After completing code changes, runs tests and pre-commit, then iteratively fixes failures until all pass.

AGPL-3.0Auto-check passedAI & LLM Engineering

Install Validate And Fix

skills CLI
$ npx skills add albumentations-team/AlbumentationsX --skill validate-and-fix -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install albumentations-team/AlbumentationsX validate-and-fix --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/albumentations-team/AlbumentationsX.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/validate-and-fix .claude/skills/validate-and-fix && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
validate-and-fix
GitHub stars
567
Token cost
~847 tokens
SKILL.md length
453 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
AGPL-3.0

At a glance

After completing code changes, runs tests and pre-commit, then iteratively fixes failures until all pass.

  • Works in 4 steps: Name the decision and failure mode:… → Run that focused validation: use the… → Add only required adjacent checks: code… → …
  • Finishing a coding task
  • SKILL.md covers Necessity Rule, Workflow, Rules and Common Pre-commit Fixes
  • Calls uv and git

What it does

Validate And Fix is an agent skill from albumentations-team/AlbumentationsX. After completing code changes, runs tests and pre-commit, then iteratively fixes failures until all pass. Use when finishing a coding task, validating changes, or when the user asks to run tests or fix errors.

Its SKILL.md is about 850 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering Computer vision and Deep learning. The repository describes itself as: Image augmentation for computer vision. AGPL-3.0-only or commercial licensing. The licence is AGPL-3.0.

When your agent uses it

  • Finishing a coding task
  • Validating changes
  • The user asks to run tests

Example prompts

  • “/validate-and-fix”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Name the decision and failure mode: identify the changed contract and the smallest test, check, or artifact that can
  2. Run that focused validation: use the matching test or quality-gate subcommand.
  3. Add only required adjacent checks: code that can affect multiple routes, a workflow/router change, or a release protocol
  4. If a selected command fails: fix the issue, then repeat that command. Do not expand the validation scope unless the

What it can do on your machine

Read from SKILL.md and the folder at commit 1458043. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • uv
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv and git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Validate And Fix loads about 847 tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 453 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~57
When it runs · the whole SKILL.md, loaded when a task matches
~847

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from albumentations-team/AlbumentationsX at commit 1458043, republished under its AGPL-3.0 licence (© albumentations-team). 453 words, ~847 tokens.

Download SKILL.mdSave it as .claude/skills/validate-and-fix/SKILL.md (or your agent's skills folder).
name
validate-and-fix
description
After completing code changes, runs tests and pre-commit, then iteratively fixes failures until all pass. Use when finishing a coding task, validating changes, or when the user asks to run tests or fix errors.

Validate and Fix

Necessity Rule

Every code path, test, and CI job must justify itself with a specific decision it protects and a failure it can expose. Do not add or run work because an adjacent file changed, because a broad command is convenient, or because a check ran in a previous pull request. Remove duplicate coverage instead of accumulating it.

For validation, state the changed contract and select the smallest command set that can falsify it. Add a broader suite only when the changed contract can affect its route. A version-only release uses the release preflight; a dependency or packaging change beyond the version uses the corresponding dependency, artifact, and install checks.

Workflow

  1. Name the decision and failure mode: identify the changed contract and the smallest test, check, or artifact that can reject it.
  2. Run that focused validation: use the matching test or quality-gate subcommand.
  3. Add only required adjacent checks: code that can affect multiple routes, a workflow/router change, or a release protocol may require a broader command. Record why.
  4. If a selected command fails: fix the issue, then repeat that command. Do not expand the validation scope unless the failure proves that the initial scope was incomplete.

For transform or guidance changes, the focused mechanical check is pre-commit run check-ax-rules --all-files. Keep deterministic contract details in docs/contributing/coding_guidelines.md; keep design and benchmark review in the applicable skill.

Before handoff, check git status --short. pre-commit run --all-files omits untracked files, so run pre-commit with --files for each new file until it is staged or tracked. When a change relies on type narrowing, run and report both mypy and Pyrefly.

Show full SKILL.md (180 more words)Show less

Rules

  • Iterate until clean. Do not report errors and stop—fix them.
  • Do not run the full suite merely by habit. Run it when the changed contract, release protocol, or a focused failure requires it.
  • For CI, workflow, support-policy, or dependency-profile changes, also run:
    • uv run python -m tools.ci_matrix check
    • uv run python -m tools.ci_shard check
    • uv run pytest -q tests/test_ci_plan.py tests/test_ci_shard.py tests/test_pr_workflow.py
    • uv run zizmor --format=plain --min-severity=medium --min-confidence=medium .github
  • For legal or packaging workflow changes, follow the license-integrity skill and verify built wheel/sdist artifacts.

Common Pre-commit Fixes

E501 Line too long
  • Never suppress with # noqa: E501 or add E501 to pyproject.toml ignore list.
  • Fix: Split the line at a word or operator boundary. For docstrings, wrap to the next line — the Google format allows multi-line short descriptions. For code, break at (, ,, or +.
C901 / PLR0912 Function too complex / too many branches
  • Never suppress with # noqa: C901, # noqa: PLR0912, or raise the limits in pyproject.toml.
  • Fix: Extract private helper methods that each own a single concern. If a function exceeds the limit it is doing too many things and must be split.

© albumentations-team, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .codex/skills/validate-and-fix of albumentations-team/AlbumentationsX.

Open the folder on GitHubat commit 1458043

Compare with similar skills

Validate And Fix next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Validate And Fix compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Validate And Fix this skillalbumentations-team/AlbumentationsX567—~847Automated safety check: PassAGPL-3.0
Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs13k8 repos~3.3kAutomated safety check: PassMIT
CLIP Image-Text MatchingOrchestra-Research/AI-Research-SKILLs13k7 repos~1.7kAutomated safety check: PassMIT
Kaiming HeK-Dense-AI/mimeo282—~1.6kAutomated safety check: PassMIT
Matlab Analyze Spectral Imagesmatlab/matlab-agentic-toolkit1.1k—~3.7kAutomated safety check: PassCustom licence
Matlab Process Imagesmatlab/matlab-agentic-toolkit1.1k—~3.7kAutomated safety check: PassCustom licence

Similar skills

  • Segment Anything Model Guide

    Orchestra-Research/AI-Research-SKILLs

    Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.

    13k GitHub starsUsed in 8 repos~3.3k tokens
    AI & LLM EngineeringAuto-check passed
  • CLIP Image-Text Matching

    Orchestra-Research/AI-Research-SKILLs

    Explains OpenAI's CLIP model for zero-shot image classification, image-text similarity, semantic image search and content moderation, with install steps and code patterns.

    13k GitHub starsUsed in 7 repos~1.7k tokens
    AI & LLM EngineeringAuto-check passed
  • Kaiming He

    K-Dense-AI/mimeo

    Applies the reasoning style of Kaiming He, computer vision pioneer and creator of ResNet.

    282 GitHub stars~1.6k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed
  • Matlab Analyze Spectral Images

    matlab/matlab-agentic-toolkit

    Work with hyperspectral and multispectral images in MATLAB. An agent skill from matlab/matlab-agentic-toolkit.

    1.1k GitHub stars~3.7k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Matlab Process Images

    matlab/matlab-agentic-toolkit

    Load this first for any task involving images, pictures, photos, scans, frames, volumes, or visual data — including reading, writing, filtering, enhancing, denoising, sharpening, deblurring…

    1.1k GitHub stars~3.7k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Scholar Compute

    joshzyj/open-scholar-skill

    Design and execute computational social science analyses across 11 modules: text-as-data/NLP (STM, BERTopic, Wordfish, BERT, conText embedding regression, LLM annotation + DSL bias correction…

    168 GitHub stars~15k tokensUpdated 21 days ago
    AI & LLM EngineeringAuto-check passed

More from albumentations-team/AlbumentationsX

All 10 skills in this repo
  • Mixing Transforms

    albumentations-team/AlbumentationsX

    Policy for AlbumentationsX transforms that combine multiple images or objects.

    567 GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Release Notes

    albumentations-team/AlbumentationsX

    Generate release notes for AlbumentationsX. An agent skill from albumentations-team/AlbumentationsX.

    567 GitHub stars~685 tokensUpdated today
    Auto-check passed
  • Performance Optimization

    albumentations-team/AlbumentationsX

    Systematic performance audit for AlbumentationsX runtime code.

    567 GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Add Transform

    albumentations-team/AlbumentationsX

    Full checklist for adding a new transform to AlbumentationsX.

    567 GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Docstring Deep Dive

    albumentations-team/AlbumentationsX

    Review public AlbumentationsX docstrings for useful descriptions, runnable examples, parameter semantics, and related transforms.

    567 GitHub stars~534 tokensUpdated today
    Auto-check passed
  • License Integrity

    albumentations-team/AlbumentationsX

    Maintain AlbumentationsX license, CLA, provenance notices, and packaged legal artifacts consistently.

    567 GitHub stars~1.3k tokensUpdated today
    Auto-check passed

Questions about Validate And Fix

What does Validate And Fix do?

After completing code changes, runs tests and pre-commit, then iteratively fixes failures until all pass. Validate And Fix is an agent skill from albumentations-team/AlbumentationsX. After completing code changes, runs tests and pre-commit, then iteratively fixes failures until all pass.

When should I use Validate And Fix?

Validate And Fix fits situations like: finishing a coding task; validating changes; the user asks to run tests.

How do I install Validate And Fix in Claude Code?

Run `npx skills add albumentations-team/AlbumentationsX --skill validate-and-fix -a claude-code`. Or copy the skill folder (.codex/skills/validate-and-fix in albumentations-team/AlbumentationsX) into .claude/skills/validate-and-fix in your project. Claude Code loads it when a task matches its description.

How do I install Validate And Fix in Codex?

Run `npx skills add albumentations-team/AlbumentationsX --skill validate-and-fix -a codex`. Or copy the skill folder (.codex/skills/validate-and-fix in albumentations-team/AlbumentationsX) into .agents/skills/validate-and-fix in your project. Codex loads it when a task matches its description.

Can I use Validate And Fix in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add albumentations-team/AlbumentationsX --skill validate-and-fix -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/validate-and-fix, .gemini/skills/validate-and-fix, .github/skills/validate-and-fix and .opencode/skills/validate-and-fix in your project.

What does Validate And Fix need to run?

Going by SKILL.md and its folder, Validate And Fix needs the command-line tools its instructions call (uv and git). Our summary lists: Python 3.

Does Validate And Fix access the network?

SKILL.md contains no URLs. Its commands use uv and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Validate And Fix safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Validate And Fix use?

Validate And Fix is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Validate And Fix use?

About 847 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Validate And Fix?

Skills that share tags, products or a category with Validate And Fix: Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars), CLIP Image-Text Matching (Orchestra-Research/AI-Research-SKILLs, 13k stars), Kaiming He (K-Dense-AI/mimeo, 282 stars) and Matlab Analyze Spectral Images (matlab/matlab-agentic-toolkit, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Validate And Fix?

albumentations-team (a GitHub organization) maintains it in albumentations-team/AlbumentationsX, which has 567 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 9, 2026.

Source: albumentations-team/AlbumentationsX on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.