Claude Skills

Training manager for local GPU training - validate CUDA, manage GPU selection, monitor progress, handle checkpoints

Reference for Codex CLI usage patterns. Consult before calling codex via Bash.

This skill should be used when checking for naming conflicts between local skills (~/.claude/skills) and plugin-provided skills (~/.claude/plugins). Use to identify duplicate or similarly named skills that may cause inconsistent agent behavior.

Orchestrates development cycle through all stages and gates. Professional execution engine. No decision-making authority.

Calculate and interpret effect sizes for statistical analyses. Use when: (1) Reporting research results to show practical significance, (2) Meta-analysis to combine study results, (3) Grant writing to justify expected effects, (4) Interpreting published studies beyond p-values, (5) Sample size planning for power analysis.

Running precommit checks and build validation. ALWAYS use after ANY code changes.

Design rigorous experiments following best practices. Use when: (1) Planning research studies, (2) Grant proposal development, (3) Pre-registration, (4) Ensuring internal validity, (5) Meeting NIH rigor standards.

This skill should be used when the user asks to "map NPC relationships", "show character connections", "analyze NPC network", "who knows who", "faction relationships", "visualize NPCs", "NPC web", "character relationship map", or mentions "NPC connections", "social network", or "faction dynamics". Maps relationships between NPCs by faction, location, and document references to identify hub characters, isolated NPCs, and missing connections.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

This skill should be used when the user asks to "audit loot", "check treasure distribution", "review magic items", "is loot balanced", "treasure by level", "too much gold", "not enough magic items", "wealth check", or mentions "treasure placement", "loot tables", or "magic item distribution". Audits treasure and magic item placement across modules and character inventories to flag wealth imbalances, rarity mismatches, and loot gaps.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Format citations and bibliographies in multiple academic styles (APA, IEEE, Chicago, Harvard, MLA, Nature, Science). Use when: (1) Converting between citation styles for different journals, (2) Cleaning and standardizing bibliography entries, (3) Validating citation formatting before submission, (4) Generating properly formatted reference lists, (5) Checking citation consistency across manuscripts.

This skill should be used when the user asks to "check encounter balance", "review CR", "is this too hard", "is this too easy", "balance my encounters", "encounter difficulty", "TPK check", "deadly encounter", "party level check", or mentions "challenge rating", "encounter math", or "XP budget". Analyzes module encounters against party composition using D&D 5e math to identify deadly, trivial, or unbalanced fights.

Direct access to GitHub Copilot MCP server tools for AI-powered development assistance

AI collaboration workflow plugin - Implements automated collaborative development process between Claude and Copilot through structured 5-stage workflow

This skill should be used when the user asks to "create a D&D campaign", "make a new module", "add an NPC", "create an encounter", "search for monsters", "find D&D items", "list campaigns", "set up a dungeon crawl", "create a mystery adventure", "add loot to characters", "search for traps", "manage character inventory", "build an adventure", "populate a dungeon", "give items to players", "create a villain", "add treasure", "write session notes", "create a player character", "edit a character", "update character stats", or mentions "Mimir campaign", "D&D 5e authoring", or "dungeon master tools". Provides MCP tools for campaign management, module creation, character creation and editing, and catalog searching.

Load feature requirements, design, and implementation plan when working on in-progress features. Use when user is implementing code, debugging, asking about requirements, or making changes related to a tracked feature. Silently loads context files to inform responses.

Go database operations - SQL, ORMs, transactions, migrations

Community management best practices and patterns. Automatically loaded when handling community-related tasks to provide domain expertise.