uv

Use `uv` instead of pip/python/venv. Run scripts with `uv run script.py`, add deps with `uv add`, use inline script metadata for standalone scripts.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tight, fully actionable command reference with clean organization and no wasted tokens. The one weakness is that its two 'See ...' pointers reference files that are not present in the bundle, undermining progressive disclosure.

Suggestions

Add the referenced scripts.md and build.md files to the references/ bundle so the 'See ...' navigation links resolve to real content.

If those files are intentionally omitted, remove the dangling links or inline the most essential details so the SKILL.md is self-sufficient.

Dimension	Reasoning	Score
Conciseness	The body is lean and entirely commands/code blocks with no conceptual padding or explanations Claude already knows, so every token earns its place.	3 / 3
Actionability	All guidance is concrete and copy-paste ready: runnable uv commands, a complete PEP 723 inline metadata block, and a complete uv_build build-backend TOML snippet.	3 / 3
Workflow Clarity	This is a simple single-purpose reference skill whose commands are unambiguous and well-organized into clear sections, satisfying the simple-skill allowance for a 3 without a multi-step workflow.	3 / 3
Progressive Disclosure	Sections are well-organized and reference pointers are clearly signaled, but the referenced files (scripts.md, build.md) do not exist in the bundle, so the promised one-level-deep navigation is broken.	2 / 3
	Total	11 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, action-oriented, and clearly distinguishable, with natural trigger terms. Its main gap is the absence of an explicit 'Use when...' clause, which leaves the activation condition only implied.

Suggestions

Add an explicit trigger clause such as 'Use when setting up Python environments, installing dependencies, or running Python scripts instead of pip/venv.' to lift completeness to 3.

Surface the inline-script-metadata and build-backend use cases as trigger conditions so users mentioning 'PEP 723' or 'packaging a pure Python project' route here.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with exact commands ('Run scripts with `uv run script.py`', 'add deps with `uv add`', 'use inline script metadata'), matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Clearly states what the skill does but lacks an explicit 'Use when...' trigger clause, so per the guideline the missing explicit when-guidance caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	Covers natural terms a user would actually say (uv, pip, python, venv, scripts, deps); these are the words a user reaching for uv would naturally invoke.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply defined (uv as a pip/python/venv substitute) with distinct triggers, making it unlikely to fire for an unrelated skill.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: mitsuhiko/agent-stuff
Path: skills/uv/SKILL.md
Commit: d265b8e

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.