How do I install the Self Review skill?

Run npx skillmds@latest add huggingface/self-review in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Self Review safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Self Review?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Self Review free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Self Review?

Hugging Face (@huggingface) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Self Review by huggingface — Agent Skill

Name: Self Review
Rating: 4.2 (5 reviews)
Author: Hugging Face

Self Review

Use before opening a PR, or whenever asked to self-review a diffusers contribution. Applies the same rubric as the `@claude` CI (checks the diff against references/review-rules.md, traces call paths for dead code). Reports findings grouped by severity, flagging what to fix before submitting (blocking issues + dead code) vs what to leave for the actual review. Report-only — does not edit files.

Hugging Face Updated Sep 10, 2026 10.8k repo stars

File contents

Self-review

Runs the same rubric as the @claude CI reviewer, so you catch issues before a maintainer does — but over your whole PR diff. (The CI scopes itself to src/diffusers/, tests/, and .ai/; for your own PR, also review your docs and scripts.) You're already on the branch with the conventions loaded, so: get the diff → review it against the rubric → report → iterate with the contributor until it's ready, then remind them to share the final notes on the PR.

1. Get the diff

git diff main...HEAD          # use your target branch if not main

If the branch trails main and the diff looks polluted with unrelated merged files, scope to your own commits: git log main..HEAD --oneline, then git show <commit>.

2. Read the rubric

references/review-rules.md is the canonical rubric (the CI pins it from main) — read it and review against it; don't rely on a remembered copy. For the areas you touched, also read references/code_style.md, references/models.md, references/pipelines.md, references/modular.md, references/testing.md, or references/pitfalls.md.

3. Report

Blocking issues — numbered. Each: title → explanation → file.py:line → impact. Cite the rule, e.g. Per references/models.md: "…only keep the inference path."
Non-blocking issues — same format, lower severity.
Dead code (advisory) — a table: path:line · Likely-dead / Used · reason.
Summary — short synthesis and a verdict (READY / NEEDS CHANGES), spelling out:
- Fix before submitting — all blocking issues, and remove the flagged dead code.
- Leave for the actual review — non-blocking issues that aren't obviously correct; raise these with the reviewer rather than guessing at them now.

Report only — do not edit files. Be concrete, cite the rule, review the whole diff, and don't invent issues or flag pure style.

4. Iterate until ready, then share

Expect several rounds: the contributor addresses findings, you review again. Keep working with them to fix as much as possible until the verdict is READY — the Leave for the actual review items are the only ones that should reach the reviewer unresolved. End the final round's report by reminding the contributor to share it on the PR (description or a comment) — it saves the reviewer a few rounds of back-and-forth. Never commit the notes as part of the diff.

---name: self-reviewdescription: Use before opening a PR, or whenever asked to self-review a diffusers contribution. Applies the same rubric as the `@claude` CI (checks the diff against references/review-rules.md, traces call paths for dead code). Reports findings grouped by severity, flagging what to fix before submitting (blocking issues + dead code) vs what to leave for the actual review. Report-only — does not edit files.---# Self-reviewRuns the same rubric as the `@claude` CI reviewer, so you catch issues before amaintainer does — but over your **whole** PR diff. (The CI scopes itself to`src/diffusers/`, `tests/`, and `.ai/`; for your own PR, also review your docsand scripts.) You're already on the branch with the conventions loaded, so: getthediff → review it against the rubric → report → iterate with the contributoruntil it's ready, then remind them to share the final notes on the PR.## 1. Get the diff```bashgit diff main...HEAD # use your target branch if not main```If the branch trails `main` and the diff looks polluted with unrelated mergedfiles, scope to your own commits: `git log main..HEAD --oneline`, then`git show <commit>`.## 2. Read the rubric`references/review-rules.md` is the canonical rubric (the CI pins it from `main`) — readit and review against it; don't rely on a remembered copy. For the areas youtouched, also read `references/code_style.md`, `references/models.md`, `references/pipelines.md`,`references/modular.md`, `references/testing.md`, or `references/pitfalls.md`.## 3. Report- **Blocking issues** — numbered. Each: title → explanation → `file.py:line` → impact. Cite the rule, e.g. *Per `references/models.md`: "…only keep the inference path."*- **Non-blocking issues** — same format, lower severity.- **Dead code (advisory)** — a table: `path:line` · Likely-dead / Used · reason.- **Summary** — short synthesis and a verdict (**READY** / **NEEDS CHANGES**), spelling out: - **Fix before submitting** — all blocking issues, and remove the flagged dead code. - **Leave for the actual review** — non-blocking issues that aren't obviously correct; raise these with the reviewer rather than guessing at them now.Report only — do not edit files. Be concrete, cite the rule, review the wholediff, and don't invent issues or flag pure style.## 4. Iterate until ready, then shareExpect several rounds: the contributor addresses findings, you review again.Keep working with them to fix as much as possible until the verdict is**READY** — the **Leave for the actual review** items are the only ones thatshould reach the reviewer unresolved. End the final round's report byreminding the contributor to share it on the PR (description or a comment) —it saves the reviewer a few rounds of back-and-forth. Never commit the notes aspart of the diff.

Frequently asked questions