New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Cast

by guaardvark in guaardvark/guaardvark

Build consistent characters, environments and props in Guaardvark's Cast Library and train LoRAs for them locally (reference photos → vision bible → sample plan → approved samples → training).

MITAuto-check passedAI & LLM Engineering

Install Cast

skills CLI
$ npx skills add guaardvark/guaardvark --skill cast -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install guaardvark/guaardvark cast --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/guaardvark/guaardvark.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/cast .claude/skills/cast && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
cast
GitHub stars
255
Token cost
~673 tokens
SKILL.md length
251 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

Build consistent characters, environments and props in Guaardvark's Cast Library and train LoRAs for them locally (reference photos → vision bible → sample plan → approved samples → training).

  • Works in 7 steps: Create the subject → Upload reference images (5 to 20 clear… → Vision bible from the refs: POST… → …
  • The user wants the same face
  • SKILL.md covers The pipeline and Rules
  • Calls curl

What it does

Cast is an agent skill from guaardvark/guaardvark. Build consistent characters, environments and props in Guaardvark's Cast Library and train LoRAs for them locally (reference photos → vision bible → sample plan → approved samples → training). Use when the user wants the same face or object across images, videos, a music video, or a Film Crew production, or asks to "train a LoRA".

Its SKILL.md is about 670 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering Fine-tuning and Diffusion and image models. It works with Model Context Protocol and Stable Diffusion. The repository describes itself as: The self-hosted AI studio: local video, image, music, voice, LoRA training, coding swarms, RAG and screen agents on one GPU, driven from the Studio or by your coding agent… The licence is MIT.

When your agent uses it

  • The user wants the same face
  • Object across images
  • A Film Crew production
  • Asks to train a LoRA

Example prompts

  • “train a LoRA”
  • “/cast”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Create the subject
  2. Upload reference images (5 to 20 clear shots, varied angles, same subject)
  3. Vision bible from the refs: POST $B/api/cast-library/subjects/$ID/bible/from-refs
  4. Plan and generate training samples: POST .../$ID/plan then POST .../$ID/generate
  5. Approve samples: POST .../$ID/samples/approve.
  6. Train: POST $B/api/cast-library/subjects/$ID/train with optional
  7. Use it: generate_image with subject_ids=[ID]; batch image/video routes with

What it can do on your machine

Read from SKILL.md and the folder at commit f022ceb. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cast loads about 673 tokens when it runs. Until then it costs about 84 tokens; SKILL.md has 251 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~84
When it runs · the whole SKILL.md, loaded when a task matches
~673

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from guaardvark/guaardvark at commit f022ceb, republished under its MIT licence (© guaardvark). 251 words, ~673 tokens.

Download SKILL.mdSave it as .claude/skills/cast/SKILL.md (or your agent's skills folder).
name
cast
description
Build consistent characters, environments and props in Guaardvark's Cast Library and train LoRAs for them locally (reference photos → vision bible → sample plan → approved samples → training). Use when the user wants the same face or object across images, videos, a music video, or a Film Crew production, or asks to "train a LoRA".

Cast Library and LoRA training

Read setup first; training needs the lora_trainer plugin (CUDA, bf16) and an installed train-ready base (Z-Image, SDXL or FLUX family). B=${GUAARDVARK_URL:-http://localhost:5000}.

The pipeline

  1. Create the subject
    bash
    curl -s -X POST $B/api/cast-library/subjects -H 'Content-Type: application/json' -d '{
  "kind": "character", "name": "Mara", "description": "late 30s, short grey hair, freckles",
  "trigger_word": "mara_v1", "voice_id": null
}'
    kind is character, environment or prop. GET $B/api/cast-library lists subjects; the numeric id is what generate_image and batch routes take as subject_ids.
  2. Upload reference images (5 to 20 clear shots, varied angles, same subject): curl -s -X POST $B/api/cast-library/subjects/$ID/upload-refs -F files=@1.jpg -F files=@2.jpg Ask first whether the person consented; do not train on someone who has not.
  3. Vision bible from the refs: POST $B/api/cast-library/subjects/$ID/bible/from-refs (the vision model writes the identity description that every prompt inherits).
  4. Plan and generate training samples: POST .../$ID/plan then POST .../$ID/generate (cancel with .../generate/cancel). Review GET .../$ID/samples; view one with GET .../samples/<sample_id>/image; drop bad ones with DELETE .../samples/<sample_id> or POST .../samples/<sample_id>/regenerate.
  5. Approve samples: POST .../$ID/samples/approve.
  6. Train: POST $B/api/cast-library/subjects/$ID/train with optional {"training_settings": {...}}. A 409 already_training means wait; a train_base_not_ready error names the base model to install first. Cancel: .../train/cancel. Progress: GET $B/api/cast-library/subjects/$ID (status, base model, LoRA path when done).
  7. Use it: generate_image with subject_ids=[ID]; batch image/video routes with subject_ids; the Film Crew casts it; the music-video Director locks it per cut.

Rules

  • Training is a GPU job of tens of minutes; say so and check inspect_gpu for conflicts first.
  • The trigger word is applied by the system when subject_ids is passed; the user does not need to type it.
  • Everything stays local: refs, samples and the LoRA file under data/.

© guaardvark, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/cast of guaardvark/guaardvark.

Open the folder on GitHubat commit f022ceb

Compare with similar skills

Cast next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Cast compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cast this skillguaardvark/guaardvark255—~673Automated safety check: PassMIT
Model Registryartokun/comfyui-mcp795—~2.1kAutomated safety check: PassMIT
Comfyui Skill OpenclawHuangYuChuh/ComfyUI_Skills_OpenClaw411—~2.7kAutomated safety check: PassApache-2.0
Civitaiartokun/comfyui-mcp795—~1.1kAutomated safety check: PassMIT
Workflow Template BuilderMooshieblob1/MooshieUI207—~640Automated safety check: PassAGPL-3.0
Train Character Loraartokun/comfyui-mcp795—~1.3kAutomated safety check: PassMIT

Similar skills

  • Model Registry

    artokun/comfyui-mcp

    Curated download URLs and target directories, organized by family (Flux, WAN, LTX, Qwen, Z-Image, SD15/SDXL), for every model the comfyui-mcp skills reference, covering checkpoints, VAEs, text…

    795 GitHub stars~2.1k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed

  • Comfyui Skill Openclaw

    HuangYuChuh/ComfyUI_Skills_OpenClaw

    Run registered ComfyUI workflows through the fast comfyui-skill CLI, and use the official local Comfy MCP for live template, node, model, validation, and orchestration capabilities.

    411 GitHub stars~2.7k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

  • Civitai

    artokun/comfyui-mcp

    Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally.

    795 GitHub stars~1.1k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed

  • Workflow Template Builder

    Mooshieblob1/MooshieUI

    Builds or modifies ComfyUI workflow JSON templates in MooshieUI's Rust backend (src-tauri/src/templates).

    207 GitHub stars~640 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Train Character Lora

    artokun/comfyui-mcp

    Train a character/identity LoRA locally on FLUX.1-dev via the comfyui-mcp train tools (GPU Docker + ostris ai-toolkit).

    795 GitHub stars~1.3k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed

  • Flux2 Lora Training

    AnastasiyaW/codex-claude-code-config

    Plan or review LoRA and edit-training work specifically for FLUX.2 Klein or Qwen-Image-Edit, including paired datasets, trainer-version contracts, and held-out fidelity checks.

    154 GitHub stars~4.5k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

More from guaardvark/guaardvark

All 15 skills in this repo

  • Setup

    guaardvark/guaardvark

    Connect this agent to a running Guaardvark (self-hosted AI studio) and check what it can do right now.

    255 GitHub starsUsed in 1 repo~1.2k tokens
    Auto-check passed

  • Voice

    guaardvark/guaardvark

    Narration and text-to-speech on the user's machine through Guaardvark's Audio Foundry (Chatterbox, Kokoro, Piper) and consent-gated voice cloning from a reference clip.

    255 GitHub starsUsed in 1 repo~798 tokens
    Auto-check passed

  • Image

    guaardvark/guaardvark

    Generate or edit images on the user's own GPU through Guaardvark: single images, instruction edits, background cut-outs, inpaint and outpaint, consistent characters from the Cast Library, and batch…

    255 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed

  • Music

    guaardvark/guaardvark

    Generate full songs with vocals or instrumentals (ACE-Step) and sound effects or ambience (Stable Audio Open) on the user's GPU through Guaardvark's Audio Foundry.

    255 GitHub stars~710 tokensUpdated yesterday
    Auto-check passed

  • Ops

    guaardvark/guaardvark

    Operate a running Guaardvark: GPU and VRAM state, plugin start/stop, logs, Celery tasks, the Interconnector sync to other machines, overnight RAG autoresearch, and infographics.

    255 GitHub stars~779 tokensUpdated yesterday
    Auto-check passed

  • Swarm

    guaardvark/guaardvark

    Launch and watch Guaardvark's Swarm Orchestrator: parallel coding agents, each in its own git worktree, working a markdown plan and merging back deterministically.

    255 GitHub stars~746 tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Cast

What does Cast do?

Build consistent characters, environments and props in Guaardvark's Cast Library and train LoRAs for them locally (reference photos → vision bible → sample plan → approved samples → training). Cast is an agent skill from guaardvark/guaardvark. Build consistent characters, environments and props in Guaardvark's Cast Library and train LoRAs for them locally (reference photos → vision bible → sample plan → approved samples → training).

When should I use Cast?

Cast fits situations like: the user wants the same face; object across images; A Film Crew production; asks to train a LoRA.

How do I install Cast in Claude Code?

Run `npx skills add guaardvark/guaardvark --skill cast -a claude-code`. Or copy the skill folder (.agents/skills/cast in guaardvark/guaardvark) into .claude/skills/cast in your project. Claude Code loads it when a task matches its description.

How do I install Cast in Codex?

Run `npx skills add guaardvark/guaardvark --skill cast -a codex`. Or copy the skill folder (.agents/skills/cast in guaardvark/guaardvark) into .agents/skills/cast in your project. Codex loads it when a task matches its description.

Can I use Cast in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add guaardvark/guaardvark --skill cast -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cast, .gemini/skills/cast, .github/skills/cast and .opencode/skills/cast in your project.

What does Cast need to run?

Going by SKILL.md and its folder, Cast needs the command-line tools its instructions call (curl).

Does Cast access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Cast safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Cast use?

Cast is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cast use?

About 673 tokens (SKILL.md is roughly 2.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Cast?

Skills that share tags, products or a category with Cast: Model Registry (artokun/comfyui-mcp, 795 stars), Comfyui Skill Openclaw (HuangYuChuh/ComfyUI_Skills_OpenClaw, 411 stars), Civitai (artokun/comfyui-mcp, 795 stars) and Workflow Template Builder (Mooshieblob1/MooshieUI, 207 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cast?

guaardvark (a GitHub user) maintains it in guaardvark/guaardvark, which has 255 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 7, 2026.

Source: guaardvark/guaardvark on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.