antithesis-debug

Interactively debug an Antithesis test run in the multiverse debugger (MVD): launch a session from a run, open a debugging-session URL, and inspect container filesystem and runtime state from inside the run.

Quality

75%

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-debug/SKILL.md

Quality

Content

90%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 content is highly actionable with executable commands, well-sequenced workflows that include validation and feedback loops, and a clean one-level-deep progressive disclosure structure backed by real reference and asset files. Minor verbosity in repeated waitForReady examples keeps conciseness just below 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with executable commands and minimal concept re-explanation, though sections like the runtime-injection and page-loading checks repeat similar waitForReady patterns and could be trimmed slightly.	4 / 5
Actionability	It provides copy-paste-ready agent-browser eval commands covering mode detection, switching, runtime injection, and ready-checks, with specific examples for the common simplified and advanced cases.	5 / 5
Workflow Clarity	Multiple recommended workflows are numbered with explicit validation checkpoints (inject runtime, waitForReady, confirm page landed), and the destructive-session guidance includes retry/reinject feedback loops plus a self-review checklist.	5 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled, one-level-deep references (setup-session, simplified-debugger, advanced-debugger, notebook, actions, common-inspections, download-log) plus an assets/ folder, and all referenced paths exist in the bundle.	5 / 5
	Total	19 / 20 Passed

Description

61%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 clearly names the niche and several concrete actions but lacks an explicit 'Use when...' trigger clause, so completeness is capped at 3. It is distinctive and specific to the Antithesis debugger domain.

Suggestions

Add an explicit 'Use when ...' clause listing natural user triggers (e.g., when the user gives an Antithesis debugging-session URL, asks to inspect a container in a run, or the triage skill has launched an MVD session).

Surface the 'debugging-session URL' as a natural trigger phrase since it is the primary user-supplied input.

Consider noting 'events' alongside filesystem and runtime state to round out the concrete actions.

Dimension	Reasoning	Score
Specificity	It lists several concrete actions ('launch a session from a run, open a debugging-session URL, and inspect container filesystem and runtime state from inside the run'), but coverage is slightly compressed relative to the skill's full scope.	4 / 5
Completeness	The 'what' is clearly stated, but there is no 'Use when...' clause or equivalent explicit 'when' guidance in the description itself, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	It names the domain ('Antithesis', 'multiverse debugger', 'MVD', 'container filesystem', 'runtime state') but omits the most natural user-side phrasings (e.g., 'debug an Antithesis run', 'debugging-session URL') as discrete trigger terms.	3 / 5
Distinctiveness Conflict Risk	It occupies a clear niche (the Antithesis MVD debugger) with distinct, domain-specific triggers and minimal overlap risk with other skills.	5 / 5
	Total	15 / 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-debug/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.