antithesis-workload
Implement Antithesis workloads by turning the property catalog into SDK assertions and test commands, then refine coverage after triage.
51
55%
Does it follow best practices?
Impact
—
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 moderately specific but could be more concrete, and the trigger terms are technical without covering natural user language variations.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Antithesis testing, writing workloads, implementing property-based assertions, or triaging Antithesis test results.'
Include more natural trigger terms and variations a user might say, such as 'chaos testing', 'fault injection', 'Antithesis SDK', 'property-based testing', or 'test coverage'.
Make the actions more concrete—specify what 'refine coverage after triage' entails, e.g., 'add missing assertions, update test commands based on triage findings, expand property coverage'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Antithesis workloads) and some actions (turning property catalog into SDK assertions, test commands, refine coverage after triage), but the actions are somewhat abstract and not fully concrete—e.g., 'refine coverage after triage' is vague about what specific steps are taken. | 2 / 3 |
Completeness | Describes what the skill does (implement Antithesis workloads via SDK assertions and test commands) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'when' is entirely absent, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Antithesis', 'workloads', 'SDK assertions', 'property catalog', and 'triage', but these are fairly technical/niche terms. Missing common variations or natural phrases a user might say, such as 'testing', 'fault injection', or 'chaos testing'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly specific to the Antithesis testing platform with distinct terminology (property catalog, SDK assertions, Antithesis workloads). Very unlikely to conflict with other skills due to the niche domain. | 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 excellent workflow clarity and progressive disclosure. Its main weakness is the lack of concrete, executable code examples in the body — the skill describes what to do at a process level but delegates all implementation specifics to reference files. The content is somewhat verbose, particularly in the scoping and self-review sections, though much of it conveys genuinely novel domain knowledge.
Suggestions
Add at least one concrete SDK assertion code example (e.g., an Always assertion for a safety property) directly in the body so the skill is actionable without reading reference files first.
Add a minimal example of a test command file structure showing the directory layout and a sample command with valid prefix to make the test template guidance concrete.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is thorough but verbose in places — the scoping section, recommendation strategy, and self-review checklist are lengthy. Some guidance (e.g., explaining why one property at a time, the provenance display examples) could be tightened. However, most content is domain-specific knowledge Claude wouldn't have, so the verbosity is partially justified. | 2 / 3 |
Actionability | The skill provides clear workflows and specific file paths, but lacks executable code examples — no SDK assertion snippets, no sample test command structure, no concrete code showing how to wire up an assertion. The guidance is specific in terms of process but abstract in terms of implementation artifacts. References to external files (references/assertions.md, etc.) may contain the concrete examples, but the main skill body doesn't. | 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, detect-recommend-confirm-implement pattern). The scoping section handles edge cases well (user specifies property vs. not, single vs. multiple). The self-review checklist serves as a comprehensive validation step. | 3 / 3 |
Progressive Disclosure | The skill has a clear reference table mapping 5 reference files to when they should be read, workflows specify exactly which references to read at each step, and the skill appropriately delegates to other skills (antithesis-research, antithesis-setup, antithesis-triage, antithesis-launch). Content is well-structured with clear sections and one-level-deep references. | 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
f837248
- 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.