Skip to content

aspiers/ai-config / .agents/skills/iterative-development

iterative-development

Verified

Implements sub-tasks from a task list at .ai/[feature]/tasks.md strictly one at a time, stopping after each to ask the user before starting the next, and keeping the task list and Relevant Files section current. Use when the user wants to review or approve each sub-task before work continues, rather than letting the agent run the list unattended with task-orchestration.

Iterative Development

Implement sub-tasks one at a time with user approval between each.

When to Use This Skill

Use this skill when:

  • Working through a task list (.ai/[feature]/tasks.md)
  • You want user feedback between each sub-task
  • Following a collaborative development workflow

Instructions

Sub-task Implementation

  • Update the task list as you work
  • Add new tasks as they emerge
  • Also update the corresponding prp.txt as appropriate
  • Maintain the "Relevant Files" section:
    • List every file created or modified
    • Give each file a one-line description of its purpose

Sub-task Iteration (IMPORTANT)

ONLY DO ONE SUB-TASK AT A TIME:

  • Only ever include one sub-task on your internal TODO list
    • This is VERY IMPORTANT!
  • Do NOT start or even consider the next sub-task until you ask the user for permission and they say "yes" or "y"

Stop after each sub-task and wait for the user's go-ahead for the next one.

Quality Controls

After completing each sub-task:

  1. Run linters according to repository guidelines
  2. Run tests according to repository guidelines
  3. If linting or testing fails, fix the issues before proceeding
  4. Ask for user approval before moving to the next sub-task

Communication

After each sub-task:

  1. Summarize what was accomplished
  2. Report any issues encountered
  3. Ask for permission to continue with the next sub-task

Workflow

1. Select one sub-task from tasks.md
2. Implement it completely
3. Run linters and tests
4. Report completion
5. Ask: "Ready for the next sub-task?"
6. Wait for "yes" or "y"
7. Repeat until all sub-tasks complete

Follow the above steps EXACTLY!!! NO EXCEPTIONS!!!

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: 466kUpdated Claude CodeCodexVerifiedInstall
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: 466kUpdated Claude CodeCodexVerifiedInstall
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: 319kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 319kUpdated Claude CodeCodexVerifiedInstall