CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

uv-package-manager

Comprehensive guide to using uv, an extremely fast Python package installer and resolver written in Rust, for modern Python project management and dependency workflows.

Quality

50%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/uv-package-manager/SKILL.md

The canonical home for this skill is uv-package-manager in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

25%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 has a well-organized trigger list and a sound progressive-disclosure shape, but it contains zero uv-specific executable guidance: the Instructions are generic boilerplate, and the entire substance is delegated to 'resources/implementation-playbook.md', a file missing from the bundle. As packaged, the skill tells Claude when to activate but not how to do anything.

Suggestions

Add concrete, executable uv commands to the Instructions — e.g. 'uv init', 'uv add <pkg>', 'uv sync', 'uv venv', 'uv python install', 'uv lock', 'uv pip compile' — covering the common cases listed in 'Use this skill when'.

Delete the generic filler bullets ('Clarify goals, constraints, and required inputs', 'Apply relevant best practices and validate outcomes', 'Provide actionable steps and verification') and the duplicated description line under the title; replace with uv-specific workflow steps (e.g. init -> add -> sync -> verify with 'uv run').

Fix the broken reference: either include 'resources/implementation-playbook.md' in the bundle or inline the key patterns into SKILL.md — currently the only path to the skill's actual content is a dead link.

DimensionReasoningScore

Conciseness

The body is short and the 'Use this skill when' list earns its place, but it opens by duplicating the frontmatter description verbatim, and the Instructions are filler applicable to any task ('Clarify goals, constraints, and required inputs', 'Apply relevant best practices and validate outcomes') — noticeable waste, matching anchor 3 ('includes some unnecessary explanation or could be tightened') rather than anchor 4's 'minor instances'.

3 / 5

Actionability

There is not a single uv command in the body — no 'uv init', 'uv add', 'uv sync', 'uv venv', nothing — and the Instructions are entirely abstract ('Apply relevant best practices and validate outcomes', 'Provide actionable steps and verification'), matching anchor 1 ('Entirely vague or abstract; no concrete code or commands; only describes rather than instructs'). Not 2 because even anchor 2's example names the tool and concrete actions, which these instructions do not; the sole pointer to detail ('open resources/implementation-playbook.md') targets a file that does not exist in the bundle.

1 / 5

Workflow Clarity

The Instructions offer only a rough meta-sequence ('Clarify goals... Apply... Provide actionable steps') with many gaps and no validation checkpoints for any actual uv task, matching anchor 2 ('Rough sequence present but many gaps; steps poorly defined; validation absent'). Not 1 because a rough sequence and clear use/don't-use scoping do exist; not 3 because no real task-level steps or checkpoints are present at all.

2 / 5

Progressive Disclosure

The body correctly delegates detail to a single, clearly signaled reference ('resources/implementation-playbook.md', listed again under '## Resources'), but per the actual bundle structure that file does not exist — no resources/, references/, scripts/, or assets/ directories are present — so the disclosure chain is broken and all detail is unreachable. This falls between anchor 1 ('impossible to navigate' to any detail) and anchor 3 (structure with working references); the in-file structure is good, but the one reference is dead.

2 / 5

Total

8

/

20

Passed

Description

53%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 clearly identifies what uv is and its niche, but reads more like a tagline than a trigger-optimized skill description. It lacks any 'Use when' trigger clause and the natural terms (pip, venv, lockfile, poetry) users would actually say, and leans on marketing fluff ('Comprehensive', 'extremely fast') rather than enumerated capabilities.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user mentions uv, or wants faster pip installs, virtual environments, lockfiles, or Python dependency management.'

Replace marketing fluff ('Comprehensive', 'extremely fast... written in Rust') with enumerated concrete actions: 'Initialize projects, add/remove dependencies, sync virtual environments, manage lockfiles, install Python interpreters, migrate from pip/poetry.'

Include the natural synonyms users say — pip, pip-tools, poetry, venv, requirements.txt, pyproject.toml, lockfile — so the skill triggers on those terms.

DimensionReasoningScore

Specificity

The description names the domain ("Python package installer and resolver") and 1-2 concrete actions (installing, resolving), matching anchor 3 ('Names domain and 1-2 concrete actions, but not comprehensive') rather than anchor 4, because it never enumerates uv's other actions (virtual environments, lockfiles, interpreter installs, migrations) that appear only in the body.

3 / 5

Completeness

The 'what' is clear ("guide to using uv... installer and resolver") but there is no 'Use when...' clause or equivalent trigger guidance in the description — 'when' is only weakly implied by "for modern Python project management and dependency workflows", which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

It contains relevant keywords ("uv", "Python package installer", "resolver", "dependency") but misses the natural phrases users actually say — "pip", "virtual environment/venv", "lockfile", "poetry", "install a package" — matching anchor 3 ('Some relevant keywords but missing common variations or synonyms'). Not 4 because the coverage of natural terms is thin, not just missing 'a few'.

3 / 5

Distinctiveness Conflict Risk

Naming "uv" and "written in Rust" gives a clear niche with minimal conflict risk, but the broad tail "modern Python project management and dependency workflows" could overlap with pip/poetry/pip-tools skills when the user doesn't say 'uv' — mostly distinct with minor overlap, anchor 4. Not 5 because the description lacks explicit distinct triggers like the anchor-5 example's 'Use when working with PDF files'.

4 / 5

Total

13

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills-claude/skills/uv-package-manager/SKILL.md

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.