gsd-execute-phase
Executes multi-step development plans in parallel phases.
Install
mkdir -p .claude/skills/gsd-execute-phase-acidicsoil && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12674" && unzip -o skill.zip -d .claude/skills/gsd-execute-phase-acidicsoil && rm skill.zipInstalls to .claude/skills/gsd-execute-phase-acidicsoil
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.
Execute all plans in a phase with wave-based parallelizationKey capabilities
- →Execute plans in a phase
- →Handle user input requests
- →Translate GSD `AskUserQuestion` to Codex `request_user_input`
- →Translate GSD `Task()` to Codex `spawn_agent`
- →Manage multi-select questions
- →Handle `spawn_agent` schema detection
How it works
The skill translates GSD workflow constructs like `AskUserQuestion` and `Task()` into Codex-compatible `request_user_input` and `spawn_agent` calls, managing user interaction and sub-agent execution.
Inputs & outputs
When to use gsd-execute-phase
- →Executing a multi-task development plan
- →Running parallel build or test phases
- →Managing complex agentic workflows
About gsd-execute-phase
Coordinates the execution of development tasks in logical phases using parallel processing. It maps GSD workflow interactions to the host environment, handling user input requests and fallbacks.
Execute all plans in a phase with wave-based parallelization
When not to use it
- →When `request_user_input` is rejected or unavailable and no non-interactive flag is present
- →When `spawn_agent` is restricted and automatic spawning is not permitted
Limitations
- →Codex has no `multiSelect` for questions
- →Codex `spawn_agent` does not create or bind a git worktree automatically
- →Codex restricts `spawn_agent` to cases where the user has explicitly requested sub-agents
How it compares
This skill provides a specific adapter for GSD workflows within Codex, enabling automated execution and interaction that would otherwise require manual translation or intervention.
Compared to similar skills
gsd-execute-phase side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| gsd-execute-phase (this skill) | 0 | 3mo | No flags | Advanced |
| workflow-automation | 3 | 7mo | Review | Intermediate |
| workflow-execute | 1 | 6mo | Review | Advanced |
| lfg | 0 | 3mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by AcidicSoil
View all by AcidicSoil →You might also like
workflow-automation
ruvnet
Workflow creation, execution, and template management. Automates complex multi-step processes with agent coordination. Use when: automating processes, creating reusable workflows, orchestrating multi-step tasks. Skip when: simple single-step tasks, ad-hoc operations.
workflow-execute
catlog22
Coordinate agent execution for workflow tasks with automatic session discovery, parallel task processing, and status tracking. Triggers on "workflow execute".
lfg
All-The-Vibes
Full autonomous engineering workflow
slfg
All-The-Vibes
Full autonomous engineering workflow using swarm mode for parallel execution
autonomous-agents
davila7
Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it's making them reliable. Every extra decision multiplies failure probability. This skill covers agent loops (ReAct, Plan-Execute), goal decomposition, reflection patterns, and production reliability. Key insight: compounding error rates kill autonomous agents. A 95% success rate per step drops to 60% b
agent-goal-planner
ruvnet
Agent skill for goal-planner - invoke with $agent-goal-planner