CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

python-development-python-scaffold

Scaffold Python projects with uv, package structure, type checking, and tests. Use when starting applications, services, or libraries with a consistent development setup.

Quality

76%

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/python-development-python-scaffold/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 delivers highly actionable, executable scaffolding templates and a clear numbered workflow, but it is padded with meta-sections that duplicate the frontmatter, lacks any verification checkpoint after scaffolding, and inlines all framework templates in one large file instead of splitting them into references. Solid mid-to-good quality with clear, fixable structural improvements.

Suggestions

Delete the "Use this skill when", "Do not use this skill when", "Context", and "Requirements" sections and the roleplay opener — they duplicate the frontmatter description and spend tokens without adding guidance (conciseness).

Add an explicit verification checkpoint at the end of the workflow, e.g., "Run `uv sync && uv run pytest -v` and confirm the health endpoint responds before delivering the scaffold" (workflow_clarity).

Split the per-framework templates (FastAPI, Django, Library, CLI) into reference files such as references/fastapi-template.md and keep SKILL.md as a concise overview with clearly signaled links, which would also let version pins live where they can be updated independently (progressive_disclosure, conciseness).

DimensionReasoningScore

Conciseness

The templates and commands are tight, but the roleplay opener ("You are a Python project architecture expert...") and the "Use this skill when" / "Do not use this skill when" / "Context" / "Requirements" meta-sections duplicate the frontmatter and pad the file, and pinned versions ("fastapi>=0.110.0", "ruff>=0.2.0") are time-sensitive content outside any deprecation section. Mostly efficient with some unnecessary content — not 2, since the bulk is useful template material rather than explanations of concepts Claude already knows.

3 / 5

Actionability

Concrete, copy-paste-ready material throughout: `uv init <project-name>`, full directory trees, complete pyproject.toml files, main.py, cli.py, Makefile, and .env.example. Minor gaps keep it from 5: no test file content despite conftest.py/test_users.py appearing in the tree, no Django structure tree, and no template for the listed "Generic" project type.

4 / 5

Workflow Clarity

Steps 1–7 are clearly sequenced (analyze type → init with uv → generate structure → configure tools), but no validation checkpoint exists anywhere — the workflow never instructs running `uv sync` or `uv run pytest` to confirm the scaffold works, even though a `make test` target is defined. Sequence present but checkpoints missing or implicit, matching the 3 anchor rather than 4 where only minor validation gaps exist.

3 / 5

Progressive Disclosure

Section headers are clear and well-organized, but ~280 lines of per-framework templates (FastAPI, Django, Library, CLI) are inlined in SKILL.md with no references/ files at all — content that should be separate is inline, matching the 3 anchor. Not 2 because the file is genuinely well-structured with distinct numbered sections, unlike a header-less wall of text.

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.

The description is strong: it names concrete capabilities with a distinctive tool (uv) and pairs a clear what with an explicit, specific Use-when clause. Its only weaknesses are minor — a slightly umbrella lead verb, a few missing natural trigger synonyms, and modest overlap risk with sibling Python development skills.

DimensionReasoningScore

Specificity

"Scaffold Python projects with uv, package structure, type checking, and tests" lists several concrete actions plus a named tool (uv), matching the anchor for several specific actions with minor gaps. Not 5 because "Scaffold Python projects" acts as an umbrella phrase and coverage is not fully comprehensive.

4 / 5

Completeness

Explicitly answers both: what ("Scaffold Python projects with uv, package structure, type checking, and tests") and when ("Use when starting applications, services, or libraries with a consistent development setup") with concrete trigger phrases. The when-clause is specific and explicit, matching the top anchor rather than the 4 anchor where the when could be more specific.

5 / 5

Trigger Term Quality

Natural phrases like "starting applications, services, or libraries", "Python projects", and "uv" are what users would say when needing this skill. A few natural terms are missing (e.g., "new project", "set up", "boilerplate"), matching the good-coverage-with-gaps anchor rather than the comprehensive one.

4 / 5

Distinctiveness Conflict Risk

"Scaffold Python projects with uv" carves a clear new-project-creation niche, but the breadth (tests, type checking, implied frameworks) creates minor overlap risk with closely related Python tooling skills. Mostly distinct with minor overlap, matching the 4 anchor rather than the minimal-conflict 5 anchor.

4 / 5

Total

17

/

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/python-development-python-scaffold/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.