quality-refinement-autoloop
Skill2 starsChanged 3 days agoMITView on GitHub
Run a self-refinement loop when a Blender result is subpar, user expectations are not met, validation fails, or repeated issues reveal missing skill depth. The loop diagnoses the gap, decides whether to repair the artifact or acquire/refine a generic skill, sanitizes lessons for reusable publication, updates docs/versioning, validates, and prepares stage/commit/push when explicitly requested.
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- keysforthewin/thisofficeedited, first seen Jul 24, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- keysforthewin/thisoffice★ 098% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository33 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/3d-fabric.mdcCursor rule
- 3d-fabricSkill
- animation-quality-gateSkill
- atlas-uv-fittingSkill
- blender-animationSkill
- blender-camerasSkill
- blender-exportSkill
- blender-lightingSkill
- blender-materialsSkill
- blender-modelingSkill
- blender-pro-workflowSkill
- blender-renderingSkill
- blender-skill-harmonizerSkill
- blender-uv-texturingSkill
- closed-surface-uv-coverageSkill
- contour-to-meshSkill
- fit-repair-optimizerSkill
- landmark-fit-repairSkill
- mascot-logo-reconstructionSkill
- multiview-constraint-solverSkill
- multiview-fit-loopSkill
- orbital-hud-motionSkill
- orthographic-registrationSkill
- reference-analysis-validatorSkill
- reference-look-calibrationSkill
- reference-to-3dSkill
- source-part-segmentationSkill
- text-to-blenderSkill
- texture-driven-mesh-fittingSkill
- texture-state-animationSkill
- wireframe-to-3dSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
22 rules. About 0 are common, 19 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈19
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Use when: Subpar output, user rejects quality, repeated Blender failure, RALPH loop, skill gap diagnosis, autonomous skill refinement, …
- Distinctive: line 12
Before the first Blender call, read ../text-to-blender/references/mcp-backends.md.
- Distinctive: line 21
Stop making product changes immediately.
- Very specific: line 43
look/material/lighting calibration.
- Distinctive: line 50
Ask: does the current skill stack already contain a generic method for this failure?
- Distinctive: line 52
If yes: run the existing skill and repair the artifact.
- Distinctive: line 53
If no: add/refine a generic skill first, then repair.
- Distinctive: line 54
If repeated failures come from skill interplay, update the harmonizer/handoff rule, not just a leaf skill.
- Distinctive: line 58
Before writing a skill change:
- Very specific: line 60
remove project/client/asset names.
- Distinctive: line 61
remove secrets, raw logs, private paths, personal data, and copyrighted source content.
- Distinctive: line 62
keep only reusable method, gates, scripts, and failure patterns.
- Distinctive: line 64
prefer deterministic scripts for fragile audits.
- Distinctive: line 83
if applicable, run the new helper against the failed artifact and save a report.
- Very specific: line 91
Only when the user asks to publish/commit/push:
- Distinctive: line 96
update README / plugin README / CHANGELOG / VERSIONING when relevant.
- Distinctive: line 97
run sanitizer and compile/audit checks.
- Distinctive: line 102
Do not bake task-specific examples into public skills.
- Distinctive: line 103
Do not call overlay curves/planes “texture coverage” unless the real mesh surface also passes coverage gates.
- Distinctive: line 104
Do not tune lighting/materials to hide geometry or UV failures.
- Distinctive: line 105
Do not claim export support if the effect exists only in Blender Python or a render sequence.
- Distinctive: line 106
Do not push without an explicit user request and an up-to-date remote check.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
MCP backend
Use when: Subpar output, user rejects quality, repeated Blender failure, RALPH loop, skill gap diagnosis, autonomous skill refinement, sanitized skill contribution, release prep, docs/version bump, staged commit and push workflow.
Before the first Blender call, read ../text-to-blender/references/mcp-backends.md. Prefer official MCP for shared capabilities; preserve the selected backend for the whole task. Tool names in recipes are client/legacy examples: map them through that reference and its agent-host guide.
Quality Refinement Autoloop
Use this when the user says the result is wrong, ugly, not aligned, not textured, not animated, not exportable, or otherwise below expectation. The goal is not to keep tweaking blindly. The goal is to convert failure into a reusable, generic skill improvement before trying again.
Autoloop phases
0. Freeze and preserve
- Stop making product changes immediately.
- Preserve the last accepted baseline and the failed artifact.
- Name the failed branch/version honestly; do not overwrite accepted outputs.
1. Evidence capture
Collect the smallest evidence set that proves the failure:
- user feedback quote or summary;
- source/reference files used;
- current output path/version;
- relevant render/contact sheet/overlay/audit report;
- scene/material/object inventory if the failure is inside Blender.
2. Diagnose failure dimension
Classify the primary gap:
- geometry / silhouette / landmarks;
- multiview/depth consistency;
- UV / atlas / texture fit;
- closed surface coverage (front/back/side);
- look/material/lighting calibration;
- animation/motion/export truth;
- orchestration/handoff between skills;
- missing validator or missing deterministic helper script.
3. Skill-gap decision
Ask: does the current skill stack already contain a generic method for this failure?
- If yes: run the existing skill and repair the artifact.
- If no: add/refine a generic skill first, then repair.
- If repeated failures come from skill interplay, update the harmonizer/handoff rule, not just a leaf skill.
4. Sanitize the lesson
Before writing a skill change:
- remove project/client/asset names;
- remove secrets, raw logs, private paths, personal data, and copyrighted source content;
- keep only reusable method, gates, scripts, and failure patterns;
- describe inputs/outputs generically;
- prefer deterministic scripts for fragile audits.
5. Patch skill stack
Apply the smallest publishable change:
- one concise skill or one concise section in an existing skill;
- optional helper script if the validation is repeatable;
- harmonizer update if ordering/handoff changed;
- manifest entry/version update.
6. Validate skill change
Required checks:
- scripts compile;
- manifest paths exist;
- skill graph audit passes with harmonizer present;
- sanitizer scan passes for project-specific terms;
- if applicable, run the new helper against the failed artifact and save a report.
7. Repair product only after skill gate
Rebuild or repair from the correct baseline using the improved skill. Do not reuse rejected outputs unless explicitly marked as source evidence.
8. Release prep when requested
Only when the user asks to publish/commit/push:
- fetch latest remote and confirm local branch is up to date;
- resolve/harmonize conflicts before staging;
- bump version using semver appropriate to scope;
- update README / plugin README / CHANGELOG / VERSIONING when relevant;
- run sanitizer and compile/audit checks;
- stage, commit, and push using the configured remote.
Hard rules
- Do not bake task-specific examples into public skills.
- Do not call overlay curves/planes “texture coverage” unless the real mesh surface also passes coverage gates.
- Do not tune lighting/materials to hide geometry or UV failures.
- Do not claim export support if the effect exists only in Blender Python or a render sequence.
- Do not push without an explicit user request and an up-to-date remote check.
Recommended artifacts
Save these near the project output when running the loop:
RALPH_OR_QUALITY_LOOP_REPORT.mdfailure_evidence/or references to existing renders/reportsskill_gap_decision.jsonsanitization_report.jsonvalidation_report.json
Scripts
scripts/ralph_autoloop_plan.pycreates a generic failure-classification and loop plan from feedback/artifact hints.scripts/sanitize_skill_contributions.pyscans skill files for project-specific or private terms before publication.scripts/release_readiness_check.pyperforms lightweight manifest/docs/version/path checks before commit/push.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

