python-testing

Select and run Python SDK verification with nox, Makefile targets, Ruff, mypy, pytest markers, sanity tests, type inference checks, and build checks. Use when adding Python tests, diagnosing Python CI, or validating Python SDK/provider changes. Do not use for TypeScript-only checks.

Quality

86%

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

Quality

Content

86%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.

An exemplary lean overview that defers executable detail to a single well-signaled, one-level-deep reference file, respecting the context window while remaining actionable. Minor gaps are the absence of any selection guidance for picking among the listed checks and no inline command examples.

Suggestions

Add one line of selection guidance mapping situations to checks (e.g. 'lint/format -> make fmt/chk; full suite -> make tst') so Claude can choose without always loading the reference.

For changes touching provider packages, name the specific check to run (make type_inference) inline, since that path is non-obvious and the reference itself flags it as requiring inspection.

Dimension	Reasoning	Score
Conciseness	The body is two lean sentences ("Use this skill to choose Python verification." and "Read `references/nox-make.md` before running broad Python checks or adding test coverage.") with no padding and no over-explanation of concepts Claude already knows; every token earns its place.	5 / 5
Actionability	The body gives a concrete pointer (a specific file path with explicit trigger conditions) and the referenced `references/nox-make.md` supplies fully executable commands (make env/fmt/chk/tst/snt/type_inference/build, nox sessions); the only minor gap is that no commands are inlined in the body itself, which is appropriate for progressive disclosure.	4 / 5
Workflow Clarity	As a simple single-purpose skill under 50 lines, the body's clear single action (read the reference, then run the appropriate verification) qualifies for the simple-skill exception; it stops short of 5 because there is no explicit guidance on which check to select for which situation and no validation checkpoints, though no destructive/batch cap applies.	4 / 5
Progressive Disclosure	The body is a clear overview pointing via a well-signaled, one-level-deep reference (`references/nox-make.md`, verified to exist and be well-organized with Setup/Make Targets/Nox Sessions/Test Placement sections); content is appropriately split and easy to navigate, matching the anchor 5 example.	5 / 5
	Total	18 / 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, third-person description that clearly answers both what and when with concrete triggers and a useful negative boundary. The only mild weakness is that the action framing collapses to a single "select and run" verb rather than multiple distinct actions.

Dimension	Reasoning	Score
Specificity	"Select and run Python SDK verification with nox, Makefile targets, Ruff, mypy, pytest markers, sanity tests, type inference checks, and build checks" lists several specific concrete checks/tools with only minor coverage gaps, but the action verb is essentially a single one ("select and run") rather than multiple distinct actions, so it sits just below the comprehensive anchor 5.	4 / 5
Completeness	It explicitly states what ("Select and run Python SDK verification with nox, Makefile targets, Ruff, mypy, ...") and when ("Use when adding Python tests, diagnosing Python CI, or validating Python SDK/provider changes") with concrete trigger phrases, matching the anchor 5 pattern; the negative boundary "Do not use for TypeScript-only checks" further sharpens it.	5 / 5
Trigger Term Quality	Natural trigger phrases like "adding Python tests", "diagnosing Python CI", and "validating Python SDK/provider changes" plus tool names (Ruff, mypy, pytest, nox) give good keyword coverage a user would actually say, though a few common synonyms (e.g. "linting", "type checking") are absent.	4 / 5
Distinctiveness Conflict Risk	It carves a clear Python-SDK-verification niche with distinct triggers and an explicit exclusion ("Do not use for TypeScript-only checks"), minimizing overlap with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ComposioHQ/composio
Path: .agents/skills/python-testing/SKILL.md
Commit: b0cf0f9

Reviewed: about 7 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.