Skill Claude CodeCodex needs its repo
Judge whether a generated mesh is fit to ship in a browser game, from the same rendered sheet the orientation review uses.
Skill Claude CodeCodex
Choose how to build a 3dscene asset. Do not default to one pipeline for every task: what the user specified about the scene's appearance matters more than the scene type, and generative reconstruction is the least stable route here.
Skill Claude CodeCodex needs its repo
Use this Skill when a game plan requires dialogue, voice lines, sound effects, foley, ambience, or other offline WAV assets. This is asset generation, not a runtime audio-playback contract; use the selected engine context after an asset has passed review.
Skill Claude CodeCodex needs its repo
Use this Skill for text-to-video, first-frame-to-video, first/last-frame transitions, and reference-image-conditioned CG-video generation. Generate video only after the game plan defines its narrative purpose, visual style, shot, duration, and acceptance criteria.
Skill Claude CodeCodex
Convert game CG intent and optional media references into validated, model-specific directing envelopes for opening, cutscene, ultimate, or promo clips. Use for standalone CG prompt direction or as a child capability of a game-generation Harness. Supports T2VA/text-only, I2VA/first-frame image…
Skill Claude CodeCodex needs its repo
Use this Skill when a game plan needs a single-subject concept image, a character reference cleaned for image-to-3D, or a front-facing transparent T-pose image for downstream character reconstruction. T-pose generation is an image-generation and image-editing task; it is not a separate asset category.
Skill Claude CodeCodex
Reconstruct a skeleton from calibrated mesh projections and sequential VLM joint annotations, then fit joints and skin weights. Generate motion from joint-position trajectories, rhythm and contact constraints through IK; refine bone orientation against the action, then export, retarget and validate on the target mesh.
Skill Claude CodeCodex
Create and control reusable game VFX in Unreal Engine 5 or Unity, including smoke, fire, explosions, dust, stylized ink/frost/cyber effects, and action-attached effects. Use for environmental or combat VFX, Niagara, Unity ParticleSystem, VFX lifecycle, animation/socket binding, or engine code that must reuse an…
Skill Claude CodeCodex
Turn requirements or a script into an original playable story, a chronological chapter plan, chapter-scoped assets and UI layouts, and traceable generation tasks.
Cursor rule Cursor
DataFlow WebUI backend development. Activate when editing FastAPI backend code — endpoints, services, schemas, or config.
Cursor rule Cursor
When using jsonschema in FormatStrPromptedGenerator, PromptedGenerator, or operators.json to constrain LLM structured output.
Cursor rule Cursor
DataFlow WebUI frontend development. Activate when editing Vue 3 frontend code — components, views, stores, router, or API client.
Cursor rule Cursor
Strict change policy for DataFlow WebUI frontend and backend. Limits what modifications are allowed.
MCP server Claude CodeCodexCursor +2
MCP server "dataflow", hosted remotely at localhost, as configured in OpenDCAI/DataFlow-WebUI.
Skill Claude CodeCodex
Reference documentation for DataFlow's coretext operators — 8 generators, 3 filters, 2 refiners and 5 evaluators. Read by generating-dataflow-pipeline when a task needs an operator beyond the six core primitives. This is a reference package, not a workflow: it is consulted, never invoked directly.
Skill Claude CodeCodex
Reference documentation for the BenchDatasetEvaluatorQuestion operator. Extended version of BenchDatasetEvaluator with question and subquestion support. Use when: evaluating answers with question context or multiple subquestions.
Skill Claude CodeCodex
Reference documentation for the BenchDatasetEvaluator operator. Covers the constructor, two comparison modes (match/semantic), and pipeline usage. Use when: comparing predicted answers against ground truth answers in benchmark evaluation.
Skill Claude CodeCodex
Reference documentation for the PromptedEvaluator operator. Use when: scoring text quality with LLM without filtering rows.
Skill Claude CodeCodex
Reference documentation for the Text2QASampleEvaluator operator. Use when: evaluating QA pair quality across multiple dimensions.
Skill Claude CodeCodex
Reference documentation for the UnifiedBenchDatasetEvaluator operator. Use when: evaluating model answers on benchmark datasets.
Skill Claude CodeCodex
Reference documentation for the GeneralFilter operator. Covers the constructor, rule-based filtering logic, and pipeline usage notes. Use when: filtering rows based on column value conditions that can be expressed as lambda functions without LLM calls.
Skill Claude CodeCodex
Reference documentation for the KCenterGreedyFilter operator. Covers the constructor, K-Center Greedy algorithm behavior, embedding serving requirements, and pipeline usage notes. Use when: downsampling a large dataset by semantic diversity using embedding vectors.
Skill Claude CodeCodex
Reference documentation for the PromptedFilter operator. Covers the constructor, actual scoring and filtering behavior, and pipeline usage notes. Use when: filtering rows based on LLM semantic quality judgment rather than simple rule-based conditions.
Skill Claude CodeCodex
Reference documentation for the BenchAnswerGenerator operator. Covers the constructor, full run() signature, actual generation behavior, and integration notes for unified bench evaluation pipelines. Use when: generating model answers from benchmark question rows before passing the dataframe into…
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: