scenario-refine-loop
Use when a Scenario output must be checked and improved rather than accepted first roll: iterating a generation until it matches the brief, fixing a batch that came back off-brief, retrying failed shots methodically, wiring an automated generate, review, revise loop, or deciding whether to re-prompt, swap references, inpaint, post-process, or change model. Keywords: refine, iterate, critique, review loop, QA, self-correction, verify, acceptance criteria, retry, drift.
- Installs
- 485
- Last 24h
- +11
- Trending rank
- #8203
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/scenario-labs/skills --skill scenario-refine-loop- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads scenario-refine-loop automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Scenario Refine Loop
Overview
Agents fail generation QA in two symmetric ways: accepting the first roll, or rewording the whole
prompt and re-rolling until the budget dies. Both skip the same two artifacts, a written rubric and
a diagnosis. The loop that converges: rubric before generating, a small batch, a recorded verdict
per asset, the cheapest targeted fix per failure, a hard round cap. Connection and the core loop:
see the scenario skill. Critic tool contracts: scenario-asset-analysis. Baseline discipline:
scenario-consistency. If a sibling skill named here is missing from your available skills, ask the
user to install it (npx skills add scenario-labs/skills --skill <name>); unattended, proceed from
tool schemas and flag the gap.
Quick reference
| Step | Do |
|---|---|
| 1. Rubric | Before generating, turn the brief into pass/fail lines a viewer can check ("subject centered on a plain field"), never taste words |
| 2. Generate | The smallest batch that tests the recipe, at the cheapest size or quality tier the schema offers on which every rubric line can still be judged; dry_run when cost matters |
| 3. Critique | asset_analyze: up to 10 images per call, one instruction embedding the rubric and a fixed per-image output shape |
| 4. Fix | Route every fail line to the cheapest fix that addresses it (table below) |
| 5. Stop | A clean round ships; three rounds without one, or one line failing twice under different fixes, means report, not respin |
A tier change is a new generation, not the keeper enlarged: re-run only the keeper's recipe at
delivery tier and re-critique it, or keep what passed and upscale it with a fidelity upscaler found
by search target="models", filters={"tags": ["image-upscale"]}, public=true (fidelity versus
creative picks and sizing in scenario-image-editing, video upscaling in scenario-video).
When the bar is the configured brand brief rather than a task rubric, and the team's Quality Gate
add-on is enabled, critique images with asset_quality_gate_run instead: its reasons and
suggestions feed the fix table directly (scenario-quality-gate; where the gate is missing it
degrades to this asset_analyze path).
Fix routing, cheapest first:
| The verdict says | Fix |
|---|---|
| One local defect on a keeper | Masked inpaint of that region; on a schema with no mask field, an instruction edit of the keeper naming that one change (scenario-image) |
| A uniform finish off (grade, tint, crop) | A deterministic tool pass (scenario-image-editing), not a re-roll |
| Wrong content, composition, or rendered palette | Edit the delta clause, re-run from the approved baseline |
| Identity or style drift | Tighten the enumeration, add or re-role references (scenario-consistency) |
| Every line failing | Change the model: re-discover with recommend (capability-shaped; search is for a name, a private model, or a tag-filtered lane such as image-upscale), keep the prompt |
Change one variable per round. A round that swaps prompt, references, and model at once cannot attribute the improvement, so the next failure restarts from zero.
The two rules that keep the loop honest
- Verdicts cite the rubric, not taste. Instruct the critic to answer per image, in order:
<index>: pass|fail, <the failed line>. "Could be better" is not a verdict; a loop chasing better instead of the brief sands off exactly what made the direction distinctive and converges on generic output. - Regenerate from the baseline, never from the last attempt. Fixes re-run from the approved
reference and prompt; chaining output to output compounds drift (
scenario-consistencyexplains why).
Worked example: four icons against a brief
- Rubric from the brief, five lines: single object, centered, plain field, palette #2A9D8F and #E9C46A only, no text.
- Generate four, one
model_runeach perscenario-image, thenjobs_wait. - One
asset_analyzecall with all four ids inimagesand the rubric-plus-shape instruction; answers land as text assets,asset_downloadthem to read the verdicts. - Two fail. Icon 2 is off palette, which is rendered content rather than a finish: edit the delta clause by pinning the hex codes in the prompt and re-run from the baseline. Icon 4 has one smeared edge: masked inpaint of that corner. Icons 1 and 3 ship untouched.
jobs_waitthe fix runs, then re-critique only the two new assets with the byte-identical instruction. Clean round: stop, file the keepers in a collection (scenario-asset-analysis).
Common mistakes
- Judging by glancing at
asset_displayin chat: unrecorded impressions do not accumulate; verdicts do. - Asking
asset_analyzeto improve or fix the image: it returns text only; every fix is a new run. - Re-rolling the whole batch because one item failed: route per item.
- Writing the rubric after seeing the batch: it inherits the batch's flaws as the standard.
- Running the loop uncapped: failed jobs are reimbursed, unsatisfying ones are not. Gate rounds on
the costs the runs themselves report (
dry_runprices the next round ahead);usagetotals lag and answer the report after the run, not the mid-run gate. - Retrying a criterion a third time on the same model: two misses under two different fixes is evidence about the model, not bad luck.
FAQ
What does the scenario-refine-loop skill do?
Use when a Scenario output must be checked and improved rather than accepted first roll: iterating a generation until it matches the brief, fixing a batch that came back off-brief, retrying failed shots methodically, wiring an automated generate, review, revise loop, or deciding whether to re-prompt, swap references, inpaint, post-process, or change model. Keywords: refine, iterate, critique, review loop, QA, self-correction, verify, acceptance criteria, retry, drift.
How do I install scenario-refine-loop?
Run npx skills add https://github.com/scenario-labs/skills --skill scenario-refine-loop in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/scenario-refine-loop/ (personal) or .claude/skills/scenario-refine-loop/ (project).
Which AI agents can use scenario-refine-loop?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is scenario-refine-loop safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains scenario-refine-loop?
It is published by scenario-labs in scenario-labs/skills. It has 485 recorded installs.
More from scenario-labs/skills
scenario
scenario-labs/skills
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.
scenario-blender-expert
scenario-labs/skills
Use when doing any 3D work in Blender through Python or an MCP bridge, headless or in a live session: modeling, sculpting a character or head, retopology, UV unwrapping, baking, texturing, rigging, animating, previs, geometry nodes, lighting and rendering, grease pencil, or finishing an AI-generated mesh into a production asset. Also before exporting or handing off an asset, to check it is ready for a game engine, a render or a 3D print (floating parts, z-fighting, inside-out normals, unapplied scale, missing UVs). Also when a bpy script fails on Blender 5.x API changes, a brush or sculpt operator fails or crashes headless, or a result has to be judged like a professional 3D artist would.
scenario-game-assets
scenario-labs/skills
Use when creating game art through Scenario MCP: sprites, sprite sheets, icons, props, loot, tilesets and autotile terrain transitions, seamless tiles, isometric buildings, top-down maps, pixel art, UI buttons and panels, parallax background layers or depth planes for side-scrollers, and character or concept art; or when assets need transparent backgrounds, background removal, style-consistent variation batches, upscaling, pixel-grid cleanup, or PNG export for Unity, Godot, or Unreal.
scenario-consistency
scenario-labs/skills
Use when one look must hold across Scenario generations: one character across scenes, a turnaround, or a video animated from its references, one product across angles, one style across icon sets, a character from an uploaded drawing, a variant off an approved baseline, or deciding when references stop scaling and a trained model is due. Triggers: make this match, same character, on-model, reference to video, style reference. Keywords: consistency, identity, control map, seed, LoRA.
scenario-sprite-animation
scenario-labs/skills
Use when animating 2D game art with Scenario: walk, idle or attack cycles in 4 or 8 directions, isometric sprite sheets, animated GIFs, frame-by-frame pixel art animation, VFX loops such as fire or smoke, looping a sprite seamlessly, animating an existing character image, a full animation sheet from one prompt, extracting animation frames from a generated video, or slicing a sprite sheet into engine-ready frames for Unity, Godot, or Unreal. Keywords: spritesheet, keyframes, frame grid, GIF.
scenario-3d
scenario-labs/skills
Use when generating or handling 3D assets through the Scenario MCP server, including text-to-3D or image-to-3D meshes, GPT-6 Astra 3D or Claude Opus 5.5 3D, GLB, FBX, OBJ, STL, or VOX files, PBR-textured or game-ready models, voxel models, multi-view reconstruction, editing a mesh by prompt, retexture, remesh, UV unwrap, auto-rigging a biped or quadruped, or retargeting an animation, previewing a mesh in the 3D viewer, or downloading a model for import into Unity, Unreal, Godot, or Blender.
Popular code quality & workflow skills
grill-me
mattpocock/skills
A relentless interview to sharpen a plan or design.
improve-codebase-architecture
mattpocock/skills
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
handoff
mattpocock/skills
Compact the current conversation into a handoff document for another agent to pick up.
domain-modeling
mattpocock/skills
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
codebase-design
mattpocock/skills
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
diagnosing-bugs
mattpocock/skills
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.