vfx-core

Plugin vfx-core from marketplace vfx-agent-toolkit in sideshowroberto/vfx-agent-toolkit. Commands read from the repo's manifest — 4 days ago.

Skills (14)

• brave-search

  Researches VFX topics with Brave Search - MCP web search for filtered URL lists, an LLM Context script for deep research with extracted page content, and image search for references. Use when searching for tutorials, docs, errors, plugins or software updates.

• development-management

  Runs Specification-Driven Development (spec-kit) workflows - agent creation, constitutional governance, roadmaps, specs and validation. Use when creating or auditing agents, writing a constitution, or validating compliance.

• gap-check

  Audits Claude's own knowledge gaps against a settled plan before building - sorts confident from guessed, researches public gaps, and lists unknowns for the user. Use after /grill-me, before a build session, or on 'gap-check' or 'check your assumptions'.

• git-guardrails-claude-code

  Sets up a Claude Code PreToolUse hook that blocks destructive git commands (push, reset --hard, clean -f, branch -D, checkout/restore .) before they run, with a Python hook that fails closed. Use when the user wants git safety hooks or to block git push/reset in Claude Code.

• grill-me

  Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

• loop-gauntlet

  Runs a build-until-it-matches loop in a DCC - an agent rebuilds a scene from reference images, scoring renders against a human-authored rubric until a stop rule fires. Use for 'iterate until it matches', Blender set rebuilds from refs, or writing or judging such a loop prompt.

• qwen-delegate

  Delegates tasks to the local Qwen model on Ollama so file content stays on the machine and out of Claude's context. Use for "ask Qwen" or "do this locally", NDA-safe file analysis, large-file summaries, boilerplate and BlinkScript drafts.

• skill-creation-update

  Writes, updates and validates Claude Code skills (SKILL.md) to the house standard - one-line YAML description, no retired top-level keys, traps-first body under 500 lines, retirement outside .claude/. Use when creating a skill, fixing or migrating an old-format one, or checking skills before a sync.

• task-observer

  Logs skill lessons (user corrections, broken rules, better workflows) to the observation log as they happen; applied only after owner review. Use when a skill is corrected, a documented rule fails, a better workflow emerges, or for "observation log" and "skill review". Session-start status comes fro

• vfx-plan

  Plans complex VFX builds by choosing Iterative, Spec-Driven or Safety-First mode, running an adversarial plan review and writing an actionable brief. Use on "help me plan" or "vfx plan", or before any multi-file or multi-system build.

• vfx-research

  Research VFX application APIs, errors, workflow integrations, and library examples using Brave Search and Context7. Use for Blender, Nuke, Houdini, Unreal, ComfyUI, and related development questions that need external evidence.

• vfx-workflow

  Apply this toolkit's audited application lessons when scripting DCC scenes, running ComfyUI workflows, or preparing cross-application VFX handoffs. Use for execution and integration work; use vfx-research for documentation lookup.

• wrap-session

  Runs the end-of-session wrap-up before clearing context - saves durable facts to memory, folds gotchas into skills, writes the session log and a handoff plan, cleans temp files. Use before /clear, when context runs low, or on "wrap up this session".

• youtube-transcript

  Retrieve available YouTube captions with timestamps and provenance, or analyze a video from its transcript. Use for YouTube links and transcript requests; this does not watch video frames or transcribe uncaptained audio.

Subagents (4)

• documentation-specialist

  Index-driven documentation updates for VFX application projects. Reads DOCUMENTATION_INDEX.md to understand structure, maintains consistency across related files, updates progress trackers, and creates session summaries. Use with "update documentation," "document session," or "index-driven update.

• python-specialist

  Python specialist for systematic multi-file work. Use when applying agent-skill templates ({{PLACEHOLDER}} substitution), batch search/replace or migrating code patterns across files, parameterizing per-asset scripts into one generic script, adding type hints (mypy strict, Protocols, TypedDict), con

• search-specialist

  Expert VFX research specialist using Brave Search API for technical documentation, tutorials, problem-solving, and industry intelligence across Unreal Engine, Blender, Houdini, Nuke, and ComfyUI

• testing-specialist

  Testing and validating Python scripts, skill scripts, and agent outputs. Use when requests include "test", "validate", "verify", "check", or "pytest". Validates JSON outputs, error handling, script independence, and generates test reports. Proactively invoked after refactoring to ensure functionalit

Hooks (1)

• SessionStart

  python "${CLAUDE_PLUGIN_ROOT}/skills/task-observer/scripts/observe_hook.py"

Similar plugins