CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

python-best-practices

Python best practices e styleguide

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/backend/python/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

76%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 lean, actionable conventions card: imperative rules, executable commands, and concrete structure examples with no padding. Its main gaps are the absence of an ordered application/validation workflow and minor missing details like tool configuration examples and a reconciliation of the black/isort/flake8 vs. ruff tooling duplication.

DimensionReasoningScore

Conciseness

The body is entirely imperative rules, code examples, directory trees, and commands with zero prose padding or explanation of concepts Claude already knows (e.g., 'SEMPRE usar type hints', bare `black .`, `isort .`, `flake8 .` commands). It matches anchor 5: lean and efficient, assuming Claude's competence — every section earns its place.

5 / 5

Actionability

Concrete and mostly executable: a copy-paste-ready typed function signature, runnable commands (`ruff check . --fix`, `ruff format .`, `mypy src/`), and explicit wrong/right module-structure trees. It falls short of anchor 5 due to minor gaps — no pyproject.toml configuration examples for the listed tools, and the module rule shows file layout but not how to split an existing class.

4 / 5

Workflow Clarity

Rules and a verification checklist are present ('Type hints em todas as funções', 'Ruff para lint e formatação') but there is no ordered application sequence — no guidance on when to run formatting vs. linting vs. type checking, and no validation checkpoints. This matches anchor 3 ('steps listed but validation gaps'). Not 4 because the checklist is unordered items, not a sequenced workflow; not a destructive/batch skill, so no lower cap applies.

3 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/ directories) and all content is appropriately inline for a ~100-line single-file skill, with clear section headers (Type Hints, Estrutura de Módulos, Code Style, Estrutura de Projeto, Checklist) making navigation easy. It scores 4 rather than 5 because it exceeds the under-50-line simple-skill threshold and the frontmatter sources (ruff docs, style guides) are never surfaced as navigation for deeper detail.

4 / 5

Total

16

/

20

Passed

Description

32%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 a bare topic label: it names the Python domain but communicates no concrete capabilities and no usage triggers, making it likely to be skipped or to collide with other Python-related skills. It needs concrete actions and an explicit 'Use when...' clause.

Suggestions

State concrete actions in the description, e.g., 'Applies Python conventions covering type hints, module organization, formatting, and linting with ruff/black/flake8 and mypy'.

Add an explicit trigger clause, e.g., 'Use when writing or reviewing Python code, or when the user mentions PEP 8, code style, linting, or type hints'.

Include natural trigger synonyms in the description itself (PEP 8, code style, linting, formatting) rather than relying on the separate triggers field, to sharpen distinctiveness against other Python skills.

DimensionReasoningScore

Specificity

The description names the domain ("Python best practices e styleguide") but states no concrete actions — no mention of what it actually does (e.g., enforcing type hints, formatting, linting). It sits between anchor 1 (entirely vague) and anchor 2 (names domain, minimal actions), landing on 2 because the Python domain is at least explicitly named.

2 / 5

Completeness

"Python best practices e styleguide" provides only a vague 'what' (a topic label, not stated actions) and no 'when' guidance at all, matching anchor 2 ('vague what and no when'). It is not 3 because the 'what' is not clear — no capability is articulated — and the missing 'Use when...' clause caps it regardless.

2 / 5

Trigger Term Quality

Relevant keywords like "Python", "best practices", and "styleguide" are present and users would naturally say them, but common variations and synonyms (PEP 8, code style, linting, formatting, type hints) are missing from the description itself, matching anchor 3. It is not 4 because keyword coverage is thin for the domain's breadth.

3 / 5

Distinctiveness Conflict Risk

"Best practices" is a catch-all that would overlap with virtually any other Python skill (testing, packaging, linting, project setup), matching anchor 2 ('very broad; high overlap risk'). It is not 3 because within the Python domain the description draws no distinct niche or triggers.

2 / 5

Total

9

/

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

fernandezbaptiste/cursor-multiagent-system

Path

skills/backend/python/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.