antithesis-workload

Implement Antithesis workloads by turning the property catalog into SDK assertions and test commands, then refine coverage after triage.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./antithesis-workload/SKILL.md

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 orchestration-skill body: concrete paths, commands, and assertion names throughout; two clearly sequenced workflows with confirmation checkpoints, validation, and a triage-driven feedback loop; and a well-organized one-level-deep reference structure. The main gaps are an orphaned bundle file, some duplicated guidance that could be trimmed, and the absence of even a minimal inline assertion example.

Suggestions

Reference references/multi-test-directories.md from the Reference Files table (or remove it) — it currently exists in the bundle but is unreachable from SKILL.md.

Deduplicate the valid command-prefix list and the reach-claim guidance, each of which appears twice or three times across Definitions, Recommended Workflows, and Self-Review.

Add a 3-5 line inline example of a typical SDK assertion (e.g. an Always and a Sometimes reach claim) so the core artifact is concrete without leaving SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is imperative and dense, defining only Antithesis-specific concepts ("SUT", "Timeline", assertion types) rather than things Claude already knows. Minor over-explanation to trim: the valid command prefixes are listed twice (Definitions and Self-Review) and the reach-claim guidance is stated in workflow step 9 and twice more in Self-Review — anchor 4, not 5.	4 / 5
Actionability	Highly concrete for an instruction-only skill: exact paths ("antithesis/scratchbook/properties/{slug}.md", "/opt/antithesis/test/v1/{name}/"), exact command prefixes, named SDK assertions, runnable commands ("snouty validate", "snouty docs"), and a worked bounds example ("counter changed by some value in `[acknowledged, attempted]`"). Anchor 4, not 5: no inline example of an actual assertion despite assertions being the core output artifact.	4 / 5
Workflow Clarity	Two numbered workflows with a hard user-confirmation checkpoint, "DO NOT PROCEED" prerequisite guards, and an explicit feedback loop (run via antithesis-launch, triage via antithesis-triage, unfired reach claims as the iteration signal), plus a Self-Review checklist and "snouty validate". Matches anchor 5: clear sequence, explicit validation, error-recovery loops, and a checklist.	5 / 5
Progressive Disclosure	The body is a genuine overview with a well-signaled one-level-deep Reference Files table (file + "when to read"), and workflows point to specific references at specific steps; all five referenced files exist. Not 5: references/multi-test-directories.md (135 lines) exists in the bundle but is never referenced from SKILL.md, leaving it unnavigable.	4 / 5
	Total	17 / 20 Passed

Description

66%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.

The description states a clear, concrete "what" with domain-specific actions, but omits any "Use when..." trigger clause, leaving the "when" only weakly implied. This caps completeness and slightly weakens its utility for skill triggering. Adding an explicit trigger clause with natural phrases would lift it to a top-tier description.

Suggestions

Add an explicit "Use when..." clause, e.g. "Use when implementing or improving an Antithesis workload, writing Antithesis SDK assertions, or expanding test-command coverage after a triage run."

Include a few natural trigger variations users might say, such as "property-based testing" or "fault injection", to widen trigger coverage without inflating length.

Briefly distinguish this skill from the sibling antithesis-* skills (research, setup, triage, launch) to reduce overlap risk when a user asks generally about Antithesis work.

Dimension	Reasoning	Score
Specificity	"turning the property catalog into SDK assertions and test commands, then refine coverage after triage" names several concrete, domain-specific actions (map catalog to assertions, create test commands, refine coverage post-triage). Matches anchor 4 — not 5 because coverage isn't comprehensive (no mention of test template organization or value menus), not 3 because more than 1-2 actions are listed.	4 / 5
Completeness	The "what" is clear (implement workloads, map catalog to assertions and commands, refine after triage), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 2 because the what is explicit and concrete.	3 / 5
Trigger Term Quality	Natural terms a user of this toolchain would say: "Antithesis workloads", "SDK assertions", "test commands", "triage". Good keyword coverage matching anchor 4 — not 5 because common variations ("property-based testing", "fault injection", "coverage") are missing.	4 / 5
Distinctiveness Conflict Risk	"Antithesis workloads" carves a clear niche with minimal conflict risk, though sibling skills (antithesis-research, antithesis-triage, antithesis-launch) are closely related and a user asking generally about Antithesis coverage could hit the wrong one. Matches anchor 4 — mostly distinct with minor overlap risk.	4 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: antithesishq/antithesis-skills
Path: antithesis-workload/SKILL.md
Commit: 1fd8470

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.