web-ui-test

Test the IronClaw web UI using the Claude for Chrome browser extension.

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 ./skills/web-ui-test/SKILL.md

Quality

Content

100%

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

The content is a well-structured, actionable manual test checklist with concrete commands, explicit verification checkpoints, and useful operational notes. It is concise and easy to follow end-to-end.

Dimension	Reasoning	Score
Conciseness	The body is lean bullets and commands with no explanation of concepts Claude already knows; troubleshooting notes like the confirm() override earn their tokens operationally.	3 / 3
Actionability	It provides an executable `cargo run` command with env vars, real install URLs, concrete cleanup commands, and specific expected outcomes — copy-paste ready.	3 / 3
Workflow Clarity	A numbered 1–7 checklist with prerequisites, server startup, and cleanup, plus explicit "Verify..." validation checkpoints after each action and a Known Issues section for error recovery.	3 / 3
Progressive Disclosure	A single self-contained SKILL.md with no bundle files and clearly sectioned content (Prerequisites, Starting the Server, Test Checklist, Cleanup, Known Issues); appropriately organized for a simple checklist skill.	3 / 3
	Total	12 / 12 Passed

Description

50%

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 identifies the target product and tool but is a single short clause with no explicit trigger guidance and only one named action. It is adequate but not exemplary.

Suggestions

Add a "Use when manually testing the IronClaw web gateway, the chat/skills tabs, or browser-based UI flows" clause to satisfy the 'when' half of completeness.

Expand the action list to concrete behaviors, e.g. "Verify connection, exercise the Chat and Skills tabs, install and remove skills by search and URL."

Add natural trigger variations such as "browser test", "chrome extension test", or "test the skills tab" so users phrase the need multiple ways.

Dimension	Reasoning	Score
Specificity	Names the domain ("IronClaw web UI"), the mechanism ("Claude for Chrome browser extension"), and a single action ("Test"), but does not list multiple concrete actions like the score-3 anchor requires.	2 / 3
Completeness	It states what the skill does but includes no explicit "Use when..." trigger guidance, so per the judging guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	"Test the ... web UI" is a natural phrase a user might say, but only one framing is offered with no common variations, matching the score-2 anchor rather than the broad coverage of score 3.	2 / 3
Distinctiveness Conflict Risk	The product name (IronClaw) and extension (Claude for Chrome) give it a niche, but the generic "Test the web UI" phrasing and absence of explicit triggers mean it could still overlap with other testing skills.	2 / 3
	Total	8 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nearai/ironclaw
Path: skills/web-ui-test/SKILL.md
Commit: 800b781

Reviewed: 2 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.