github-workflow-automation
ruvnet
Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management
github-actions-templates
wshobson
Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.
hooks-automation
ruvnet
Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre$post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows.
cli-commands
windmill-labs
MUST use when using the CLI.
dev
atopile
LLM-focused workflow for working in this repo: compile Zig, run the orchestrated test runner, consume test-report.json/html artifacts, and discover/debug ConfigFlags.
toolhive-release
stacklok
Creates ToolHive release PRs by analyzing commits since the last release, categorizing changes, recommending semantic version bump type (major/minor/patch), and triggering the release workflow. Use when cutting a release, preparing a new version, checking what changed since last release, or when the user mentions "release", "version bump", or "cut a release".