antithesis-workload
Implement Antithesis workloads by turning the property catalog into SDK assertions and test commands, then refine coverage after triage.
64
55%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./antithesis-workload/SKILL.mdQuality
Discovery
40%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 targets a very specific niche (Antithesis workloads) which gives it strong distinctiveness, but it lacks a 'Use when...' clause entirely, making it incomplete for skill selection purposes. The actions described are somewhat abstract and the trigger terms are heavily jargon-laden, reducing accessibility for natural user queries.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Antithesis testing, writing workloads, property-based testing with Antithesis, or triaging Antithesis test results.'
Include more natural trigger terms and variations users might say, such as 'Antithesis testing', 'property-based testing', 'test workload', 'fault injection testing', or 'Antithesis SDK'.
Make the actions more concrete — specify what 'refine coverage' means (e.g., 'add missing assertions', 'update test commands based on triage findings') and clarify which SDK is involved.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a specific domain (Antithesis workloads) and mentions some actions ('turning the property catalog into SDK assertions and test commands', 'refine coverage after triage'), but these are somewhat abstract and not fully concrete — e.g., what SDK, what kind of assertions, what does 'refine coverage' entail specifically? | 2 / 3 |
Completeness | The description answers 'what does this do' at a moderate level but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and since the 'what' is also only moderately clear, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'Antithesis', 'workloads', 'SDK assertions', 'property catalog', and 'triage', but these are fairly technical/niche. A user might say 'Antithesis' or 'workload' but terms like 'property catalog' and 'SDK assertions' are jargon that may not match natural user queries. Missing common variations or broader trigger terms. | 2 / 3 |
Distinctiveness Conflict Risk | The description is highly specific to Antithesis workloads and property catalogs, which is a very narrow niche. It is unlikely to conflict with other skills due to the specialized domain terminology. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured orchestration skill with strong workflow clarity and progressive disclosure. Its main weakness is the lack of concrete code examples — no SDK assertion snippets, no sample test commands — which forces Claude to rely entirely on the referenced files for implementation details. The content is somewhat verbose in places, particularly the scoping and self-review sections, though much of the detail serves legitimate purposes for a complex multi-step process.
Suggestions
Add at least one concrete code example showing a property being mapped to an SDK assertion call (e.g., an Always assertion for a safety property), so Claude has a template without needing to read reference files first.
Add a minimal example of a test command file with the correct naming convention and structure, showing how it reuses project clients.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly well-structured but includes some verbose sections that could be tightened — e.g., the lengthy scoping discussion about what to do when users ask for multiple properties, and the extensive self-review checklist that repeats concepts already covered. Some definitions (SUT, test template) are reasonable for domain-specific terms, but others like the assertion type definitions could be more compact. | 2 / 3 |
Actionability | The skill provides clear workflows and specific file paths, but lacks concrete executable code examples. There are no actual SDK assertion code snippets, no example test command implementations, and no sample property-to-assertion mappings. The guidance is specific in terms of process but abstract in terms of implementation — it tells Claude what to produce but not how the code should look. | 2 / 3 |
Workflow Clarity | The workflows are clearly sequenced with explicit steps, validation checkpoints (self-review criteria, `snouty validate`), and feedback loops (post-triage iteration cycle). The scoping section provides clear decision trees for different user scenarios. The prerequisite checks with 'DO NOT PROCEED' gates are strong validation checkpoints. | 3 / 3 |
Progressive Disclosure | The skill has excellent progressive disclosure with a clear reference table pointing to specific files for specific tasks (component-implementation.md, assertions.md, test-commands.md, iteration.md). The workflows explicitly sequence when to read each reference file. Cross-skill references (antithesis-research, antithesis-setup, antithesis-triage, antithesis-launch) are well-signaled with clear handoff points. | 3 / 3 |
Total | 10 / 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.
- Repository
- antithesishq/antithesis-skills
- Commit
a851a75
- 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.