CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

uv-python-project-setup

Create, repair, and validate uv Python project setup. Use when initializing Python apps or libraries, managing uv dependencies, virtual environments, or CI-ready uv workflows.

Quality

75%

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/agent-ops/uv-python-project-setup/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%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 a well-organized, lean process runbook with a clear fail-fast validation loop, but it contains no concrete uv commands or executable guidance, and its progressive-disclosure pointer does not match the actual bundle structure. Its main value is process discipline rather than domain instruction.

Suggestions

Add the core uv commands to the Workflow section (e.g., `uv init --python 3.12`, `uv add <pkg>`, `uv sync --locked`, `uv run pytest`) so the guidance is executable rather than purely procedural.

Fix the Progressive Disclosure section to reference the actual bundle files (references/contract.yaml, references/evals.yaml, references/task-profile.json) instead of the non-existent Infrastructure/... path, so deferred context is actually navigable.

Remove the duplicated frontmatter description from the opening of the body and tighten the Philosophy section to concrete rules, freeing tokens for the missing command detail.

DimensionReasoningScore

Conciseness

The body is lean, assumes Claude's competence, and explains no background concepts, but the verbatim duplication of the frontmatter description in the opening line and the platitudinous "Philosophy" bullets are tokens that could be trimmed. That minor trimmable material keeps it below the every-token-earns-its-place 5 anchor.

4 / 5

Actionability

No concrete uv commands or code appear anywhere: "uv commands" is listed as an output but `uv init`, `uv add`, `uv sync`, or `uv lock` are never shown, and the workflow steps are abstract directives like "Take the smallest action that advances the confirmed goal". This is minimal concrete guidance with the specific executable steps missing, and there is no partial concrete detail to credit a 3.

2 / 5

Workflow Clarity

The 5-step workflow has a clear sequence plus explicit validation checkpoints and a fix-and-rerun loop ("Stop at the first failed gate or blocker", "Rerun the relevant validation after fixes before claiming completion"). It falls short of 5 because the steps themselves are abstract and no concrete validation command is specified.

4 / 5

Progressive Disclosure

Sections are well organized and a Progressive Disclosure section exists, but its only pointer ("Infrastructure/references/deferred-skill-context/agent-ops-uv-python-project-setup/") does not resolve within the bundle, while the actual bundle references (references/contract.yaml, evals.yaml, task-profile.json) are never linked from the body. References present but not clearly signaled matches the 3 anchor rather than the well-signaled 4 anchor.

3 / 5

Total

13

/

20

Passed

Description

83%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 strong description: explicit what and when clauses, natural trigger terms, and a clear uv niche. Its only weaknesses are slightly broad action verbs and a few missing synonyms (venv, lockfile, pyproject.toml).

DimensionReasoningScore

Specificity

"Create, repair, and validate uv Python project setup" names the domain and several concrete actions. It falls short of a 5 because the actions are broad verbs with no sub-task coverage (no lockfile repair, uv sync/add specifics), and above a 3 because more than 1-2 specific actions are listed.

4 / 5

Completeness

It clearly answers both what ("Create, repair, and validate uv Python project setup") and when ("Use when initializing Python apps or libraries, managing uv dependencies, virtual environments, or CI-ready uv workflows") with concrete trigger phrases, matching the 5-anchor example structure.

5 / 5

Trigger Term Quality

Natural terms like "initializing Python apps or libraries", "uv dependencies", "virtual environments", and "CI-ready uv workflows" give good keyword coverage. A few natural terms users would say are missing (e.g., "venv", "lockfile", "pyproject.toml"), so it does not reach comprehensive 5-level coverage.

4 / 5

Distinctiveness Conflict Risk

The uv-specific focus ("uv dependencies", "uv workflows") is a clear niche with minimal conflict risk, but "initializing Python apps" and "virtual environments" could overlap generic Python environment/packaging skills, keeping it at mostly-distinct rather than minimal-risk.

4 / 5

Total

17

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

jscraik/Agent-Skills

Path

Skills/agent-ops/uv-python-project-setup/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.