lore-development

Plugin lore-development from marketplace vibe-garden in rjroy/vibe-garden. Commands read from the repo's manifest — 1 month ago.

Skills (14)

• brainstorm

  Use when exploring before committing, thinking through trade-offs, or digesting sketches and diagrams. Triggers include "let's brainstorm", "what if we...", and "explore options". Bad ideas welcome, questions over answers, mistakes on purpose.

• define-validation

  Use to add validation criteria to a spec or plan. Triggers include "define validation", "how will we validate", "what should the AI check", and "add validation to this".

• design

  Use when the user has a specific architecture, tool, or technique in mind and wants to explore whether and how it applies. Not full-feature design but a focused technical investigation of one element. Triggers include "design this", "I want to use X for this", "how should this work technically", and

• implement

  Use when ready to build from the user's current request or intent, optionally informed by a spec, design, plan, or notes. Triggers include "implement this", "build this", "implement the request/intent", "continue implementation", and "resume where we left off".

• install-formula

  Install the reusable lore-development Beads formula into the current project. Use when a project should run the lore-development workflow through bd molecules.

• intent

  Use when the user wants to think through what to build and why. Produces a conversational record of intent and context, not a requirements contract. Triggers include "help me shape this idea", "what should we build", or "capture the intent".

• migrate

  Preview and, after explicit user confirmation, migrate pre-work and .lore/work lore layouts into historical intents, shared work, and gitignored local paths, converting legacy HTML artifacts to Markdown with original-byte backups. Does not migrate project files automatically.

• poke-holes

  Use when a spec, plan, design, or idea needs adversarial review to find what's wrong rather than what's right. Triggers include "poke holes in this", "tear this apart", "what am I missing", "stress test this", "find what's wrong", "challenge this", and "what could go wrong".

• prep-plan

  Use to think through an implementation approach with the user, discuss useful evidence, and optionally record a working plan. Input can be conversational intent, design, brainstorm, research, or a prompt. Triggers include "prep plan", "prepare a plan", "plan this", "make a plan", "plan the implement

• refactor

  Use to inspect a bounded area for code smells and discuss whether a behavior-preserving cleanup is worthwhile. Diagnosis only; implementation happens separately through simplify when the user asks to proceed.

• research

  Use when specifics matter more than general training knowledge, or when details are newer than the training cutoff. Triggers include "research this", "find documentation for", "look up how X works", "what's the current state of", and "what's the prior art".

• retro

  Use when completed work needs to be recorded as a lore artifact covering what happened, what surprised, what broke, and what drifted. Observation only, not interpretation. Triggers include "let's do a retro", "/retro", "review what happened", "capture what happened", and "write up the session".

• simplify

  Use when the user wants to simplify or clean up code without changing behavior. Accepts standalone scope or user-selected findings from /refactor.

• vision

  This skill should be used when the user wants to define the north star for a project — why it exists, what problems it solves, what it would never become. Suited for the start of a project or when direction feels unclear. Triggers include "define the project vision", "what should this project become

Subagents (6)

• bun-typescript-reviewer

  Reviews Bun and TypeScript implementations for requested behavior and material defects across daemon, Unix-socket, CLI, Next.js, and React boundaries.

• design-reviewer

  Reviews design documents with fresh context for weak decisions, missing trade-offs, and contracts that are not implementable.

• intent-reviewer

  Reviews intent notes with fresh context for faithful capture of the user's present what and why, without turning historical context into a contract.

• lore-researcher

  Use this agent when you need to search .lore/ for related prior work before starting an intent or plan. This agent surfaces useful historical context and operational learning without making old artifacts binding. Invoked automatically by /intent and /prep-plan, or manually when exploring what contex

• plan-reviewer

  Reviews implementation plans with fresh context for a feasible approach, scope fit, and useful project-specific evidence.

• rust-daemon-cli-reviewer

  Reviews Rust daemon and CLI implementations for requested behavior and material defects at Unix-socket and process-security boundaries.