
Muapi Workflow
Discover, design, and run MuAPI generative-media workflows from natural-language prompts via thin CLI wrappers for solo builders automating image, video, or multi-step AI pipelines.
Overview
MuAPI Workflow is an agent skill most often used in Build (also Operate iterate, Launch distribution asset prep) that discovers, creates, edits, and runs MuAPI generative workflows through bash wrappers around the muapi
Install
npx skills add https://github.com/samuraigpt/generative-media-skills --skill muapi-workflowWhat is this skill?
- Discover relevant workflows with `muapi workflow discover --query` and a configurable limit
- Create or edit workflows from a single `--prompt` with optional `--workflow-id`
- Run workflows interactively with `--workflow-id` via the Interactive Workflow Runner wrapper
- Supports `--async`, `--view`, and `--json` output modes on create/edit
- Three assistant/expert bash entrypoints: discover, architect, runner—all thin muapi CLI wrappers
- 3 bash entrypoints: discover, architect (create/edit), interactive runner
Adoption & trust: 653 installs on skills.sh; 3.5k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You know what you want a generative pipeline to do but lack a repeatable workflow ID, discovery path, or scripted create/run loop for your coding agent.
Who is it for?
Solo builders already using muapi who want agent-callable discover → architect → run steps for generative media without re-explaining CLI syntax each session.
Skip if: Teams without muapi installed, builders who only need static design templates, or anyone expecting in-skill model hosting without the external CLI.
When should I use this skill?
You need to discover, create, edit, or run MuAPI workflows from an agent session with --query or --prompt and optional --workflow-id.
What do I get? / Deliverables
You get discoverable workflow matches, a prompt-driven create or edit against muapi, and an interactive or async run path your agent can invoke with stable flags.
- Workflow discovery results
- Created or edited workflow ID
- Workflow run output (view, async, or JSON)
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Workflow architecting and API integration land in Build because you wire external generative services before you ship repeatable pipelines. Integrations is the canonical shelf: the skill wraps muapi workflow discover, create, edit, and run—not frontend UI or pure docs.
Where it fits
Discover existing MuAPI workflows matching a video stylization query before committing to a custom graph.
Create a new workflow from a prompt and export JSON for your agent to poll async completion.
Edit an existing workflow-id after quality drift without rebuilding the pipeline from scratch in chat.
How it compares
Use instead of ad-hoc shell snippets in chat when you need consistent muapi workflow discover/create/run flags for agent tools.
Common Questions / FAQ
Who is muapi-workflow for?
Indie builders and small teams automating generative media with MuAPI who want Claude Code, Cursor, or Codex to call thin bash wrappers for discovery, workflow design, and execution.
When should I use muapi-workflow?
During Build when wiring integrations; in Operate when tuning or re-running pipelines; and when prepping repeatable asset workflows before Launch—whenever you have a query or prompt and need muapi workflow discover, create, edit, or run.
Is muapi-workflow safe to install?
The skill runs shell and network calls through muapi; review the Security Audits panel on this page and treat API keys and workflow prompts as sensitive before enabling in production agents.
SKILL.md
READMESKILL.md - Muapi Workflow
#!/bin/bash # Assistant Skill: Discover Relevant Workflow # Thin wrapper around muapi CLI. QUERY="" LIMIT=5 while [[ $# -gt 0 ]]; do case $1 in --query|-q) QUERY="$2"; shift 2 ;; --limit) LIMIT="$2"; shift 2 ;; *) shift ;; esac done if [ -z "$QUERY" ]; then echo "Error: --query is required" >&2; exit 1; fi muapi workflow discover "$QUERY" --limit "$LIMIT" #!/bin/bash # Expert Skill: AI Workflow Architect # Thin wrapper around muapi CLI. PROMPT="" WORKFLOW_ID="" # Set to edit an existing workflow ASYNC=false VIEW=false JSON_ONLY=false while [[ $# -gt 0 ]]; do case $1 in --prompt|-p) PROMPT="$2"; shift 2 ;; --workflow-id|-w) WORKFLOW_ID="$2"; shift 2 ;; --async) ASYNC=true; shift ;; --view) VIEW=true; shift ;; --json) JSON_ONLY=true; shift ;; *) shift ;; esac done if [ -z "$PROMPT" ]; then echo "Error: --prompt is required" >&2; exit 1; fi ARGS=() [ "$ASYNC" = true ] && ARGS+=("--async") [ "$VIEW" = true ] && ARGS+=("--view") [ "$JSON_ONLY" = true ] && ARGS+=("--output-json") if [ -n "$WORKFLOW_ID" ]; then muapi workflow edit "$WORKFLOW_ID" --prompt "$PROMPT" "${ARGS[@]}" else muapi workflow create "$PROMPT" "${ARGS[@]}" fi #!/bin/bash # Assistant Skill: Interactive Workflow Runner # Thin wrapper around muapi CLI. WORKFLOW_ID="" while [[ $# -gt 0 ]]; do case $1 in --workflow-id|-w) WORKFLOW_ID="$2"; shift 2 ;; *) shift ;; esac done if [ -z "$WORKFLOW_ID" ]; then echo "Error: --workflow-id is required" >&2; exit 1; fi muapi workflow run-interactive "$WORKFLOW_ID" #!/bin/bash # Assistant Skill: List Workflows # Thin wrapper around muapi CLI. JSON_ONLY=false LIMIT=20 while [[ $# -gt 0 ]]; do case $1 in --json) JSON_ONLY=true; shift ;; --limit) LIMIT="$2"; shift 2 ;; *) shift ;; esac done if [ "$JSON_ONLY" = true ]; then muapi workflow list --output-json else muapi workflow list | head -n $((LIMIT + 5)) fi #!/bin/bash # Expert Skill: Run & Visualize an AI Workflow # Thin wrapper around muapi CLI. WORKFLOW_ID="" INPUT_ARGS=() WEBHOOK="" ASYNC=false DOWNLOAD_DIR="" while [[ $# -gt 0 ]]; do case $1 in --workflow-id|-w) WORKFLOW_ID="$2"; shift 2 ;; --input|-i) INPUT_ARGS+=("$2"); shift 2 ;; --webhook) WEBHOOK="$2"; shift 2 ;; --async) ASYNC=true; shift ;; --download|-d) DOWNLOAD_DIR="$2"; shift 2 ;; *) shift ;; esac done if [ -z "$WORKFLOW_ID" ]; then echo "Error: --workflow-id is required" >&2; exit 1; fi ARGS=() for ITEM in "${INPUT_ARGS[@]}"; do ARGS+=("--input" "$ITEM"); done [ -n "$WEBHOOK" ] && ARGS+=("--webhook" "$WEBHOOK") [ "$ASYNC" = true ] && ARGS+=("--no-wait") [ -n "$DOWNLOAD_DIR" ] && ARGS+=("--download" "$DOWNLOAD_DIR") if [ ${#INPUT_ARGS[@]} -gt 0 ]; then muapi workflow execute "$WORKFLOW_ID" "${ARGS[@]}" else muapi workflow run "$WORKFLOW_ID" "${ARGS[@]}" fi --- name: muapi-workflow version: 0.1.0 description: Build, run, and visualize multi-step AI generation workflows. The AI architect translates natural language descriptions into connected node graphs — chain image generation, video creation, enhancement, and editing into automated pipelines. --- # AI Workflow Builder Chain any combination of muapi.ai generation steps into automated pipelines. The AI architect converts your plain-language description into a runnable node graph. ## Prerequisites Always ensure the `muapi` CLI is up-to-date before running any commands. Reinstall from source at the start of every session: ```bash pip install --upgrade /path/to/muapi-cli ``` Replace `/path/to/muapi-cli` with the actual path to the `muapi-cli` directory in the workspace (the directory containing `pyproject.toml`). ## Core Operations 1. **Generate** (`generate-workflow.sh`) — AI architect creates a workflow from a description 2. **Discover** (