CtrlK
BlogDocsLog inGet started
Tessl Logo

write-vibe-tests

Write or refactor Mistral Vibe tests with proper decoupling. Use when adding behavior coverage, testing ports/adapters, replacing brittle mocks, creating fakes, adding characterization tests before refactors, or changing tests under tests/ for vibe/core, vibe/cli, vibe/acp, tools, config, sessions, skills, hooks, MCP, or setup.

68

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 body is lean, actionable, and well-organized, giving Claude concrete boundaries, tooling, and verification commands without explaining concepts it already knows. The main gaps are the absence of a concrete example test and an explicit validate-fix-retry feedback loop.

Suggestions

Add a short, copy-pasteable example test (e.g. a fake-adapter behavior test) to make the actionability fully concrete.

Make the Verification flow's error-recovery loop explicit (e.g. 'If ruff/pytest fail: fix and re-run until green') to reach a 5 on workflow_clarity.

Trim the minor overlap between the 'Avoid' bullets and the 'Prefer Fakes Over Mocks' / 'Core Principle' sections to tighten conciseness.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence — no basic explanations of pytest or testing concepts — with every section earning its place; minor duplication between the 'Avoid' list and earlier principles keeps it just short of a 5.

4 / 5

Actionability

Provides concrete, executable guidance: a boundaries table, specific tooling stack (pytest, pytest-asyncio, respx, pytest-textual-snapshot), and copy-paste verification commands ('uv run ruff format .', 'uv run pytest <test-path>'); lacks an actual example test, which would make it fully copy-paste ready.

4 / 5

Workflow Clarity

The 'Legacy Or Refactor Workflow' is a clear 5-step sequence and the 'Verification' section gives an ordered format/check/test/pyright flow with an implied fix loop; checkpoints are present but the error-recovery feedback loop is implicit rather than explicit.

4 / 5

Progressive Disclosure

Well-organized with clear section headers (Core Principle, Boundaries, Fakes, Workflow, Test Shape, Avoid, Verification) and no external references needed; at ~70 lines with all content inline it is well structured but slightly above the under-50-line simple-skill exception.

4 / 5

Total

16

/

20

Passed

Description

92%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 specific, complete, and distinct: it states concrete actions, explicit 'Use when' triggers, and a clearly bounded niche. The only minor weakness is that several trigger terms lean on testing jargon rather than the most natural user phrasing.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Write or refactor', 'adding behavior coverage, testing ports/adapters, replacing brittle mocks, creating fakes, adding characterization tests' — with comprehensive coverage of the test-writing domain.

5 / 5

Completeness

Explicitly answers 'what' ('Write or refactor Mistral Vibe tests with proper decoupling') and 'when' ('Use when adding behavior coverage, testing ports/adapters, replacing brittle mocks, creating fakes...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong keyword coverage including natural synonyms (fakes, brittle mocks, characterization tests) and enumerated code areas (vibe/core, vibe/cli, vibe/acp, tools, config, sessions, hooks, MCP); slightly jargon-heavy rather than user-natural phrasing, so not a 5.

4 / 5

Distinctiveness Conflict Risk

Niche is clearly scoped to 'Mistral Vibe tests' across a specific enumerated set of areas, giving distinct triggers and minimal conflict risk with other skills.

5 / 5

Total

19

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
mistralai/mistral-vibe
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.