CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

python-code-style

Python code style, linting, formatting, naming conventions, and documentation standards. Use when writing new code, reviewing style, configuring linters, writing docstrings, or establishing project standards.

Quality

78%

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 ./plugins/python-development/skills/python-code-style/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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-organized, highly actionable standards reference whose main weakness is token efficiency: roughly half the body restates knowledge Claude already has (PEP 8 naming, import ordering, docstring format, README/changelog structure). Moving reference material into bundle files and keeping only the project-specific decisions inline would sharpen both conciseness and progressive disclosure.

Suggestions

Cut or drastically compress Pattern 3 (naming conventions), Pattern 4 (import grouping), and Pattern 7 (README/CHANGELOG templates) — Claude already knows PEP 8, import ordering, and Keep-a-Changelog; keep only the project-specific choices (Google-style docstrings, 120-char lines, absolute imports).

Move docstring examples and README/CHANGELOG scaffolds into references/ files (e.g., DOCSTRINGS.md, TEMPLATES.md) and keep SKILL.md as a lean overview with one-level-deep pointers.

Fix the Quick Start block: the TOML config is inside a ```bash fence; label it ```toml or split install commands from configuration.

Add a short end-to-end "set up a new project" sequence (install → configure pyproject.toml → run ruff check --fix → wire into CI) with a verification step to back the 'Automate in CI' bullet.

DimensionReasoningScore

Conciseness

Several sections re-teach concepts Claude already knows: PEP 8 naming with snake_case/PascalCase/SCREAMING_SNAKE_CASE good-vs-avoid lists (Pattern 3), stdlib/third-party/local import grouping (Pattern 4), Google docstring format, and README/Keep-a-Changelog templates (Pattern 7). That is several padded/unnecessary sections, matching anchor 2; not 1 because there is no fluffy prose and the tooling configs (ruff/mypy/pyright settings, 120-char lines, py312 target) are genuinely additive project decisions.

2 / 5

Actionability

Nearly everything is copy-paste ready: complete ruff/mypy/pyright TOML configs, executable commands ("pip install ruff mypy", "ruff check --fix .", "ruff format ."), and full worked docstring/class examples covering the common cases. The Quick Start mislabels TOML inside a ```bash fence, but the identical config appears correctly in a ```toml block in Pattern 1, so this stays at anchor 5 rather than dropping to 4.

5 / 5

Workflow Clarity

This is a standards/reference skill rather than a fragile multi-step process, and it is clearly sequenced: When to Use → Quick Start (install → configure) → run commands → Fundamental → Advanced → Best Practices summary. It stays at anchor 4 rather than 5 because there is no explicit end-to-end setup sequence (install, configure, wire into CI, verify) despite "Automate in CI - Run linters on every commit" appearing only as an unexplained bullet in the summary.

4 / 5

Progressive Disclosure

The body is well-sectioned with a clear overview-to-advanced progression, but everything is inlined in a single ~360-line SKILL.md with no bundle files: docstring templates, naming convention examples, and README/CHANGELOG scaffolds are content that naturally belongs in separate reference files. This matches anchor 3 (structure present, but content that should be separate is inline); not 2 because the sectioning and navigation are genuinely good.

3 / 5

Total

14

/

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 that explicitly states both capabilities and usage triggers in a compact form. The main improvement opportunities are converting noun-phrase capabilities into concrete actions and adding high-frequency user terms like tool names and "PEP 8".

Suggestions

Rewrite capability areas as concrete actions, e.g., "Configures ruff/mypy, applies PEP 8 naming conventions, writes Google-style docstrings" instead of the noun list.

Add high-frequency trigger terms users naturally say: "ruff", "mypy", "PEP 8", "format code", "type hints".

DimensionReasoningScore

Specificity

"linting, formatting, naming conventions, and documentation standards" lists several specific capability areas with minor gaps in coverage, matching the anchor for several specific items. It falls below 5 because these are noun-phrase topics rather than concrete actions (e.g., "configure ruff, write Google-style docstrings"), and above 3 because it names far more than 1-2 items.

4 / 5

Completeness

It explicitly answers "what" ("Python code style, linting, formatting, naming conventions, and documentation standards") and "when" with concrete trigger phrases ("Use when writing new code, reviewing style, configuring linters, writing docstrings, or establishing project standards"), exactly matching the anchor for both what AND when with concrete triggers.

5 / 5

Trigger Term Quality

The "Use when" clause supplies natural phrases users would say: "writing new code", "reviewing style", "configuring linters", "writing docstrings", "establishing project standards". Below 5 because common variations users actually say are missing — tool names (ruff, mypy, pylint), "PEP 8", "format code", "type hints"; above 3 because coverage is broad, not just a few relevant keywords.

4 / 5

Distinctiveness Conflict Risk

The Python-specific, style-focused scope ("Python code style... linting, formatting") carves a clear niche with distinct triggers, but the broad "Use when writing new code" trigger could overlap general coding or code-review skills, matching "mostly distinct; minor overlap risk" rather than the minimal-conflict anchor 5.

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

wshobson/agents

Path

plugins/python-development/skills/python-code-style/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.