CtrlK
BlogDocsLog inGet started
Tessl Logo

antithesis-debug

Use this skill to interactively debug Antithesis test runs using the multiverse debugger (MVD session). Open a debugging-session URL, inspect container filesystems and runtime state, run shell commands, and extract evidence from inside the Antithesis environment. Supports both the simplified debugger (default) and the advanced notebook mode.

75

Quality

92%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured skill that provides clear, actionable guidance for debugging Antithesis test runs. Its strengths are excellent progressive disclosure with well-organized reference tables, concrete executable commands, and thorough workflow documentation with validation steps. The main weakness is moderate verbosity — some sections could be tightened, and there's some repetition between the general guidance and earlier sections.

DimensionReasoningScore

Conciseness

The skill is fairly long (~200+ lines) and includes some redundancy — for example, runtime injection is explained in the main body and then reiterated in the 'Advanced mode only' guidance section. The mode detection/switching and page loading checks sections repeat patterns. However, most content is domain-specific knowledge Claude wouldn't have, so the verbosity is moderate rather than severe.

2 / 3

Actionability

The skill provides concrete, executable bash commands throughout — runtime injection, mode detection, mode switching, waitForReady calls, simplified command execution, and page loading checks are all copy-paste ready. The workflows give specific step-by-step instructions with exact commands and method calls.

3 / 3

Workflow Clarity

Multiple workflows are clearly sequenced with numbered steps. The skill includes validation checkpoints (waitForReady, loadingFinished, loadingStatus), error recovery guidance (retry missing-runtime errors, fork fresh branch on nonzero exit), and a self-review checklist. The guidance about sequential execution and not fabricating container names adds important safety constraints.

3 / 3

Progressive Disclosure

The skill is well-structured as an overview with clear tables pointing to specific reference files (setup-session.md, simplified-debugger.md, advanced-debugger.md, notebook.md, actions.md, common-inspections.md). References are one level deep, clearly signaled with 'When to read' guidance, and organized by mode (simplified vs advanced). The main body contains just enough to orient without duplicating reference content.

3 / 3

Total

11

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong skill description that clearly identifies a specific niche (Antithesis multiverse debugger sessions), lists concrete actions (open URLs, inspect filesystems, run shell commands, extract evidence), and provides clear trigger context. The only minor issue is the use of second-person-adjacent 'Use this skill to' phrasing, but it effectively communicates both what the skill does and when to use it.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: 'Open a debugging-session URL, inspect container filesystems and runtime state, run shell commands, and extract evidence from inside the Antithesis environment.' Also mentions two modes: simplified debugger and advanced notebook mode.

3 / 3

Completeness

Clearly answers both 'what' (inspect container filesystems, run shell commands, extract evidence, open debugging URLs) and 'when' ('Use this skill to interactively debug Antithesis test runs using the multiverse debugger'). The opening clause serves as an explicit trigger guidance.

3 / 3

Trigger Term Quality

Includes strong natural trigger terms users would say: 'debug', 'Antithesis', 'test runs', 'multiverse debugger', 'MVD session', 'debugging-session URL', 'container filesystems', 'shell commands', 'notebook mode'. These cover the domain well and match what a user working with Antithesis would naturally mention.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with very specific niche: Antithesis multiverse debugger (MVD) sessions. The domain-specific terminology (Antithesis, MVD, multiverse debugger) makes it extremely unlikely to conflict with other skills.

3 / 3

Total

12

/

12

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
antithesishq/antithesis-skills
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.