CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

real-world-testing

Use when fixing a bug, writing or reviewing tests, or adding a regression test anywhere in Mastra (core, storage adapters, server adapters, memory, client SDKs, integrations). Especially use before mocking a class, model, storage, or server; before writing a unit test that only checks wiring or that a value is defined; before writing a one-off test for a single engine, adapter, or code path; before adding a recorded (__recordings__) fixture; or when a test passes but you aren't sure it reproduces the real failure.

Quality

82%

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

81%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 strong, tight instruction skill: concrete commands and a real-API template, an explicitly validated workflow with feedback loops and a final checklist, and clean organization with no padding. Weaknesses are minor — a few trimmable rationale sentences and placeholder-filled code in the scenario template.

DimensionReasoningScore

Conciseness

Dense and prescriptive with no explanation of concepts Claude already knows — the anti-pattern list, principles, and table all carry specific instruction. Only minor trimmable passages remain, e.g., the opening rationale "it says things are fine, it costs time to run and maintain, and it breaks on harmless refactors" and refactor-breakage being stated in both the anti-pattern list and the principles.

4 / 5

Actionability

Provides copy-paste run commands ("cd packages/core && npx vitest run src/loop/test-utils/aimock/scenarios/<name>.scenario.test.ts"), a near-complete scenario template using the real API (describeForAllEngines, runLoopScenario, sequenceIndex fixtures), and a table mapping areas to shared suites. Minor gaps: the template uses "'...'" placeholders and defers the full API to the repo README.

4 / 5

Workflow Clarity

The numbered principles follow the test lifecycle (design → reproduce → verify → cover paths → consolidate) with explicit validation loops — "Run it against the pre-fix commit... and confirm it fails on the assertion you mean", "break the behavior on purpose and confirm the new test fails", "run them 20–40 times" — plus a final "Before you finish" checklist of checkpoints.

5 / 5

Progressive Disclosure

Well-organized sections with clear headers, a compact area-to-suite table, and one well-signaled external pointer ("Read packages/core/src/loop/test-utils/aimock/README.md for the full API"). No bundle files exist; ~45 lines of aimock operational detail are inlined, which is acceptable at this size but is the main organization gap versus the fully-split anchor 5.

4 / 5

Total

17

/

20

Passed

Description

73%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 trigger-rich, well-scoped description with exemplary "when" guidance and natural developer vocabulary. Its main weakness is that the skill's actual capability (what it does when invoked) is never stated, leaving the reader to infer purpose from the trigger list.

Suggestions

Lead with a one-sentence statement of what the skill does (e.g., "Enforces real-world, failure-reproducing tests over mocks, smoke tests, and one-offs in Mastra") before the "Use when" clauses, so the "what" is explicit rather than inferred.

Narrow the broadest triggers ("fixing a bug", "writing or reviewing tests") to reduce overlap with general debugging or code-review skills — e.g., "fixing a bug that lacks a failing regression test".

Add a natural synonym or two for the test-quality domain (e.g., "flaky test", "integration test") to round out trigger coverage.

DimensionReasoningScore

Specificity

Quotes several concrete trigger situations — "before mocking a class, model, storage, or server", "before writing a unit test that only checks wiring or that a value is defined", "before adding a recorded (__recordings__) fixture" — but never states what the skill itself does, a minor coverage gap versus the comprehensive anchor 5.

4 / 5

Completeness

The "when" is explicit and detailed (multiple "Use when..." / "Especially use before..." clauses), but the "what" is never stated — the skill's actual capability must be inferred from triggers, which caps it below anchor 4 ("Has both 'what' and 'when'"). It sits above anchor 2 because the "when" content is substantive rather than vague.

3 / 5

Trigger Term Quality

Comprehensive natural vocabulary with synonyms: "fixing a bug", "writing or reviewing tests", "adding a regression test", "mocking", "unit test", "one-off test", "recorded fixture", and "a test passes but you aren't sure it reproduces the real failure" — phrases a developer would naturally say when needing this skill.

5 / 5

Distinctiveness Conflict Risk

Scoped to Mastra with distinctive artifacts ("recorded (__recordings__) fixture", "engine, adapter, or code path", "storage adapters", "server adapters"), giving a clear niche with distinct triggers; broad opening triggers like "fixing a bug" and "writing or reviewing tests" create minor overlap risk with general debugging or code-review skills.

4 / 5

Total

16

/

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

mastra-ai/mastra

Path

.agents/skills/real-world-testing/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.