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

80%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/uv/SKILL.md

Quality

Content

90%Weight 40%Scale 1-5

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

The body is lean, executable, and well-organized with clearly signaled deeper references. The main gap is that the referenced detail files (scripts.md, build.md) are not bundled, slightly undermining progressive disclosure.

Suggestions

Provide the referenced scripts.md and build.md in the bundle, or inline a minimal amount of their key detail so the links resolve.

Consider a one-line note on when to prefer `uv run --with` versus `uv add` to clarify the ad-hoc vs. project dependency distinction.

Dimension	Reasoning	Score
Conciseness	Lean reference card with minimal prose and well-chosen inline comments; assumes Claude's competence and avoids explaining what uv is.	5 / 5
Actionability	Fully executable, copy-paste-ready commands and config snippets (`uv run script.py`, `uv add requests`, `uv init --script foo.py`, build-system toml) covering the common cases.	5 / 5
Workflow Clarity	Commands are clearly organized by task with helpful inline comments, but this is a reference card rather than a sequenced multi-step workflow with checkpoints.	4 / 5
Progressive Disclosure	Good section structure with one-level-deep references to scripts.md and build.md, but those referenced files are not present in the bundle, so the navigation promise is only partially deliverable.	4 / 5
	Total	18 / 20 Passed

Description

70%Weight 40%Scale 1-5

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 and well-targeted to a distinct tool, but it omits an explicit 'Use when...' trigger clause, capping completeness. Adding trigger guidance and a couple more subcommands would raise it.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when managing Python dependencies, running scripts, or the user mentions pip/venv/uv.'

Mention a couple more core uv capabilities (e.g. sync/lock, project management) for fuller coverage of the tool's scope.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "Run scripts with `uv run script.py`", "add deps with `uv add`", "use inline script metadata" — with only minor gaps (no mention of lock/sync/publish).	4 / 5
Completeness	The 'what' is clear (use uv instead of pip/python/venv with specific subcommands), but there is no explicit 'Use when...' clause, so per the cap completeness stays at 3.	3 / 5
Trigger Term Quality	Good keyword coverage including the tool name `uv` and the alternatives users naturally name (pip, python, venv), though a few natural phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	A clear single-tool niche ('Use `uv` instead of pip/python/venv') with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	16 / 20 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: 13bc8f8

Reviewed: 9 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.