mflux-pr
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.zipInstalls 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.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
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
ghisn’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-porting → Integration surfaces checklist.
Correctness
make lintandmake test-fast- 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 - 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>/:
| Category | Expected |
|---|---|
pyproject.toml, cli/defaults/defaults.py, ModelConfig, mflux-save routing | Required wiring |
README.md table + attribution | Required |
Training runner.py, example JSON, .gitignore JSON exceptions | If training supported |
| Shared VAE/callback/training one-liners | Only if required; document blast radius in PR |
Personal .gitignore, unrelated formatting | Remove |
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.mdmodel table row (correct release date). - Showcase asset if other models have one (
src/mflux/assets/; may needgit add -fwhen*.jpgis 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
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.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| mflux-pr (this skill) | 1 | 2mo | Review | Advanced |
| unit-test-workflow | 0 | 4mo | Review | Beginner |
| python-testing-patterns | 77 | 2mo | Review | Intermediate |
| pr-review | 6 | 2mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by filipstrand
View all by filipstrand →You might also like
unit-test-workflow
lasp
Run and validate cdflib unit tests after code changes. Use when editing Python code, verifying regressions, or preparing a PR. Covers default local pytest runs, optional remote-data tests, and failure triage.
python-testing-patterns
wshobson
Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.
pr-review
pytorch
Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".
pytest
prowler-cloud
Pytest testing patterns for Python. Trigger: When writing or refactoring pytest tests (fixtures, mocking, parametrize, markers). For Prowler-specific API/SDK testing conventions, also use prowler-test-api or prowler-test-sdk.
ast-grep-find
parcadei
AST-based code search and refactoring via ast-grep MCP
code-change-verification
openai
Run the mandatory verification stack when changes affect runtime code, tests, or build/test behavior in the OpenAI Agents Python repository.