Skills Guide

Media Forge: Create

VerifiedCaution

Main orchestrator. Refines user brief, routes to domain agent, runs quality review, and returns verdict. Handles retry up to 3 times.

Download and use
Sby Skills Guide Bot
ContentIntermediate
7/24/2026
Claude Code
#media-generation#orchestration#image-generation#video-generation#quality-review

Recommended for

Claude CodeUI/UX designerSEO & contentProduct managerWriter / marketerSolo / indie hacker

Automated summary

Main orchestration skill that turns a user brief into an image or video by chaining prompt refinement, routing to a domain agent, generation, quality review, and retries.

Strengths

  • Single entry point: routing to the right domain agent is handled internally, with no manual selection
  • Explicit feedback loop: a failed verdict sends the fix directive back to the target agent, up to 3 attempts
  • Full traceability through lineage.json (agents, prompts, model calls, verdicts) plus a USD cost summary
  • Delegates spec writing to prompt-engineer, separating brief clarification from actual generation

Limitations

  • Fully dependent on media-forge:prompt-engineer, the domain agents, and media-forge:quality-reviewer; without them the pipeline cannot run
  • Capped at 3 fix attempts, so an ambiguous brief may end in failure with no escalation path to the user
  • Covers images and videos only and does not describe handling model-call errors or budget overruns
When to use it

Use it whenever a user wants to produce an image or video from a natural-language brief with automated quality gating.

When not to use it

Avoid it if the media-forge skills and agents are not installed, or if the task is editing an existing media file rather than generating a new one.

Security analysis

Caution
Quality score84/100

The orchestrator contains no destructive, exfiltration, obfuscation, or safety-disabling instructions. Risk is moderate because it grants Bash/Write access and dispatches to unspecified subagents, so downstream behavior must be trusted, but this file itself only coordinates generation and review.

Findings
  • •Declares Bash and Write, allowing command execution and filesystem modification, although no concrete commands are specified.
  • •Delegates execution to external domain agents whose behavior and tool use are not defined in this file.
How this analysis is made

Examples

Generate an image from a brief
Create a 16:9 hero image of a misty Nordic fjord at dawn, muted teal palette, no text, and review the result before handing it back.
Generate a short video clip
Produce a 5-second looping video of neon rain on a Tokyo alley floor, then show me the quality verdict and cost.
Retry after a failed verdict
Make a product shot of a ceramic mug on a linen backdrop — if the reviewer fails it, let the pipeline apply the fixes and regenerate.

name: create description: "Main orchestrator. Refines user brief, routes to domain agent, runs reviewer, surfaces verdict. Triggers: create, generate, make, produce." allowed-tools: Read, Write, Bash, Grep, Glob preamble-tier: 1 user-invocable: true

media-forge:create

Main orchestration skill. Accepts a user brief and manages the full pipeline: refinement, domain routing, generation, quality review, and retry.

Workflow

  1. Dispatch media-forge:prompt-engineer with user brief. Receive refined_spec.json.
  2. Read refined_spec.domain to select the target domain agent.
  3. Dispatch the domain agent with refined_spec.json path. Receive asset paths.
  4. Dispatch media-forge:quality-reviewer with asset paths. Receive verdict JSON.
  5. If verdict.pass === false and retry count < 3: dispatch verdict.fix_target_agent with verdict.fix_directive. Go to step 4.
  6. Return final asset paths, lineage, and verdict to user.

When to use

Invoke when the user wants to generate any image or video. This is the primary entry point. It handles all routing internally.

Outputs

  • Final asset file paths
  • lineage.json: chain of agents, prompts, model calls, and verdicts
  • Cost summary in USD
  • Quality verdict (pass/fail + scores)

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/media-forge-create-mryiqgva/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/media-forge-create-mryiqgva' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/media-forge-create-mryiqgva/download' --output '.skill-downloads/media-forge-create-mryiqgva/SKILL.md.part' && mv '.skill-downloads/media-forge-create-mryiqgva/SKILL.md.part' '.skill-downloads/media-forge-create-mryiqgva/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Read, Write, Bash, Grep, Glob

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/media-forge-create-mryiqgva/SKILL.md' && test -s '.skill-downloads/media-forge-create-mryiqgva/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/create' && cp -R '.skill-downloads/media-forge-create-mryiqgva' '.claude/skills/create'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/media-forge-create-mryiqgva'

openskills read 'media-forge-create-mryiqgva'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/media-forge-create-mryiqgva/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills

Writing Fragments

Content

Mine raw writing fragments through a relentless interview, without imposing structure. Capture ideas, quotes, and leading words for later use.

Claude CodebeginnerSafe 240,316
Skills Guide Bot

UI Copywriting & Auditing

Content

Write or audit user-facing UI copy including buttons, errors, empty states, and tooltips across the monorepo, following the design system source of truth.

Claude CodeCursorbeginnerSafe 108,623
Skills Guide Bot

Music MIDI Extraction

Content

Extracts the MIDI or score from an existing music production via the CogMusic MCP tool and confirms availability.

Claude CodebeginnerSafe 69,866
Skills Guide Bot