gameassets
claudeSearch and deliver from a local game-asset library. Indexes packs and individual assets by concept taxonomy, licence and the work each needs before it is usable.
1 skill · 5 commands · 1 MCP server
Drive a live Blender session from Claude Code. Model procedurally with Blender Python, generate organic meshes through a pluggable backend (your own GPU or a paid API), and gate every result on real geometry - non-manifold edges, topology, UVs, scale, polycount - before it can be exported.
Plugin blender from marketplace lilo-labs-plugins in LiLo-Labs/claude-code-plugins. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.
blenderUse when the user wants to model, generate, inspect, fix or export 3D assets in Blender - building geometry procedurally with Blender Python, generating organic meshes from a text prompt, checking a mesh for non-manifold edges, topology, UVs, scale or polycount, rendering a turnaround to judge a res
/blender:blender-agentHand a whole asset to a headless Claude that drives Blender unattended
/blender:blender-checkMeasure the geometry in the scene and report what would fail downstream
/blender:blender-exportVerify then export the scene or selected objects to a target format
/blender:blender-makeModel or generate an asset in Blender, then render, verify and report it
/blender:blender-statusCheck the Blender connection, the configured mesh backend and what it costs
blenderruns: python3 ${CLAUDE_PLUGIN_ROOT}/blendpipe/mcp_blender.py
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/guard_spend.py"
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/guard_export.py"
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/guard_export.py"
Search and deliver from a local game-asset library. Indexes packs and individual assets by concept taxonomy, licence and the work each needs before it is usable.
1 skill · 5 commands · 1 MCP server
Review a pull request as a conversation instead of a diff. Publishes the request as a page you can talk to Claude inside, then writes the discussion back to the PR and merges on your approval.
1 skill · 2 commands · hooks
Paint a 3D model for multi-filament printing from a single command. Finds each feature by looking from many angles and lightings, lets the mesh's own geometry draw every boundary, iterates with you to confirm what they are, offers colour plans, and writes an Orca/Bambu-ready 3MF with the geometry preserved byte-for-byte.
1 skill · 1 command · hooks
Capture thoughts as a checklist during conversations and surface them to Claude at the right time
1 skill · 1 command · hooks
Turn one character image into a finished, engine-ready sprite sheet. Vision rigs the character into parts and joints, a deterministic skeletal animator draws fifteen animations and 8-direction movement from those parts, and the build measures its own output: a clip that comes apart has the responsible swing damped and reported, a transform is not allowed to break what the artist drew in one piece, and a walk keeps its feet on the floor. Exports to Unity, Godot, Phaser, GameMaker, RPG Maker and Unreal with every output frame provably built from the source's own palette.
1 skill · 1 command
Interactive visual architecture diagrams that stay in sync as Claude works. Auto-layout, live SSE updates, comment-driven interrupts.
1 skill · hooks
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Token usage tracking, model cost attribution per agent, budget alerts, and optimization recommendations
24 skills · 1 command · 1 agent · hooks
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Install the "Architecture & Domain Modeling" workflow plugin from Agentic Awesome Skills.
13 skills
Independent auditing for AI agents, open source. Claude discovers your setup, confirms the cost, and audits your agent against the one question other tools skip: is it doing the job it's supposed to do, given your business rules and org structure? Test any model (Anthropic, OpenAI, Gemini, Azure, Bedrock, …) graded by self, one independent judge, or a cross-vendor panel; each provider is billed to its own account via a key in your settings, never the command line. Results render as an interactive artifact (with a static-report fallback).
1 skill · hooks
Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.
10 skills · 2 commands · 3 agents
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.