CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

55%

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-package-manager/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

18%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 short and neatly sectioned but contains almost no uv-specific substance: no commands, no code, and no concrete workflow, with all real guidance deferred to a playbook file that is missing from the bundle. Generic filler instructions and tautological exclusions occupy the space where executable uv guidance should be.

Suggestions

Add concrete, executable uv guidance to the Instructions section — e.g. `uv init`, `uv add <pkg>`, `uv sync`, `uv venv`, `uv python install` — replacing abstract directives like "Apply relevant best practices and validate outcomes".

Provide a step-by-step workflow with validation checkpoints (e.g. init project → add dependencies → `uv sync` → verify with `uv lock --check` / `uv run`) instead of the generic clarify/apply/validate bullets.

Fix the dangling reference: either include `resources/implementation-playbook.md` in the bundle or remove the pointer, since all detailed patterns currently live in a file that does not exist.

DimensionReasoningScore

Conciseness

The body is brief, but not every token earns its place: "an extremely fast Python package installer and resolver written in Rust" is background Claude already knows, "The task is unrelated to uv package manager" is a tautology, and "Apply relevant best practices and validate outcomes" is generic filler. It is not long-winded enough for score 2, but the removable filler in three sections keeps it below score 4.

3 / 5

Actionability

There is no concrete code or command anywhere: the Instructions are abstract directives ("Clarify goals, constraints, and required inputs", "Provide actionable steps and verification") that could apply to any skill — no `uv init`, `uv add`, `uv sync`, `uv venv`, or any uv-specific executable guidance. This matches the "entirely vague; only describes rather than instructs" anchor; it does not reach score 2 because not even a high-level uv-specific hint exists.

1 / 5

Workflow Clarity

No sequenced uv workflow is presented; the Instructions bullets form a generic meta-process (clarify → apply → provide) with no task steps, ordering, or validation checkpoints for any uv operation. Even the score-2 anchor's rough "open → change → save" style sequence is absent, so this sits at the "steps missing or incoherent" anchor.

1 / 5

Progressive Disclosure

The single reference "resources/implementation-playbook.md" is clearly signaled in both Instructions and Resources, but the file does not exist in the bundle (no resources/, references/, scripts/, or assets/ directories), so the detail it defers to is unreachable — the actual bundle structure is a dangling path carrying all substantive content. Not score 3 because a broken reference that strands all detailed content fails navigation worse than a poorly signaled but real one; not score 1 because the SKILL.md itself is sectioned and the reference is only one level deep.

2 / 5

Total

7

/

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 a clear what/when structure anchored to a named tool and natural trigger phrases. Its main weaknesses are the generic "Master" verb (areas named instead of concrete actions) and missing common trigger synonyms like pip, poetry, venv, and lockfile that would sharpen both capability coverage and firing precision.

DimensionReasoningScore

Specificity

"Master the uv package manager for fast Python dependency management, virtual environments, and modern Python project workflows" names the domain and several functional areas, but the only verb is the generic "Master" — no concrete actions like installing packages, creating environments, or resolving dependencies are stated. It exceeds the score-2 anchor (which only names a domain) but lacks the several specific actions needed for score 4.

3 / 5

Completeness

Both parts are present: a clear "what" ("Master the uv package manager for fast Python dependency management, virtual environments, and modern Python project workflows") and an explicit "Use when..." clause with three concrete triggers. Not score 5 because the when-clause omits core uv scenarios (pip/poetry migration, lockfiles, interpreter installs) and the what leans on the generic "Master"; not score 3 because the when is explicit rather than implied.

4 / 5

Trigger Term Quality

"Use when setting up Python projects, managing dependencies, or optimizing Python development workflows with uv" supplies natural phrases a user would say, plus the primary term "uv" itself; however common variations are missing (pip, poetry, venv, requirements.txt, pyproject.toml, lockfile). Coverage goes well beyond the single-keyword score-3 anchor but is not comprehensive enough for score 5.

4 / 5

Distinctiveness Conflict Risk

The named tool "uv" (appearing twice) establishes a clear niche, but triggers like "setting up Python projects, managing dependencies" would also naturally fire for pip/poetry/setuptools skills — minor overlap with closely related tooling. Distinct enough to exceed score 3, but the overlap risk keeps it below score 5.

4 / 5

Total

15

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

rmyndharis/antigravity-skills

Path

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.