naman10parikh/agentgrid / .claude/skills/loop-create
loop-create
VerifiedScaffold a new agent with the full file structure. Use when creating any new agent for the Energy platform. NOTE — ".loop" is a working name for the agent file format. When building, use a configurable extension constant.
Required Input
Ask the user for:
- Agent name — symbolic, one word (e.g., Ribbon, Compass, Quill, Forge)
- Workflow — one sentence describing what it automates
- UI type — chat | dashboard | tool-picker | flow-builder | game | custom
- Target user — who uses this? (e.g., "couples planning date nights")
Generated Structure
{AgentName}.loop/
├── SOUL.md # Identity, personality, boundaries
├── skills/
│ └── core.md # Primary workflow with steps
├── MEMORY.md # Bootstrap memory (<2000 tokens)
├── HEARTBEAT.md # Periodic checks and self-maintenance
├── ui-template.yaml # UI type, color scheme, layout
└── BRAND.md # Name rationale, tagline, landing copy
SOUL.md Template
# {AgentName}
## Identity
I am {AgentName}, powered by Energy. I help {target_user} by {workflow}.
## Personality
- Tone: [warm/professional/playful/direct]
- I use [first person / "we"]
- I proactively suggest next steps
- I remember past interactions
## Boundaries
- I never share user data across sessions without consent
- I escalate to a human when confidence < 70%
- I refuse harmful or illegal requests
Naming Convention
The name should be a symbolic element of the workflow:
- Ribbon (gifts) — wrapping, presentation
- Compass (dates) — direction, exploration
- Quill (content) — writing instrument
- Forge (dev) — creation, building
After generating, verify all files are parseable and memory is under 2,000 tokens.
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: 469k | 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: 321k | 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: 321k | 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: 321k | Updated | Claude CodeCodex | Verified | Install |