antithesis-research

Analyze a codebase to figure out how it should be tested with Antithesis: map the system, identify failure-prone areas and testable properties, and produce the research artifacts needed for workload and environment planning.

Quality

80%

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-research/SKILL.md

Quality

Content

85%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.

The body is well-structured, actionable, and uses progressive disclosure effectively with a clear reference table and explicit validation feedback loops in its workflows. The main opportunity is minor trimming of the Self-Review checklist and tightening the occasional guidance bullet.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and action-oriented; the Definitions and Documentation Grounding sections add only genuinely non-obvious Antithesis-specific terms rather than basic concepts Claude already knows, with minor trimmable bulk in the Self-Review checklist.	4 / 5
Actionability	Workflows give concrete numbered steps with exact output paths and exact grep targets (assert_always!, assert_sometimes!, valid command prefixes), delegating detailed methodology to verified reference files; this is an instruction-only skill with specific, actionable guidance and only minor gaps in the main body.	4 / 5
Workflow Clarity	Clear multi-step sequences with explicit validation checkpoints and feedback loops (evaluate findings, then apply refinements, fill gaps, and escalate biases), capped by a detailed self-review checklist for a batch/multi-artifact process.	5 / 5
Progressive Disclosure	A concise overview body is supported by a Reference Files table pointing one level deep to nine real, verified reference files, each with a stated "when to read" trigger, giving easy navigation and an appropriate content split.	5 / 5
	Total	18 / 20 Passed

Description

75%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 is specific, concrete, and well-differentiated, but it lacks an explicit "Use when..." trigger clause that would tell Claude when to invoke it. Adding trigger guidance would lift the completeness and trigger-term dimensions.

Suggestions

Append a 'Use when...' clause naming the natural trigger phrases (e.g., 'Use when planning how to test a system with Antithesis, or when the user asks for testable properties, failure-prone areas, or Antithesis research artifacts').

Include a couple of common synonyms/variations users might say (e.g., 'property-based testing,' 'reliability testing,' 'chaos testing') to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in a distinct domain: "map the system," "identify failure-prone areas and testable properties," and "produce the research artifacts needed for workload and environment planning" — comprehensive coverage of the research phase.	5 / 5
Completeness	The "what" is explicit, but there is no "Use when..." clause or equivalent trigger guidance, so per the judging guideline a missing when caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms ("codebase," "tested with Antithesis," "failure-prone areas," "testable properties"), but the phrasing is specialized and lacks common synonyms or variations a user might naturally say.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (Antithesis research) with distinct triggers unlikely to overlap with sibling skills like triage, setup, or workload.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: antithesishq/antithesis-skills
Path: antithesis-research/SKILL.md
Commit: 6a6b566

Reviewed: 5 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.