python-patterns

Python development principles and decision-making. Framework selection, async patterns, type hints, project structure. Teaches thinking, not copying.

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/python-patterns/SKILL.md

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-organized, decision-oriented reference with genuinely concrete library recommendations and some executable code, but it is monolithic, restates some Python basics Claude already knows, and leans on ASCII trees and illustrative stubs rather than consistently executable guidance. It lacks validation checkpoints in its workflows.

Suggestions

Trim restated common knowledge (N+1/select_related/fat-models reminders) and de-duplicate the repeated "think, not copy" messaging to improve token efficiency.

Replace illustrative stubs ("...") with minimal complete runnable snippets so the actionability examples are copy-paste ready.

Split the framework-specific deep-dives (Django, FastAPI) into referenced bundle files so the SKILL.md overview practices real progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient, using compact ASCII decision trees and tables instead of prose, but it restates well-known basics Claude already knows (e.g., "select_related() for FKs", "Avoid N+1 queries", "Fat models, thin views") and repeats the "think, not copy" theme, so it could be tightened.	2 / 3
Actionability	It offers concrete, specific guidance (named libraries like httpx/asyncpg/aiofiles, real async-test code, named Django methods), but a large portion is ASCII decision trees and illustrative stubs ("def find_user(...) -> Optional[User]: ..."), so it is not consistently copy-paste ready.	2 / 3
Workflow Clarity	A decision checklist and framework decision tree provide a usable sequence, but there are no explicit validation checkpoints or feedback loops; since this is decision guidance rather than a destructive/batch operation the missing feedback loop is not a hard cap, yet the sequence still lacks checkpoints.	2 / 3
Progressive Disclosure	The skill is well-organized into clear numbered sections, but it is a single monolithic ~435-line file with all content inline and no references to separate bundle files (none exist); content like the Django and FastAPI sections could be split out, matching the "content that should be separate is inline" anchor.	2 / 3
	Total	8 / 12 Passed

Description

50%

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 clear and reasonably specific about its Python focus but relies on topic-style capability phrasing rather than concrete verb-driven actions. It omits an explicit "Use when..." trigger from the description field, capping completeness, and the broad "Python development" framing carries some conflict risk.

Suggestions

Rewrite capability phrases as concrete verb actions (e.g., "Select frameworks, design async architectures, add type hints, structure projects") to lift specificity toward the top anchor.

Add an explicit "Use when..." trigger clause inside the description field itself (e.g., "Use when writing Python, choosing a framework, adding type hints, or laying out a Python project") so completeness is not capped at 2.

Narrow the opening from the generic "Python development principles" to a more distinctive niche statement to reduce overlap with general Python skills.

Dimension	Reasoning	Score
Specificity	The description names a clear domain ("Python development") and several concrete capability areas ("Framework selection, async patterns, type hints, project structure"), but these are topic phrases rather than verb-driven actions and "Teaches thinking, not copying" is abstract framing, so it falls short of the multiple-specific-actions anchor.	2 / 3
Completeness	It clearly answers what the skill does, but the description field itself contains no "Use when..." clause or explicit trigger guidance (that lives in the separate when_to_use field), so per the judging guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	It includes some natural terms a user would say ("Python", "type hints", "async"), but "Framework selection" and "project structure" are abstract rather than common trigger phrasings, and it misses common variations, matching the "some relevant keywords but missing common variations" anchor.	2 / 3
Distinctiveness Conflict Risk	"Python development principles and decision-making" is a broad framing that could overlap with general Python coding skills, though the named sub-areas (async, type hints, frameworks) give it some specificity, matching the "somewhat specific but could still overlap" anchor.	2 / 3
	Total	8 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: vudovn/ag-kit
Path: .agents/skills/python-patterns/SKILL.md
Commit: 04514f0

Reviewed: about 12 hours ago

Table of Contents

Discovery Implementation Validation

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.