vitron-ai/themis
Reference tile for Themis, a Node.js and TypeScript unit test framework designed for AI coding agents. Covers unit-test authoring, Jest/Vitest migration, agent-readable failure output with repair hints, and first-class integrations for Claude Code, Cursor, and generic agents.
96
94%
Does it follow best practices?
Impact
97%
2.69xAverage score across 10 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that clearly communicates what the skill does and when to use it. It includes an explicit 'Use when' clause with natural trigger terms, names specific technologies (Themis, Jest, Vitest), and describes concrete actions. The description is concise yet comprehensive, making it easy to distinguish from other testing-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'write unit tests', 'generate a test suite', 'migrate/convert Jest or Vitest tests to Themis', 'runs validation commands', and 'applies Themis migration workflows'. | 3 / 3 |
Completeness | Clearly answers both 'what' (produces Themis-native tests, runs validation commands, applies migration workflows) and 'when' (explicit 'Use when' clause covering writing tests, generating suites, and migrating from Jest/Vitest). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'unit tests', 'test suite', 'Jest', 'Vitest', 'Themis', 'migrate', 'convert', 'Node.js', 'TypeScript'. These cover common variations of how users would phrase requests. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific focus on Themis as a testing framework, with clear differentiation from generic testing skills by naming Jest and Vitest migration and the Node.js/TypeScript context. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong skill file with excellent actionability and workflow clarity. The multi-step processes include proper validation checkpoints and feedback loops for error recovery. Minor verbosity in some sections (Claude Code Integration, Scope Notes) prevents a perfect conciseness score, but overall the content is well-structured and immediately useful.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some sections that could be tightened. The 'Claude Code Integration' and 'Scope Notes' sections add moderate value but border on unnecessary context. The 'Agent-Readable Output' section explaining JSON fields is useful but slightly verbose. | 2 / 3 |
Actionability | Provides fully executable code examples, specific CLI commands with flags, and concrete workflows. The Themis test example is copy-paste ready, and all commands (init, generate, test, migrate) include real flags and arguments. | 3 / 3 |
Workflow Clarity | Both the Primary Workflow and Migration Contract sections have clear numbered sequences with explicit validation checkpoints and feedback loops (test → check failures → fix → rerun-failed → update-contracts if needed → confirm stable). Error recovery paths are well-defined. | 3 / 3 |
Progressive Disclosure | Clear top-level overview with well-signaled one-level-deep references to authoring.md, migration.md, and index.md. Content is appropriately split into focused sections (workflow, authoring rules, migration, agent output) without being monolithic. | 3 / 3 |
Total | 11 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents