stellar-build

Benchmark stellar-build skills to measure quality and the lift from optimization. Use when the user says "bench my skills", "bench-skills", "benchmark skills", "did optimization help", "measure my skills", "stellar-loop bench", or wants to quantify whether /optimize-skills actually improved things. Held-out eval prompts scored by an LLM judge, reproducible with fixed seeds. Fully local.

Explain and control the stellar-build learning loop — the system that improves your skills from how you use them. Use when the user says "learning loop", "how does the learning loop work", "what is the learning loop", "self-improving skills", "stellar-loop", "show my skill usage", "is tracing on", or wants an overview / status of the local trace-capture + optimize + bench cycle.

Compile your local stellar-build usage traces into sharper skills. Use when the user says "optimize my skills", "optimize-skills", "improve my skills from usage", "learn from my traces", "stellar-loop optimize", or wants the learning loop to refine installed skills based on how they've actually been used. DSPy-style prompt optimization over the local trace store at ~/.stellar/traces — fully local, reversible.

Rewrite a rough request into a sharp, structured prompt before acting on it. Use when the user says "reprompt this", "reprompt", "improve this prompt", "make this prompt better", "structure this request", or hands you a vague/underspecified ask you should sharpen first. Complements the automatic per-turn sharpener (the UserPromptSubmit hook) for explicit, heavier rewrites. Personalizes from ~/.stellar/profile.md when present.

Senior software engineer for story execution and code implementation. Use when the user asks to talk to Elliot or requests the developer agent.

Strategic business analyst and requirements expert. Use when the user asks to talk to Justin or requests the business analyst.

Create, update, or validate a PRD. Use when the user wants help producing, editing, or validating a PRD.

Technical documentation specialist and knowledge curator. Use when the user asks to talk to Bri or requests the tech writer.

Forensic case investigation with evidence-graded findings, calibrated to the input. Use when the user asks to investigate a bug, trace what caused an incident, walk through unfamiliar code, or build a mental model of a code area before working on it.

Product manager for PRD creation and requirements discovery. Use when the user asks to talk to Nicole or requests the product manager.

Create, update, or validate a product brief. Use when the user wants help producing, editing, or validating a brief.

System architect and technical design leader. Use when the user asks to talk to Tyler or requests the architect.

Facilitate interactive brainstorming sessions using diverse creative techniques and ideation methods. Use when the user says help me brainstorm or help me ideate.

Review code changes adversarially using parallel review layers (Blind Hunter, Edge Case Hunter, Acceptance Auditor) with structured triage into actionable categories. Use when the user says "run code review" or "review this code"

Create architecture solution design decisions for AI agent consistency. Use when the user says "lets create architecture" or "create technical architecture" or "create a solution design"

Break requirements into epics and user stories. Use when the user says "create the epics and stories list"

Plan UX patterns and design specifications. Use when the user says "lets create UX design" or "create UX specifications" or "help me plan the UX"

Execute story implementation following a context filled story spec file. Use when the user says "dev this story [story file]" or "implement the next story in the sprint plan"

UX designer and UI specialist. Use when the user asks to talk to Kaan or requests the UX designer.

Working Backwards PRFAQ challenge to forge product concepts. Use when the user requests to 'create a PRFAQ', 'work backwards', or 'run the PRFAQ challenge'.

Analyzes current state and user query to answer BMad questions or recommend the next skill(s) to use. Use when user asks for help, bmad help, what to do next, or what to start with in BMad.

Help users discover what to build on Stellar. Use when a user says "what should I build on Stellar", "Stellar app ideas", "I want to build on Stellar but don't know what", "Stellar startup ideas", "find me a Stellar project idea", "I'm new to Stellar and want to build something", or "what's hot on Stellar right now". Interviews user sharply, then proposes ranked ideas grounded in real ecosystem gaps from the LumenLoop 728-project database and current SCF funding patterns.

Surface current and recent Stellar Community Fund (SCF) round activity. Use when a user says "current SCF round", "what's happening with SCF", "active SCF submissions", "should I apply to SCF this round", "SCF deadline", "who is applying to SCF right now", "SCF round status", or "show me this round's submissions". Fetches live data from communityfund.stellar.org and cross-references with the LumenLoop ecosystem DB to flag repeat builders and category trends.

Map the competitive landscape for a Stellar project idea. Use when a user says "who are my competitors on Stellar", "competitive analysis Stellar", "what already exists in this space on Stellar", "show me similar Stellar projects", "is anyone else building this on Stellar", or "map the Stellar landscape for X". Queries the 728-project LumenLoop ecosystem database and Electric Capital developer activity to rank competitors by SCF funding history and repo activity.

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

Orchestrates group discussions between installed BMAD agents, enabling natural multi-agent conversations where each agent is a real subagent with independent thinking. Use when user requests party mode, wants multiple agent perspectives, group discussion, roundtable, or multi-agent conversation about their project.

Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven. Use when you need exhaustive edge-case analysis of code, specs, or diffs.

Walk through the devnet → mainnet deployment checklist for a Soroban contract or Stellar dApp. Use when a user says "deploy to Stellar mainnet", "going live on Stellar", "deploy my Soroban contract", "Stellar production deployment", "mainnet checklist", or "ship it on Stellar". Covers pre-deployment verification, deployment mechanics with stellar CLI, and post-deployment monitoring with Soroban-specific gates.

Meta-skill — browse and discover all installed stellar.new skills. Use when a user says "what skills do I have", "show me available skills", "what can I do", "find a skill for X", "which skill should I use", "help me navigate", "what does stellar.new do", or "where do I start". Lists skills by journey phase, surfaces the SKILL_ROUTER trigger phrases, and recommends the next skill given current context.