Agent Claude Code
Use proactively when writing or editing C# (.cs) files. Applies project C# standards and runs quality checks.
Agent Claude Code
Use proactively when writing or editing C# (.cs) files. Applies project C# standards and runs quality checks.
Agent Claude Code
Use proactively when creating or editing diagrams, architecture visuals, or PlantUML (.puml, .plantuml, .pu) files. Selects the right diagram format, applies diagramming standards, and writes diagram files.
Agent Claude Code
Use proactively when writing or editing Flutter / Dart (.dart) files. Applies project Dart and Flutter standards and runs quality checks.
Agent Claude Code
Use proactively when writing or editing LLM prompts, Jinja templates (.j2, .jinja, .jinja2), or prompt files (.md, .txt). Reads model-specific standards and validates syntax.
Agent Claude Code
Use proactively when writing or editing Python (.py) files. Applies project python standards and runs quality checks.
Agent Claude Code
Use proactively when writing or editing React (.tsx/.jsx) files, Tailwind CSS classes, or shadcn/ui components. Applies project React standards and runs quality checks.
Agent Claude Code
Use proactively when writing or editing Swift (.swift) files. Applies project Swift standards and runs quality checks.
Agent Claude Code
Use when creating, updating, or rewriting a ClickUp task. Applies the ticket-writing skill for body content and maps attributes to native ClickUp fields via MCP. Introspects the target list before acting, asks the user for missing values instead of defaulting, and returns the task URL.
Agent Claude Code
Use proactively when writing or editing TypeScript (.ts) files. Applies project TypeScript standards and runs quality checks.
Command Claude Code
Sync the root repo and all submodules to their default branch and pull latest.
Command Claude Code
Generate or update docs/mission.md, docs/tech-stack.md, and docs/architecture.md from evidence-gated codebase exploration.
Hook Claude Code
One of 3 in settings.json
Runs before the agent uses a tool for Bash tool calls, executing rtk-rewrite.sh via bash. From Dynokostya/just-works.
Hook Claude Code
One of 3 in settings.json
Runs when the agent sends a notification, running afplay /System/Library/Sounds/Glass.aiff. From Dynokostya/just-works.
Settings file Claude Code
One of 3 in settings.json
Agent settings declaring 2 hook events (PreToolUse, Notification) and 16 allowed tools.
Skill Claude CodeCodex
Apply when writing or editing C# (.cs) files. Behavioral corrections for error handling, resource management, async patterns, data modeling, type safety, nullability, security defaults, and common antipatterns. Project conventions always override these defaults.
Skill Claude CodeCodex
Apply when writing or editing Dart (.dart) files. Behavioral corrections for null safety, async patterns, type system, error handling, and common antipatterns. Project conventions always override these defaults.
Skill Claude CodeCodex
Apply when implementing Domain-Driven Design patterns in Python (.py) files. Covers tactical patterns (entities, value objects, aggregates, domain events, repositories), layered architecture with dependency inversion, persistence strategies, validation boundaries, and common DDD anti-patterns. Best suited for projects…
Skill Claude CodeCodex
Apply when creating or editing prompts targeting Claude Fable 5 (model ID claude-fable-5). Covers effort-level selection, longer autonomous turns, brief-instruction steering, progress-claim grounding, action boundaries, parallel subagent orchestration, memory systems, early-stopping and context-budget mitigations…
Skill Claude CodeCodex
Apply when structuring or restructuring a Python backend by business capability (vertical slices) — laying out a new project, reorganizing a layered codebase, or drawing feature boundaries. Governs top-level layout; for the internals of a complex slice see ddd-architecture-python. Covers directory layout, feature…
Skill Claude CodeCodex
Apply when writing or editing Flutter widgets in Dart (.dart) files. Behavioral corrections for widget composition, BuildContext, state management, performance, lifecycle, and common antipatterns. Pairs with dart-coding for language rules. Project conventions always override these defaults.
Skill Claude CodeCodex
Apply when creating or editing prompts targeting the Gemini 3 family (3.0, 3.1 Pro, 3 Flash, 3.1 Flash-Lite). Covers prompt layering (system instruction + context + task), thinkinglevel tuning, structured output prompting, function calling guidance, grounding prompt wording, few-shot examples, long-context patterns…
Skill Claude CodeCodex
Apply when creating or editing prompts targeting GPT-5.6 (gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna). Covers lean prompting, outcome-first structure, reasoning-effort calibration (none through max), verbosity tuning, autonomy and approval boundaries, tool routing, programmatic tool calling, preamble and phase patterns…
Skill Claude CodeCodex
Forces the minimal working solution — least code, fewest files, no speculative abstraction. Channels a senior dev applying YAGNI: stdlib, native platform features, and existing dependencies over custom code. Three levels: lite (name the lazier option, user picks), full (enforce the ladder), ultra (deletion-first…
Skill Claude CodeCodex
Apply when creating or editing prompts targeting Claude Opus 5 (model ID claude-opus-5). Covers response and deliverable length, progress narration, over-verification removal, subagent damping, self-correction narration, scope constraints, effort-level implications, code review harnesses, XML structure, long-context…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: