CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

antithesis-documentation

Use Antithesis documentation efficiently for product, workflow, and integration questions. Prefer the snouty docs CLI when available, and otherwise request markdown versions of documentation pages directly.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./antithesis-documentation/SKILL.md
SKILL.md
Quality
Evals
Security

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 an excellent, highly actionable workflow document: concrete CLI commands, a clear sequenced process with fallbacks and a self-review checklist, and clean single-file organization. The only real weakness is token efficiency — a padded product overview and unsectioned version/date details that could be trimmed.

Suggestions

Trim the Antithesis Overview to one or two sentences (or drop it in favor of retrieving the overview from the docs themselves), removing staging-comparison details not needed for documentation lookup.

Remove the duplicated "Skill version" line from the body (it already lives in frontmatter metadata) and place version-sensitive details like the 0.8.0 minimum in a clearly labeled compatibility note so they read as constraints rather than narration.

Tighten the "Useful details" and "Direct Markdown Fallback" bullets by merging overlapping path-normalization examples into a single line.

DimensionReasoningScore

Conciseness

The operational sections are lean and command-focused, but the Antithesis Overview explains product-marketing details Claude does not need for doc lookup ("much more hostile than production", "you do not need to compete for deployment locks or worry about environmental drift"), and time-sensitive version information ("older than 0.8.0", plus the duplicated "Skill version: `2026-10-30 d5d7b3b`" already in frontmatter) is not placed in a deprecated/old-patterns section. This makes it mostly efficient with some unnecessary explanation (anchor 3) rather than merely minor trimmable instances (anchor 4).

3 / 5

Actionability

The guidance is fully executable with copy-paste-ready commands throughout — "snouty docs tree --depth 2", "snouty docs search -l <terms>", "snouty docs show <path>", "snouty docs sqlite" — plus concrete URL-conversion examples (".../reference/sdk/go/" becomes ".../reference/sdk/go.md") covering the common cases. As an instruction-only skill, its absence of code is not penalized because the guidance is highly actionable.

5 / 5

Workflow Clarity

The recommended workflow is a clearly numbered 6-step sequence (tree → filter → search → show → cite), with error-recovery guidance (treat the docs-update warning as non-fatal if content is returned; numbered fallback when snouty is missing) and an explicit Self-Review checklist verifying grounding and citation. This matches anchor 5's clear sequence, feedback loops, and checklist; no destructive or batch operations apply a cap.

5 / 5

Progressive Disclosure

There are no bundle files and none are needed: the single-file body is organized into clear, well-labeled sections (Overview, Accessing Documentation, Using snouty docs, Direct Markdown Fallback, Output, Self-Review) where no content warrants splitting out, and navigation is easy. This satisfies anchor 5's "content appropriately split" in spirit for a self-contained single-purpose skill, and is above anchor 4 because there are no organization gaps or misplaced content.

5 / 5

Total

18

/

20

Passed

Description

65%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 clear, appropriately concise description with a strong niche identity and good trigger terms for the Antithesis ecosystem. Its main weakness is the absence of an explicit "when to use" clause and a fuller enumeration of capabilities, which leaves both completeness and specificity in the middle of the scale.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks about Antithesis, its SDKs, setup, workflows, or the snouty CLI, or when answering questions that should be grounded in Antithesis documentation."

Enumerate a few more concrete capabilities (e.g., searching the docs tree, reading specific pages, citing sources) so the description communicates more than just the access method.

Include common natural variations users might say — "Antithesis testing platform", "Antithesis SDK", "Antithesis setup/troubleshooting" — to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain ("Antithesis documentation") and 1-2 concrete actions ("Prefer the snouty docs CLI when available", "request markdown versions of documentation pages directly"), matching the anchor for domain plus 1-2 concrete actions. It does not list several specific capabilities (e.g., searching, browsing the doc tree, citing pages), so it falls short of anchor 4.

3 / 5

Completeness

The "what" is clear ("Use Antithesis documentation efficiently for product, workflow, and integration questions") but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is above anchor 2 because the "what" is specific rather than vague.

3 / 5

Trigger Term Quality

Includes strong natural terms for the niche — "Antithesis", "documentation", "snouty docs CLI", "product, workflow, and integration questions" — which a user with this need would naturally say. A few natural variations ("SDK", "setup", "testing platform", "troubleshooting") are missing, keeping it below anchor 5.

4 / 5

Distinctiveness Conflict Risk

The description is anchored to a distinct brand-specific niche ("Antithesis", "snouty docs CLI") with clear triggers and minimal conflict risk against generic skills, matching anchor 5. No overlap risk with unrelated skills is apparent.

5 / 5

Total

15

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

antithesishq/antithesis-skills

Path

antithesis-documentation/SKILL.md

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.