SkillAgentSearch skills...

scenario

Use when connecting an AI agent to Scenario (scenario.com) through MCP, or when a task involves generating images, video, 3D, audio, sprites, textures, or game assets.

Install / Use

npx skills add scenario-labs/skills --skill scenario

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

86/100

Category

Other

Supported Platforms

Claude Code
Cursor

Our assessment of scenario

scenario scores 86/100 on our quality scale, 179th of 329 Other skills we index.

Its SKILL.md is 18 KB long, well organised into 8 sections and no code examples: a thorough specification that gives an agent plenty to work with.

With 1,048 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
30/30
Structure
13/20
Description
15/15
Adoption
13/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated 29 days ago, so scenario is actively maintained.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-11-10. Automated pattern scan on 2026-11-10. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

scenario compared with similar skills

All 4 of these similar skills score higher than scenario; compare them before choosing.

SkillScoreStarsUpdatedFormat
scenario (this skill)by scenario-labs861.0k29d agoSKILL.md
taste-skillby Leonxlnx100116.8k8d agoCLAUDE.md
Agent-Reachby Panniantong100112.3k8d agoCLAUDE.md
rufloby ruvnet10081.9ktodayCLAUDE.md
headroomby headroomlabs-ai10079.8ktodayCLAUDE.md

Frequently asked questions

How do I install scenario?
Run npx skills add scenario-labs/skills --skill scenario. The install tabs above show the steps for each supported agent.
Which AI agents does scenario work with?
It is written for Claude Code and Cursor, as a SKILL.md file. Other agents that read the same format can often use it too.
Is scenario safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is scenario still maintained?
The repository was last updated 29 days ago, so scenario is actively maintained.

name: scenario description: Use when connecting an AI agent to Scenario (scenario.com) through MCP, or when a task involves generating images, video, 3D, audio, sprites, textures, or game assets. Also when picking a Scenario model, running a LoRA, refining a generation prompt, uploading reference images, waiting on generation jobs, checking credits or quota, hitting Scenario auth, scope, or Forbidden errors, or setting up mcp.scenario.com in Claude Code, Cursor, VSCode, or another agent. license: MIT

Scenario

Overview

Scenario generates images, video, 3D, and audio across 500+ models, plus custom training.

Setup

  • Endpoint: https://mcp.scenario.com/mcp (Streamable HTTP). Prefer OAuth: no credentials pass through the conversation.
  • Client config, headless API-key setup, and per-client re-authentication: references/setup.md.
  • Never ask an agent to collect, encode, or echo a secret.
  • A previously authenticated connection now failing: re-authenticate before debugging. diagnostics_run names the layer (auth, tenant-scope, api-unreachable, or healthy).

Two tool kinds:

  • Direct: the loop below, plus asset_get, job_get, jobs_list, and models_list. ?toolsets=full exposes everything.
  • Catalog: the rest (collections, tagging, analysis, training, members, keys).
    • scenario_tools_search takes only query (tool name or keywords) and limit; returns schema and lane.
    • scenario_tool_execute_read / write / delete take a required name and parameters, which holds every input, scope ids and dry_run included: {"name": "collection_add_assets", "parameters": {"team_id": "…", "project_id": "…", "collection_id": "…", "asset_ids": ["…"]}}. plan_generation takes only description.
    • Direct tools take scope, and model_run its dry_run, at top level. Never route them through an executor.
    • The executor drops a misplaced key silently: arguments surfaces as a false scope error, and a top-level dry_run runs the job, billed.
    • The lane is the result's own permission, not the verb: asset_analyze is write-class, since it starts a billed job.

Scope first

  • Resolve scope first, then pass team_id and project_id on every call.
  • A team is the organization, the company or studio account; its projects sit inside it. "My organization" or "my studio" names the team.
  • teams_list returns the teams with their projects. projects_list needs a team_id.
  • Confirm the pair with the user: a guess writes into someone else's project. Unattended, take the pair from the task; if it names none, stop and list the choices.
  • The server fills scope only for read-only tools with one candidate, so an omission fails once a second team or project appears. The error names the wrong half.

Quick reference

| Step | Tool | Notes | | ----------------- | ---------------------------------------- | ---------------------------------------------------------------------------- | | Resolve scope | teams_list, then projects_list | Once per session; pass the ids on every call | | Find a model | search or recommend | Free; recommend for a capability, search for a name | | Get the schema | model_schema_get | Always before model_run; check runs_as and caps | | Generate | model_run | Schema-conformant parameters; dry_run for cost | | Wait | jobs_wait | Whenever model_run returns a job_id without assets; never loop job_get | | View / save | asset_display / asset_download | Never paste raw asset URLs; format converts images, meshes | | Inspect an asset | asset_get | Free; dimensions, duration, firstFrame / lastFrame ids | | Upload inputs | upload_asset + upload_asset_complete | Local files become asset_ids | | Refine a prompt | prompt_spark | Advisory rewrite; needs model_id | | Quota / debugging | usage, diagnostics_run | CU consumption; diagnose MCP prompt | | Saved preferences | memory_recall | OAuth only; before generating in a project, again after switching |

  • Multi-step request ("product video with voiceover", "concept to 3D"): catalog plan_generation (read lane). Plain words in description, ordered steps out, each naming a tool and an optional model hint. It runs nothing. A single step goes to recommend.
  • Stated preference ("always 9:16"): catalog memory_set (delete lane), scope project_user_memory (user_memory across projects). It replaces the whole layer: memory_get and merge first.

Worked example

Generating a stylized game prop image:

  1. Discover the model:
    • recommend with the user's own words as prompt for a capability. Unscoped, it ranks models the team cannot run.
    • search requires target (models, assets, workflows); for a known name: target="models", query="<model name>", public=true. It ranks by keyword and its filters hold no capability key, so a capability-worded query can rank the wrong output type first.
    • The user's own trained models: omit public on search (it has no private flag); pass include_private_models: true on recommend.
    • Re-discover ids each time: availability differs per team.
  2. model_schema_get on the pick: exact field names, types, required flags, defaults, and caps.
    • Overrunning a cap such as the prompt's max_length is a 400, never a trim.
    • File fields take asset ids, even when named ...Url.
    • cost_impact: true flags the fields that move the price.
  3. If the schema carries runs_as ("lora" or "composition"), never send that model's id to model_run. Its run_with.required_arguments holds the real call: model_id there is the base model, and its parameters (the loras or modelId wiring) merge with your inputs from the same schema. required_arguments alone discards your prompt.
  4. Optional: prompt_spark rewrites a thin prompt into an on-model one. Pass the discovered id (a LoRA's own, not its base) and the draft prompt. Skip deliberate prompts.
  5. model_run with model_id and schema-conformant parameters.
    • Unless the user says cost does not matter, price first with dry_run: true, top level beside model_id. No job is created, and creativeUnitsCost is this exact payload's price.
    • A recommend quote assumes defaults; cost_impact fields move the real number.
    • Run: inline assets (status: success) need no wait; otherwise pass job_id to jobs_wait.
    • Unfinished status: in_progress after a timed-out wait; with wait=false, queued, in-progress, or warming-up. All need jobs_wait.
    • A 429: stop launching and find its class under Errors and recovery before the next call. Re-sending the same payload at once never clears it.
  6. jobs_wait with job_ids=[...] (up to 32).
    • Each completed row carries assetIds and cuCost: no job_get follow-up.
    • On timeout (in_progress), re-call with pending_job_ids as job_ids; never re-run or cancel. No timeout argument exists.
    • Failed jobs are reimbursed, except xAI generations stopped by moderation.
  7. asset_display shows the asset inline. Its format picks the rendering:
    • display (default): inline image, links, viewer data; does not disable the host widget.
    • viewer: lighter payload for hosts rendering the interactive widget.
    • json, markdown: metadata and links.
  8. asset_download returns a file URL, one call per asset; save it with curl -L (it may redirect).
    • format converts images (png, webp, jpg; gif keeps an animated GIF animated, while the png default flattens it to one frame) and meshes (glb, fbx, obj). Omit it for video and audio, or it fails with 400 Invalid target format.
    • curl failing with host_not_allowed or CONNECT tunnel failed, response 403 while MCP calls work points at the host's egress policy. A CDN 403 alone does not: fetch a fresh URL first.
    • Sandbox network access names the setting. On some hosts it is an organization allowlist the user may not control.
    • Meanwhile hand over asset_display's app_url. The user downloads there and, for a mesh, picks an export format asset_download does not offer.
    • The signed URL expires: a last resort, never the deliverable.

Local inputs go up with upload_asset:

  • Always file_name, content_type, and kind (image, audio, video, 3d), plus exactly one of file_size or data. Without either it fails with Either 'file_size' … or 'data' is required.
  • Prefer file_size (exact bytes on disk) and omit data; the reply carries presigned part URLs and instructions.
  • PUT each part's raw bytes to its URL with no added headers: a checksum header makes the store answer 403. Check every PUT returned 200, then upload_asset_complete with the upload_id.
  • Inline base64 data only under 100KB, and only when no shell can PUT parts. It returns the asset directly, with no complete step; a larger file is rejected, naming the cap.
  • Both calls take scope and nothing else: no parts list, no etags.
  • Inline data is decoded inside upload_asset: a decode error there (libpng read error, Corrupt JPEG data, unable to read pixels) means the base64 string broke, not the file.
    • The agent retypes every character of data; a 57K-character string broke that way.
    • Re-sending it repeats the error. With a shell, switch to the file_size path, even when the user asked for inline, and say why.
  • On the file_size path the server decodes at completion: Upload upl_… failed: with Corrupt JPEG data, premature end of data segment, bad Huffman code, or libpng read error means it could not.
    • Check for a corrupt source, a truncated or re-encoded body, a missing part, or a wrong file_size.
    • Confirm the local file opens under its declared content type, then start over with a fresh upload_asset and raw PUTs. Never re-complete the same upload_id.
  • A phone's HEIC photo uploads as is (content_type: "image/heic"): do not convert it. Unhandled image format lists what kind: "image" accepts; convert any other type locally.
  • Without a shell, the user uploads at app.scenario.com; continue from the asset id.

Filing is part of delivering, not a tidy-up:

  • collection_create takes a name and the scope pair only. asset_ids sent there is silently ignored, so adding is always a second call: collection_add_assets.
  • It accepts any number of ids, batches by 49, and skips duplicates. Results separate already_present_asset_ids from added_asset_ids.
  • After a failure, resend the whole list: duplicates are skipped.
  • Confirm from that reply: search filters={"collection_ids": [...]} lags on a fresh write.
  • asset_add_tags is additive, one asset_id per call. A tag the asset already carries returns 400 Duplicated tag: read tags via assets_get_bulk first and send only the missing ones.

Reusable templates and reference content follow the shared asset lifecycle: resolve existing assets, stage new versions, publish only through a supported operation, and verify public ac

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars1.0k
CategoryOther
Updated29d ago
Forks129

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions