python-architecture

Activate when creating new modules, refactoring class hierarchies, introducing design patterns, or making changes spanning 3+ files in the APM CLI codebase.

Quality

78%

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-architecture/SKILL.md

Quality

Content

82%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 content is a tight, action-oriented architecture guardrail that avoids padding and bakes in a validation checkpoint. It could improve progressive-disclosure labeling and add an executable example command to nudge it to full marks.

Suggestions

Add one concrete example invocation of `scripts/lint-architecture-boundaries.sh` (and a representative regression-test name) so the guardrail step is copy-paste ready.

Make the deferred references explicit navigation, e.g. 'See [.apm/instructions/architecture.instructions.md](...) for the full centralization rule' and label the persona link as 'See the Python architect persona for...'.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: terse bullet rules with no padding, no explanation of what design patterns or base classes are, and every line earns its place.	5 / 5
Actionability	It names concrete anchors to follow (BaseIntegrator, CommandLogger, AuthResolver) and points to executable artifacts (lint-architecture-boundaries.sh, a regression test), but offers no copy-paste code or command invocation for the common cases.	4 / 5
Workflow Clarity	It prescribes a clear sequence of decisions (follow existing patterns -> extend the canonical owner -> lock with dual guardrail) including an explicit validation check (lint script plus regression test), though it is rule-oriented rather than a numbered multi-step workflow.	4 / 5
Progressive Disclosure	Structure is clean with focused sections, and the deep rule is correctly deferred to a one-level-deep reference (`.apm/instructions/architecture.instructions.md`) plus a persona link, but references are plain paths rather than clearly labeled 'See X for Y' navigation.	4 / 5
	Total	17 / 20 Passed

Description

75%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 concrete and well-scoped to a specific codebase, with explicit activation triggers. It would benefit from richer trigger synonyms and a slightly broader 'when' enumeration to reach full marks.

Suggestions

Add natural synonyms and concrete file patterns users might name (e.g. 'base classes', 'shared logic', 'src/apm_cli/**') to broaden trigger coverage.

Expand the 'when' clause to mention a couple more common scenarios (e.g. 'adding cross-cutting concerns like logging or auth') so activation guidance is more comprehensive.

Dimension	Reasoning	Score
Specificity	It names concrete actions ('creating new modules, refactoring class hierarchies, introducing design patterns, making changes spanning 3+ files'), listing several specific triggers rather than vague abstractions.	4 / 5
Completeness	It has a clear 'what' (architecture-level changes) and an explicit 'when' trigger ('Activate when...'), though the 'when' clause is narrow and could enumerate more scenarios.	4 / 5
Trigger Term Quality	It surfaces natural phrasing users would say ('refactoring class hierarchies', 'design patterns', '3+ files') but lacks synonyms/file extensions, so a few common variations are missing.	4 / 5
Distinctiveness Conflict Risk	The scope is pinned to the APM CLI codebase and large-span architectural changes, making it mostly distinct from generic coding skills with only minor overlap risk.	4 / 5
	Total	16 / 20 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
relative_links	Relative link issues: 1 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: microsoft/apm
Path: .agents/skills/python-architecture/SKILL.md
Commit: 71a877c

Reviewed: ~5 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.