CtrlK
BlogDocsLog inGet started
Tessl Logo

uv-package-manager

Master the uv package manager for fast Python dependency management, virtual environments, and modern Python project workflows. Use when setting up Python projects, managing dependencies, or optimizing Python development workflows with uv.

52

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

46%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 content is highly actionable, with concrete executable commands and configuration examples for the common uv workflows, but it is a monolithic ~830-line manual rather than a skill overview. Padding, duplicated sections, missing validation checkpoints in multi-step workflows, and the complete absence of progressive disclosure (no reference files) drag the overall quality down substantially.

Suggestions

Split the monolithic body into one-level-deep reference files (e.g., references/docker.md, references/ci-cd.md, references/migration.md, references/command-reference.md) and reduce SKILL.md to a concise overview with well-signaled pointers, per the progressive_disclosure anchor 5 example.

Delete duplicated and already-known content: merge 'Best Practices' with 'Best Practices Summary', remove the repeated lockfile commands (Pattern 7 vs Pattern 15) and the duplicated tool-comparison sections, and drop the Core Concepts / venv-activation explanations Claude already knows.

Add explicit validation checkpoints to workflows (e.g., run 'uv lock --check' after upgrades, verify 'uv --version' and a smoke test after install/migration) and remove unverified flags such as 'uv pip install --jobs' and 'uv lock --no-install'.

DimensionReasoningScore

Conciseness

The ~830-line body is noticeably verbose: a 'Core Concepts' section explaining what uv is ('Blazing fast installation speeds'), platform-by-platform venv activation Claude already knows, a 'Comparison with Other Tools' section that repeats the earlier 'UV vs Traditional Tools' list, and duplicate best-practices sections ('Best Practices' and 'Best Practices Summary' with near-identical items). This matches anchor 2 — several unnecessary explanations and padded sections — rather than anchor 3's 'mostly efficient'.

2 / 5

Actionability

Nearly every section gives executable, copy-paste-ready bash, TOML, YAML, and Dockerfile covering common cases (init/add/sync/lock, CI via setup-uv, multi-stage Docker), which approaches anchor 5. Minor gaps hold it at anchor 4: some commands appear unverified or wrong, e.g. 'uv pip install --jobs 4' (not a documented uv flag) and 'uv lock --no-install' (uv lock does not install), and there are no expected-output examples.

4 / 5

Workflow Clarity

Multi-step workflows (new project, existing project, migration, Docker, CI) are presented as clear command sequences, and 'Verify Installation' plus a Troubleshooting section provide some checkpoints. But validation is otherwise implicit or absent — no check after 'uv lock --upgrade', no verification a migration succeeded, and destructive/batch operations like 'uv cache clean' lack any confirm-then-validate guidance — fitting anchor 3's 'sequence present but checkpoints missing'.

3 / 5

Progressive Disclosure

No reference files exist at all; everything — the full command reference, Docker and CI guides, migration guide, tool comparisons — is inlined in one ~800-line SKILL.md. Anchor 2 ('content that clearly belongs in separate files is inlined') fits best: section headers do provide minimal structure (ruling out 1), but there are no bundle files or one-level-deep references to justify 3 or higher.

2 / 5

Total

11

/

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.

A solid description with an explicit and well-phrased 'Use when...' trigger clause and natural keyword coverage. Its main weakness is a generic 'Master...' verb that names capability domains instead of concrete actions, which limits specificity and keeps completeness just below the top anchor.

DimensionReasoningScore

Specificity

Names the domain ('uv package manager') and capability areas ('fast Python dependency management, virtual environments, and modern Python project workflows') but the only verb is the generic 'Master', with no concrete actions like adding/removing dependencies or locking. It lists more than minimal capability areas (above anchor 2) but stops short of the specific action list anchor 4 requires.

3 / 5

Completeness

Has both an explicit 'what' (dependency management, virtual environments, project workflows with uv) and an explicit 'Use when...' clause with concrete trigger phrases. Below anchor 5 because the 'what' describes domains rather than the specific concrete actions shown in the exemplar.

4 / 5

Trigger Term Quality

Includes natural phrases users would say — 'setting up Python projects', 'managing dependencies', 'Python development workflows', 'virtual environments', 'uv', 'package manager' — matching anchor 4. Not anchor 5: common variations like pip, poetry, lockfile, migration, or 'install Python' are absent.

4 / 5

Distinctiveness Conflict Risk

'uv package manager' carves a clear niche with the tool name as a trigger, but 'setting up Python projects, managing dependencies' is broad enough to overlap with generic pip/poetry/project-setup skills. Minor overlap risk with closely related skills fits anchor 4 rather than the minimal-conflict anchor 5.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (833 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository
Galaxy-Dawn/claude-scholar
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.