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.
evals/evals.json
View on GitHub[
{
"prompt": "Walk me through the full Phase A exploration cycle.",
"should_trigger": true
},
{
"prompt": "How do I run the exploration workflow end to end?",
"should_trigger": true
},
{
"prompt": "Run the exploration workflow on this problem.",
"should_trigger": true
},
{
"prompt": "What are the phases of the exploration cycle and how do they connect?",
"should_trigger": true
},
{
"prompt": "Build a stakeholder map for the new initiative.",
"should_trigger": false
},
{
"prompt": "Create a Mermaid diagram of the approval process.",
"should_trigger": false
},
{
"prompt": "Deploy the latest build to production.",
"should_trigger": false
},
{
"prompt": "Fix the failing unit test in the auth module.",
"should_trigger": false
},
{
"prompt": "I have an idea I want to explore — let's start a discovery session.",
"should_trigger": true
},
{
"prompt": "Let's start a new exploration session for this feature.",
"should_trigger": true
},
{
"prompt": "There's an active exploration session in progress, what phase are we in?",
"should_trigger": true
},
{
"prompt": "Build me a React component for a data table.",
"should_trigger": false
},
{
"prompt": "Run the billing audit on my portfolio.",
"should_trigger": false
},
{
"prompt": "Let's kick off a new exploration session. I want to capture a brief for the problem I've been thinking about.",
"should_trigger": true
},
{
"prompt": "I have a rough idea to explore — it's somewhere between a process improvement and a new feature. Can you help me think it through and write it up?",
"should_trigger": true
},
{
"prompt": "I need to capture a session brief for a research spike we're starting on our data pipeline.",
"should_trigger": true
},
{
"prompt": "Help me draft an exploration brief — I want to understand the problem before we build anything.",
"should_trigger": true
},
{
"prompt": "Generate a commit message for these changes.",
"should_trigger": false
},
{
"prompt": "Summarize last week's meeting notes.",
"should_trigger": false
},
{
"prompt": "What time is it in New York?",
"should_trigger": false
},
{
"prompt": "Start a discovery session for my new idea.",
"should_trigger": true
},
{
"prompt": "Let's plan this out before we build anything.",
"should_trigger": true
},
{
"prompt": "I have an idea I want to explore — help me figure out what we're actually building.",
"should_trigger": true
},
{
"prompt": "Help me think through the scope before we start building.",
"should_trigger": true
},
{
"prompt": "Build a working demo of my scheduling app.",
"should_trigger": false
},
{
"prompt": "Generate user stories using our BRD.",
"should_trigger": false
},
{
"prompt": "Show me layout options for the dashboard.",
"should_trigger": false
},
{
"prompt": "Deploy the latest release to staging.",
"should_trigger": false
},
{
"prompt": "Evaluate and improve the exploration-session-brief skill.",
"should_trigger": true
},
{
"prompt": "Run an optimization loop on our exploration workflow to find what to improve.",
"should_trigger": true
},
{
"prompt": "The exploration cycle feels slow — help me identify which skill to optimize first.",
"should_trigger": true
},
{
"prompt": "Iterate on the business-requirements-capture prompts to improve BRD quality.",
"should_trigger": true
},
{
"prompt": "Generate a BRD from our session captures.",
"should_trigger": false
},
{
"prompt": "Refactor the login module for clarity.",
"should_trigger": false
},
{
"prompt": "Create user stories from the BRD.",
"should_trigger": false
},
{
"prompt": "Let's explore this idea I have for a staff scheduling tool.",
"should_trigger": true
},
{
"prompt": "I have an idea I want to explore — can we start a discovery session?",
"should_trigger": true
},
{
"prompt": "Where did we leave off with the customer portal exploration?",
"should_trigger": true
},
{
"prompt": "Let's start an exploration session for a new HR onboarding system.",
"should_trigger": true
},
{
"prompt": "Resume my exploration from yesterday.",
"should_trigger": true
},
{
"prompt": "Start a discovery planning session for my onboarding redesign.",
"should_trigger": true
},
{
"prompt": "I need to explore whether we should build or buy this reporting tool.",
"should_trigger": true
},
{
"prompt": "Help me think through this business problem — I'm not sure if we need software.",
"should_trigger": true
},
{
"prompt": "Fix the bug in the authentication service on line 42.",
"should_trigger": false
},
{
"prompt": "Run the test suite and report the results.",
"should_trigger": false
},
{
"prompt": "Review my pull request and suggest improvements.",
"should_trigger": false
},
{
"prompt": "How do I configure the GitHub Actions workflow?",
"should_trigger": false
},
{
"prompt": "Generate a BRD from the session captures we already have.",
"should_trigger": false
},
{
"prompt": "take my vibe app to production using an engineering harness",
"should_trigger": true
},
{
"prompt": "reengineer this prototype and prepare an engineering handoff",
"should_trigger": true
},
{
"prompt": "run the full vibe-to-engineering-handoff pipeline on localhost:3000",
"should_trigger": true
},
{
"prompt": "prepare this codebase for formal engineering via an execution harness",
"should_trigger": true
},
{
"prompt": "launch browser-harness to audit my frontend",
"should_trigger": false
},
{
"prompt": "extract domain models from the prototype",
"should_trigger": false
},
{
"prompt": "generate user stories from the BRD",
"should_trigger": false
}
]
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 |