CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

64

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/uv/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

An exemplary lean quick-reference with fully executable commands and zero padding. The one real defect is progressive disclosure: both referenced detail files (scripts.md, build.md) are missing from the bundle, leaving broken navigation paths.

Suggestions

Add the missing scripts.md and build.md bundle files (e.g. under references/), or remove/inline the dangling links so no reference points to a nonexistent file.

Add one line distinguishing when to use `uv add` (projects) versus inline script metadata (standalone scripts) to sharpen workflow choice.

DimensionReasoningScore

Conciseness

Lean and efficient — no explanation of what uv or PEP 723 is, just five commented commands, the inline-metadata block, and a minimal TOML snippet. Every token earns its place and it fully assumes Claude's competence. Not below 5: there is no padded or over-explained section anywhere in the body.

5 / 5

Actionability

Fully executable, copy-paste-ready commands covering the common cases: `uv run script.py`, `uv run --with requests script.py`, `uv add requests`, `uv init --script foo.py`, plus the exact inline script metadata block and build-backend TOML. Not 4: there are no gaps — every example is complete and runnable as written, including the version-pinned build-system requires line.

5 / 5

Workflow Clarity

Each command is unambiguous with an inline comment stating its purpose, and the section headers separate the script path from the project path. Not 5: several distinct workflows exist (ad-hoc scripts vs. project dependencies vs. packaging) without explicit guidance on choosing between them or any validation checkpoint (e.g. `uv lock --check` or `uv run` smoke-testing after `uv add`); not 3 because no step is missing or ambiguous for the operations shown.

4 / 5

Progressive Disclosure

Sections are well-organized and references are clearly signaled — "See [scripts.md](scripts.md) for full details on running scripts, locking, and reproducibility" and "See [build.md](build.md) for project structure, namespaces, and file inclusion" — but neither file exists in the bundle, so the promised deeper detail is unreachable. Not 4: dangling references are more than a minor organization gap since navigation dead-ends exactly at the disclosure point; not 2 because the inline content is appropriately thin and the signaling itself is good.

3 / 5

Total

17

/

20

Passed

Description

66%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.

A lean, concrete description that names specific commands, but it omits any explicit trigger guidance for when the skill should be used. Adding a 'Use when...' clause covering dependency installation, virtual environments, and running Python scripts would raise completeness and trigger coverage.

Suggestions

Add an explicit trigger clause, e.g. "Use when installing Python dependencies, running Python scripts, or creating virtual environments — reach for `uv` instead of pip, venv, or pipx."

Include natural trigger variations users say, such as "virtual environment", "install a package", "requirements.txt", and "pyproject.toml".

Mention project-level workflows (e.g. `uv init`, `uv sync`) so the 'what' coverage matches what the skill body actually supports.

DimensionReasoningScore

Specificity

Lists several concrete actions with literal command syntax — "Run scripts with `uv run script.py`", "add deps with `uv add`", "use inline script metadata for standalone scripts" — matching the anchor for several specific actions with minor gaps. Not 5: coverage omits other uv capabilities the skill itself supports (project init, `uv sync`, the `uv_build` packaging backend covered in the body), so it is not comprehensive.

4 / 5

Completeness

Has a clear 'what' (run scripts, add deps, use inline script metadata) but no explicit 'Use when...' clause or equivalent trigger guidance; "Use `uv` instead of pip/python/venv" only weakly implies when to invoke it. Per the judging guideline, a missing 'Use when' clause caps completeness at 3 — above 2 because the 'what' is concrete and specific, below 4 because no 'when' is stated at all.

3 / 5

Trigger Term Quality

Includes the natural terms users would actually say — "pip", "python", "venv", "run scripts", "add deps", "standalone scripts" — giving good keyword coverage. Not 5: common variations like "virtual environment", "install", "requirements.txt", and "pyproject.toml" are missing; not 3 because the pip/python/venv terms are the most-likely user phrases and are all present.

4 / 5

Distinctiveness Conflict Risk

Naming the distinct tool `uv` and its subcommands gives it a clear niche with minimal confusion risk. Not 5: triggers on generic "pip/python/venv" terms creates minor overlap risk with broader Python-environment or dependency-management skills.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing

Warning

Total

15

/

16

Passed

Repository
mitsuhiko/agent-stuff
Reviewed

Table of Contents

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.