CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

python

Provides modern Python 3.12+ best practices covering syntax, type hints, error handling, project structure, and idiomatic patterns. Use when the user asks to "write Python code", "create a Python module", "set up a Python project", "review Python code", "refactor Python", "add type hints", "fix Python style", or when generating any Python source code. Does not cover any specific library or framework — see the fastmcp, chromadb, pytest-best-practices and fastapi-best-practices skills for those.

65

Quality

82%

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

The canonical home for this skill is modern-python-development in provectus/awos-recruitment

SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

A well-structured, actionable reference skill with excellent progressive disclosure: a lean overview body, one-level-deep references that all exist, and concrete executable code for every topic. The main weakness is token efficiency — the naming conventions table and parts of the legacy/modern table restate knowledge Claude already has and could be trimmed to only the non-obvious rows.

Suggestions

Trim the Naming Conventions table to only non-obvious rows (type alias via the `type` statement, name-mangling guidance, dunder reservation) and drop rows like snake_case functions and PascalCase classes that Claude already knows.

Reduce the Legacy-vs-Modern table to pairs where the modern choice is a genuine policy decision (match/case, `type` statement) and remove pairs Claude applies by default (f-string vs .format, builtin generics).

Make illustrative snippets fully copy-paste ready by including imports (e.g., `from collections.abc import Callable, Awaitable`) or noting they are signature illustrations.

DimensionReasoningScore

Conciseness

The body is terse and tabular with no padded prose, but the Naming Conventions table (PascalCase classes, snake_case functions) and several legacy-vs-modern pairs (f-string vs .format, pathlib vs os.path) restate basic knowledge Claude already has. This is a full section of trimmable material, more than a minor instance, so it sits at anchor 3 rather than 4.

3 / 5

Actionability

Concrete, executable snippets throughout (match/case destructuring, the type statement, a frozen/slots dataclass with default_factory, TaskGroup with except*, walrus). Minor gaps keep it from 5: some snippets are illustrative fragments (def calculate_total(...) -> float: ... with an ellipsis body) or omit imports (Callable[P, Awaitable[None]]), so they are not fully copy-paste ready.

4 / 5

Workflow Clarity

This is a style-reference skill with no multi-step process and no destructive or batch operations, so no validation cap applies; sections are clearly organized and every rule is unambiguous. Not 5 because the simple-skill exception targets under-50-line skills, and this ~197-line body gives no ordering of when to apply which section; not 3 because nothing is implicit or incoherent.

4 / 5

Progressive Disclosure

The SKILL.md body is an appropriately sized overview, and the four references (modern-syntax.md, type-hints.md, patterns.md, project-structure.md) are each clearly signaled with per-file scope notes in the Additional Resources section. Verified against the actual bundle: all four files exist, are one level deep, and contain no nested cross-file references.

5 / 5

Total

16

/

20

Passed

Description

87%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: third-person, explicit what/when structure with seven natural trigger phrases, plus explicit boundary de-scoping that prevents conflicts with library-specific sibling skills. The only gaps are missing synonyms/file extensions (e.g., ".py", "Pythonic") and topic-area phrasing rather than action-oriented phrasing.

DimensionReasoningScore

Specificity

Enumerates five concrete coverage areas ("syntax, type hints, error handling, project structure, and idiomatic patterns") within a clearly named domain (modern Python 3.12+ best practices). Not 5 because it lists topic areas rather than multiple concrete actions; not 3 because coverage goes well beyond 1-2 items.

4 / 5

Completeness

Explicitly answers both what ("Provides modern Python 3.12+ best practices covering...") and when ("Use when the user asks to...") with concrete trigger phrases, matching the top anchor exactly.

5 / 5

Trigger Term Quality

Seven natural, quotable trigger phrases ("write Python code", "refactor Python", "add type hints", "fix Python style") that users would genuinely say. Not 5 because it lacks synonyms and file extensions such as ".py" or "Pythonic"; not 3 because keyword coverage is thorough, not partial.

4 / 5

Distinctiveness Conflict Risk

Explicitly de-scopes libraries/frameworks and redirects to named sibling skills ("see the fastmcp, chromadb, pytest-best-practices and fastapi-best-practices skills"), giving it a clear, low-conflict niche of pure language/stdlib guidance.

5 / 5

Total

18

/

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

provectus/awos-recruitment

Path

.claude/skills/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.