antithesis-setup

Scaffold the Antithesis harness with docker-compose: initialize the working directory, write Dockerfiles and docker-compose.yaml with build directives, and prepare to submit your first Antithesis test run. If the desired setup is Kubernetes, defer to the antithesis-setup-k8s skill.

Quality

77%

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-setup/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.

A well-structured orchestration document: the body stays lean and directive while concrete implementation detail lives in verified, well-signaled reference files, and the workflow includes validation and review checkpoints. The only notable issue is repetition of the launch-skill rule.

Suggestions

State the antithesis-launch rule once in General Guidance and reference it from the other two locations to remove the triplicated instruction.

Trim Self-Review items that verbatim restate the success criteria at the top of the file, keeping only the checks that add new information.

Dimension	Reasoning	Score
Conciseness	Dense, directive prose with no padding of concepts Claude already knows, but minor duplication: the antithesis-launch rule appears three times (Purpose, General Guidance, Self-Review) and the Self-Review checklist partially restates the success criteria.	4 / 5
Actionability	Concrete, executable guidance throughout ('snouty validate' on antithesis/config/, 'platform: linux/amd64', depends_on with 'condition: service_healthy', 'init: true', 'NO_COLOR=1', hyphen hostname rules), with the bulk of executable detail appropriately delegated to real reference files; only minor gaps remain in the body itself.	4 / 5
Workflow Clarity	A clearly sequenced six-step workflow (one reference file per step) with an explicit feedback loop ('check whether what you learned invalidates any decisions from earlier steps'), required local testing before submission, and a comprehensive Self-Review checklist serving as validation checkpoints.	5 / 5
Progressive Disclosure	A clean overview body pointing to six one-level-deep reference files, each with a one-line scope description; all six exist in references/ (verified on disk), and the references/language/ subdirectory is reached via instrumentation.md as an appropriately signaled second tier rather than buried nesting.	5 / 5
	Total	18 / 20 Passed

Description

70%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.

A specific, well-scoped description with strong distinctiveness and good natural keywords, weakened only by the absence of an explicit 'Use when...' trigger clause and some coverage gaps (instrumentation, validation) in the action list.

Suggestions

Add an explicit trigger clause, e.g. 'Use when setting up or scaffolding Antithesis testing for a project with Docker Compose, or when the user mentions Antithesis setup or a first test run.'

Mention the instrumentation/SDK and validation outcomes (e.g., 'install the Antithesis SDK and pass snouty validate') so the action list reflects the skill's actual scope.

Include a few natural variations users would say ('set up Antithesis', 'first Antithesis run') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('initialize the working directory, write Dockerfiles and docker-compose.yaml with build directives, and prepare to submit your first Antithesis test run'), but coverage has minor gaps — instrumentation/SDK setup and validation are part of the skill yet unmentioned, and 'prepare to submit' is soft.	4 / 5
Completeness	The 'what' is concrete and clear, but there is no 'Use when...' clause or equivalent explicit trigger guidance; the Kubernetes sentence is a boundary/deferral rule, not a trigger, which caps completeness at 3.	3 / 5
Trigger Term Quality	Good natural-term coverage for the domain ('Antithesis', 'harness', 'docker-compose', 'Dockerfiles', 'test run', 'Kubernetes'), but few synonyms or variations users might phrase differently (e.g., no 'set up'/'setup' phrasing beyond 'scaffold').	4 / 5
Distinctiveness Conflict Risk	Clear niche ('Antithesis harness with docker-compose') with explicit disambiguation from the nearest sibling skill ('If the desired setup is Kubernetes, defer to the antithesis-setup-k8s skill'), giving minimal conflict risk.	5 / 5
	Total	16 / 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-setup/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.