CtrlK
BlogDocsLog inGet started
Tessl Logo

testing-core-processors

Use when writing or debugging integration tests for error processors in packages/core/src/processors/. Covers the MockLanguageModelV2 pattern for simulating API errors and verifying retry behavior, plus the build prerequisites for focused vitest runs.

70

Quality

85%

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

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.

A highly actionable, well-structured skill body built on executable code and concrete commands with genuine troubleshooting checkpoints. Slight conciseness trims and a final verification step would lift the remaining dimensions.

Suggestions

Tighten inline code comments (e.g., '// Track calls and captured prompts', the 'IMPORTANT' note) to reduce token cost without losing the gotcha.

Add an explicit final verification step in Test Structure (e.g., 'Run the focused test and confirm all three cases pass green') to complete the workflow loop.

Consider moving the full MockLanguageModelV2 block into a references/ file and summarizing the shape inline, since the body exceeds the simple-skill line threshold.

DimensionReasoningScore

Conciseness

Lean prose with no padding of concepts Claude already knows, and the large code block is justified as a copy-paste reference pattern; a few inline comments and the verbose 'IMPORTANT: Stream response must include all event types' note could be slightly trimmed, keeping it just below the leanest anchor.

4 / 5

Actionability

Fully executable guidance throughout — a complete MockLanguageModelV2 example, specific commands ('pnpm build:core', 'npx vitest run ...'), explicit per-test assertions, and a concrete tool-call message format covering the common cases.

5 / 5

Workflow Clarity

Clear sequencing with a build prerequisite and a validation checkpoint ('If focused vitest runs fail to resolve @internal/test-utils/setup, the build step was skipped') plus an enumerated test-structure checklist with per-test asserts; lacks an explicit final 'run and confirm green' verification step, so it falls just short of the top anchor.

4 / 5

Progressive Disclosure

No bundle files exist and the body is well-organized into clearly labeled sections (Prerequisites, Mock Model Pattern, Stream Mock Gotcha, Test Structure, etc.) with a real external reference (prefill-error-recovery.test.ts); at ~100 lines it slightly exceeds the simple-skill threshold and the core code block could arguably live in a reference file, leaving minor organization gaps.

4 / 5

Total

17

/

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, concrete description with an explicit 'Use when' trigger and a tightly scoped niche. Minor specificity/keyword gaps prevent a perfect score on those dimensions, but completeness and distinctiveness are exemplary.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'writing or debugging integration tests', 'simulating API errors', 'verifying retry behavior', and noting build prerequisites — but omits coverage of the test-structure patterns (happy path / control / selectivity), leaving minor gaps versus a fully comprehensive description.

4 / 5

Completeness

Explicitly answers both 'what' (MockLanguageModelV2 pattern, simulating API errors, verifying retry, build prerequisites) and 'when' with a concrete 'Use when writing or debugging integration tests...' trigger phrase, matching the top anchor.

5 / 5

Trigger Term Quality

Strong natural terms a user would say ('integration tests', 'error processors', 'retry behavior', 'vitest') plus the specific MockLanguageModelV2 hook, but lacks synonyms or alternate phrasings a user might use, so a few natural terms are missing.

4 / 5

Distinctiveness Conflict Risk

Scoped to a precise niche — error processors in packages/core/src/processors/ with MockLanguageModelV2 and vitest signals — giving clear distinct triggers and minimal conflict risk with other skills.

5 / 5

Total

18

/

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
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.