rjroy/vibe-garden Skills

--- name: add-item description: This skill should be used when the user asks to "create an issue", "add an item", "add a bug", "create a task", "add to backlog", or invokes /compass-rose:add-item. Creates a new repository issue and adds it to the project with custom fields. allowed-tools: Skill(c

--- name: backlog description: This skill should be used when the user asks to "review backlog", "analyze backlog quality", "backlog health", "recommend items", or invokes /compass-rose:backlog. Reviews backlog items and analyzes quality to recommend best items to work on. allowed-tools: Skill(co

--- name: brainstorm description: This skill explores ideas and possibilities, recording "what if" scenarios. Use when brainstorming approaches, thinking through trade-offs, consuming sketches or diagrams into a session, or exploring before committing. Triggers include "let's brainstorm", "what if

--- name: ddp description: This skill visualizes flows, relationships, and architectures using Mermaid diagrams when text descriptions fail to communicate. Use when needing to see how data flows, map class relationships, visualize control flow, or explain architecture. Triggers include "draw this"

--- name: define-validation description: This skill defines AI validation criteria for work in progress. Use when validation wasn't defined in spec/plan, or when starting work without formal documentation. Triggers include "how will the AI validate", "define validation criteria", "what should the

This skill makes technical decisions for complex problems. Use when the "how" IS the problem - algorithms, data structures, system boundaries, performance, security. Triggers include "design this", "what's the algorithm for", "how should this work technically", "technical approach for", "architecture for".

This skill should be used when the user asks to "document this codebase", "excavate features", "what does this code do", "map out the system", "create specs from code", or needs to progressively discover and document features in an existing codebase. Invoked via /lore-development:excavate.

This skill files a structured issue to .lore/issues/ from an observation made during work. Use when the AI or user spots a bug, gap, or pattern worth tracking and wants to record it directly, bypassing the idea capture flow. Triggers include "file an issue", "log an issue", "record this issue", "create a lore issue", "track this as an issue", "flag this as an issue", "note this problem".

# GitHub API Scripts Skill ## Overview This skill provides Python scripts for reliable GitHub Project API operations. It replaces embedded GraphQL guidance in command markdown files with tested, reusable abstractions. ## Configuration Operations require a configuration file at `.compass-rose/con

This skill orchestrates implementation by delegating code, testing, and review to sub-agents while recording what happened. Use when ready to build from a spec, design, plan, or to resume from notes. Triggers include "implement this", "build this", "implement the spec", "implement the design", "implement the plan", "continue implementation", "resume where we left off".

--- name: next-item description: This skill should be used when the user asks "what should I work on", "next item", "highest priority", "what's ready", or invokes /compass-rose:next-item. Recommends the highest-priority ready item with rationale. allowed-tools: Skill(compass-rose:gh-api-scripts),

--- name: plan-breakdown description: This skill should be used when the user asks to "break down this plan", "decompose this plan", "create tasks from this plan", "plan-breakdown", "break plan into tasks", "scope this into tasks", "generate tasks from plan", or wants to generate task files from a

--- name: poke-holes description: This skill shifts posture to adversarial/rigorous mode for challenging ideas. Appropriate when the user wants critical analysis, not validation. Triggers include "poke holes in this", "tear this apart", "what am I missing", "stress test this", "find what's wrong",

--- name: prep-plan description: This skill builds implementation plans as persistent, reviewable lore artifacts. Use when ready to plan how to build something, break work into ordered steps, or decide what to delegate to sub-agents. Triggers include "prep plan", "prep-plan", "prepare a plan", "pl

--- name: reprioritize description: This skill should be used when the user asks to "reprioritize", "update priorities", "scan codebase for relevance", or invokes /compass-rose:reprioritize. Provides codebase-aware priority recommendations with batch update capability. allowed-tools: Skill(compas

--- name: research description: This skill gathers context from outside the project scope. Use for exploring external documentation, finding prior art, understanding libraries or frameworks, or gathering reference material. Triggers include "research this", "find documentation for", "what's the pr

--- name: retro description: This skill reviews completed work and records lessons learned. Use after completing a feature, when capturing insights before they fade, for periodic reflection on progress, or to graduate lessons to higher scopes. Triggers include "let's do a retro", "what did we lear

Reviews captured ideas from "idea:" prompts and refines them into structured issues through conversation. Use when you have accumulated ideas and want to process them. Triggers include "review ideas", "process ideas", "check my ideas", "what ideas do I have".

--- name: start-work argument-hint: [issue-number-or-url-or-"next"] description: This skill should be used when the user asks to "start work", "begin working", "work on issue", "start implementation", or invokes /compass-rose:start-work. Begins work on an item with XL/L escalation prompts and sta