simonepri/ifttt-lint / .agents/skills/execute
execute
VerifiedExecute a plan file — parse phases, spawn parallel subagents, handle failures.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.3 KB |
SKILL.md
View on GitHub---
name: execute
description: Execute a plan file — parse phases, spawn parallel subagents, handle failures.
allowed-tools: Bash, Read, Glob, Grep, AskUserQuestion, Agent, Edit, Write
---
# Execute
Execute a plan file produced by `/plan`. $ARGUMENTS is the path to the plan file.
1. **Parse**: read the plan file. Extract the phases and tasks. Each phase contains independent tasks that can run in parallel.
2. **Execute phase by phase**: for each phase:
- **Independent tasks** (touching separate files/modules): spawn a subagent per task. Give each subagent the plan file path, its assigned task, and the interfaces it needs to implement.
- **Interdependent tasks** (shared state, cross-cutting concerns): use an agent team instead — agents share a task list and coordinate directly, which avoids integration conflicts.
- Wait for all agents in the phase to complete before starting the next phase.
3. **Handle failures**: if a subagent gets stuck or goes off track, kill it, revert only that task's changes (not the entire branch — other tasks in the phase may have succeeded), and spawn a fresh one with adjusted instructions. If a task fails repeatedly (3 attempts), stop and report the failure — don't block other phases that don't depend on it.
4. **Report**: return a summary of completed tasks and any failures.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |