Handles the full pull request workflow for mflux models including testing, diff audits, and repository compliance.

Install

mkdir -p .claude/skills/mflux-pr && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/4638" && unzip -o skill.zip -d .claude/skills/mflux-pr && rm skill.zip

Installs to .claude/skills/mflux-pr

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Make a clean PR in mflux (inspect diff, quick verification, commit, push, open PR) using repo conventions.
106 charsno explicit “when” trigger
Advanced

Key capabilities

  • Perform cross-model diff audits
  • Validate quantized model storage claims
  • Automate fast test execution (linting/unit tests)
  • Verify integration surfaces like tokenizer edge cases
  • Standardize PR formatting for model ports

How it works

It executes a hard-coded sequence of shell commands (linting, testing, disk space verification) to ensure compliance before pushing changes.

Inputs & outputs

You give it
Model name and proposed code changes
You get back
Verification report and prepared PR documentation

When to use mflux-pr

  • Run fast tests before opening a PR
  • Perform cross-model diff audits
  • Verify model porting integration surfaces
  • Sync documentation with model changes

About this skill

mflux pull request workflow

When to Use

  • You’re about to open a PR (or want a safe sequence to do it).

Instructions

  • If you run tests as part of PR hygiene, prefer fast tests first:
    • make test-fast
  • Keep commits focused and messages consistent with repo history.
  • If the PR changes CLI defaults, public APIs, or model behavior, check for README/example drift before opening the PR.
  • Always ask for permission before pushing to the remote repository.
  • If gh isn’t available, fall back to the GitHub web UI (or stop and ask).

Pre-merge checklist (model port PRs)

Use after the core port lands and you are polishing for merge. For the full integration surfaces tick list (LoRA key formats, save routing, tokenizer edge cases, etc. learned from past closed PRs), see mflux-model-portingIntegration surfaces checklist.

Correctness

  1. make lint and make test-fast
  2. Slow golden tests for the new model:
    MFLUX_PRESERVE_TEST_OUTPUT=1 uv run pytest tests/image_generation/test_generate_image_<model>.py -m slow -v
    
  3. Optional but high-signal: diffusers side-by-side + latent injection (mflux-debugging, mflux-manual-testing)

Cross-model diff audit

List files changed outside src/mflux/models/<model>/:

CategoryExpected
pyproject.toml, cli/defaults/defaults.py, ModelConfig, mflux-save routingRequired wiring
README.md table + attributionRequired
Training runner.py, example JSON, .gitignore JSON exceptionsIf training supported
Shared VAE/callback/training one-linersOnly if required; document blast radius in PR
Personal .gitignore, unrelated formattingRemove

Verify quantized README disk claims with measurement:

du -sh ~/.cache/huggingface/hub/models--<org>--<Model>*
mflux-save --model <alias> --quantize 8 --path /tmp/model-q8 && du -sh /tmp/model-q8

Docs / examples

  • Model README matches a recent port (e.g. Flux2): hero image, turbo + base CLI, feature section, disk warning, Notes, Training.
  • Main README.md model table row (correct release date).
  • Showcase asset if other models have one (src/mflux/assets/; may need git add -f when *.jpg is gitignored).

PR description callouts

  • Shared code touched and why (shared VAE, callbacks, training runner, etc.).
  • Reference pipeline features intentionally not ported (optional preprocessors, extra encoders, components omitted from mflux weight downloads).
  • Known non-parity with diffusers (RNG, sigma schedule, optional modules) if golden tests lock mflux-native sampling.

When not to use it

  • If the PR is not related to mflux model porting
  • In repositories without standard makefiles

Prerequisites

Access to `uv` and `pytest`GitHub CLI (`gh`) for PR automation

Limitations

  • Requires human approval before remote pushing
  • Assumes standard directory structures (e.g., `src/mflux/models/`)

How it compares

It automates the specific, repetitive checklist required for model porting, which is prone to manual error.

Compared to similar skills

mflux-pr side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
mflux-pr (this skill)12moReviewAdvanced
unit-test-workflow04moReviewBeginner
python-testing-patterns772moReviewIntermediate
pr-review62moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry