Claude Skills by rjroy

The lore directory redesign names an extraction skill that surfaces mistakes from build artifacts (especially retro notes) at design time, with a human gate, and promotes confirmed mistakes into `.lore/learned/`. The shape is sketched in the redesign brainstorm but not designed.

Use when extracting knowledge from .lore/ artifacts into the reference wiki. Converts work artifacts (retros, specs, plans, research, notes) into structured HTML wiki pages grouped by knowledge type. Triggers include "ingest this", "extract knowledge from", "add this to the wiki", "update the reference from", and "populate the field guide".

This skill is used when the project wiki needs a health check. Triggers include 'lint the wiki', 'check wiki health', 'run field-guide lint', 'are there stale wiki pages', 'find orphaned pages', 'check for contradictions in the wiki'.

Use when asking questions about the project wiki, querying accumulated knowledge, searching project decisions or lessons. Triggers include "query the wiki", "what does the wiki say about", "search project knowledge", and natural language questions directed at the field-guide wiki.

Use when a plan exists and needs validation gates added to each step before implementation begins. Produces task files that implement can consume. Triggers include "break down this plan", "add validation to the plan steps", "plan-breakdown", and "gate this plan".

This skill should be used when the user wants to clean up code without changing behavior. Dispatches cleanup agents, runs tests to verify behavior is preserved, then runs code review. Triggers include "simplify this", "clean up this code", "refactor without changing behavior", "reduce complexity".

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", "create a vision document", "what are we building toward".

Brainstormed, specified, and built the `/implement` skill for lore-development. The skill orchestrates implementation by delegating to sub-agents while recording notes as retro fuel. Went from brainstorm through spec through skill creation in one session.

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.

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.

This skill provides Python scripts for reliable GitHub Project API operations. It replaces embedded GraphQL guidance in command markdown files with tested, reusable abstractions.

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.

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.

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 status tracking.

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 we...", "explore options for", "think through possibilities".

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", "visualize how", "diagram the flow", "show me the architecture", "I can't hold this in my head".

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 AI check", "validation for this work".

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 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".

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", "challenge this", "play devil's advocate", "what could go wrong".

This skill builds implementation plans as persistent, reviewable lore artifacts. Use when ready to plan how to build something. Triggers include "prep plan", "prep-plan", "prepare a plan", "plan this", "make a plan", "how should we build this", "plan the implementation".

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 prior art", "look up how X works".

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 learn", "review what happened", "capture lessons from", "graduate lessons".

This skill defines requirements and success criteria for features. Use when capturing requirements, defining what "done" looks like, or documenting constraints. Triggers include "write a spec for", "define the requirements", "what should this do", "capture the requirements".

This skill performs periodic hygiene on the .lore/ directory through four modes: status (verify/update document status), tags (unify tags, find connections), filenames (convention consistency, rename suggestions), directories (structure optimization). Use when documents have accumulated, status fields are stale, or organization needs attention. Triggers include "tend the lore", "check document status", "lore hygiene", "what's stale", "review lore health", "tag audit", "organize lore".

This skill scans available agents and creates/updates the project's agent registry. Use when setting up lore-development in a new project, when new agents become available, or when you want to customize which agents are relevant. Triggers include "update lore agents", "set up agents for this project", "which agents are available", "configure project agents".

Scans specs for stubs and generates outstanding stub index. Use when reviewing spec coverage, before starting new specification work, or after completing a specification. Triggers include "update stubs", "check stubs", "stub index", "outstanding stubs".