richfrem/agent-plugins-skills / plugins/agent-exploration-cycle/.apm/skills/running-exploration-cycle
running-exploration-cycle
VerifiedRuns the business exploration cycle end to end: starts or resumes a session (intake interview, session brief), enforces the Discovery Plan HARD-GATE, routes the four phases (Discovery Plan, Visual Blueprinting, Prototype, Handoff) to the sibling skills and keeps session state. Use when the user says "let's explore this idea", "I have an idea I want to explore", "help me plan this out", "start discovery", "resume my exploration", "where did we leave off", or starts any conversation about a need, problem or idea before building. Not for hardening an existing prototype (use reengineering-vibe-code) or for engineering build work.
references/using-exploration-cycle.md
View on GitHub# Using Exploration Cycle (`using-exploration-cycle`) (absorbed skill)
> Absorbed from the retired `using-exploration-cycle` skill into `running-exploration-cycle`; the full original body follows.
> Original trigger description: Use when starting any conversation - establishes how to find and follow the business exploration workflow.
Front-door dispatcher ensuring all incoming conversation requests check active exploration state and route through the governed phased exploration workflow.
## Contents
- [Critical Constraints](#critical-constraints)
- [Quick start](#quick-start)
- [Workflow](#workflow)
- [Verification](#verification)
## Critical Constraints
1. **Subagent Exclusion**: If dispatched as an isolated subagent (via `dispatch.py`) to execute a specific task, skip this skill entirely.
2. **Mandatory State Gate**: Before answering any user message or scoping request, verify active exploration state. If a session is in progress, route through the active phase of `exploration-workflow`.
3. **Database Sovereignty**: The SQLite state database is the absolute authority; `exploration/exploration-dashboard.md` is a read-only projection. Never rely on conversational memory for gate passage.
4. **Proactive Review During Waits**: Review upstream phase artifacts (discovery plans, visual captures, specs) during subagent execution waits.
## Quick start
Check whether an active exploration dashboard exists:
```bash
test -f exploration/exploration-dashboard.md && cat exploration/exploration-dashboard.md || echo "No active exploration session"
```
## Workflow
1. **Inspect Dashboard**: Check for `exploration/exploration-dashboard.md`.
2. **Evaluate Status**:
- If `Complete`: Session ended. Answer normally or offer new exploration.
- If `In Progress`: Identify current phase and yield control to `exploration-workflow`. Never answer in freeform prose.
- If absent: If prompt expresses exploration intent ("I want to build...", "explore..."), bootstrap session via `exploration-workflow`.
3. **Continuous Review**: During execution or agent waits, verify artifact consistency and cross-phase alignment.
## Verification
Verify exploration session state and dashboard synchronization:
```bash
python3 scripts/state_engine.py status # run from the running-exploration-cycle skill folder
```
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 |