antithesis-feature-workload

Design and build an Antithesis workload for a specific feature: analyze the feature, discover its testable properties, build a self-driving workload that runs locally and in Antithesis, and iterate until the feature's behaviors are exercised and its invariants are checked.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./antithesis-feature-workload/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, highly actionable skill body: clear workflows with genuine feedback loops, concrete specifics (paths, SDK types, env vars), and exemplary progressive disclosure via a "when to read" reference table. Only mild trimming of the sibling-skill relationships and self-review sections would improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is instruction-dense with no explanations of concepts Claude already knows, but sections like "Relationship to Other Skills" and the ~20-item Self-Review checklist carry some prose that could be tightened, so it is efficient with minor over-explanation rather than lean throughout.	4 / 5
Actionability	Concrete, executable guidance throughout — exact paths like "antithesis/feature-workloads/<feature-slug>/analysis.md", named SDK assertion types (Always, AlwaysOrUnreachable, Sometimes, Reachable), the ANTITHESIS_OUTPUT_DIR dual-mode switch, and specific tooling (snouty, docker-compose). The only gap is that no code examples appear inline, which the reference files cover.	4 / 5
Workflow Clarity	The 16-step workflow is clearly sequenced with explicit feedback loops ("loop back to step 3", reach-claims-first iteration policy, conditional branching at step 14) and validation checkpoints, plus a dedicated verification step for classifying failures and a self-review checklist.	5 / 5
Progressive Disclosure	The body is a well-organized overview with a reference table that includes a "When to read" column; all seven referenced files exist in references/ and are exactly one level deep, making navigation easy.	5 / 5
	Total	18 / 20 Passed

Description

71%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 capability coverage and a clear niche, undermined by the complete absence of an explicit "when to use" clause. Users would likely find it via the word Antithesis but get no explicit routing signal versus sibling Antithesis skills.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user wants to test a specific feature with Antithesis, mentions building a workload or feature testing, or asks to check a feature's invariants."

Add natural trigger synonyms users would actually say — "test a feature", "fuzz a feature", "feature testing" — to broaden keyword coverage beyond "workload" and "properties".

Sharpen distinctiveness from the sibling antithesis-workload skill by naming the contrast in the description (e.g. "feature-scoped rather than whole-system workload").

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "analyze the feature, discover its testable properties, build a self-driving workload that runs locally and in Antithesis, and iterate until the feature's behaviors are exercised and its invariants are checked" — comprehensively covering the skill's capability space.	5 / 5
Completeness	The "what" is explicit and concrete, but there is no "Use when..." clause or equivalent trigger guidance anywhere in the description, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Good keyword coverage with natural domain terms ("Antithesis workload", "feature", "testable properties", "invariants"), but common user phrasings like "test a feature", "feature testing", or "fuzz a feature" are missing, so it falls short of comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	"Antithesis workload for a specific feature" carves a clear niche, but it shares the "Antithesis + workload" trigger space with the sibling antithesis-workload skill, leaving minor overlap risk rather than minimal.	4 / 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
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

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

Reviewed: 1 day 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.