web-ui-test

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

Quality

65%

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

75%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 a tight, highly actionable manual test checklist with explicit verification checkpoints and useful error diagnostics throughout. All dimensions land at 4: strong and executable, with only minor gaps (a redundant intro line, a few manual-judgment steps, and an unverified destructive cleanup).

Dimension	Reasoning	Score
Conciseness	The body is a lean, imperative checklist ("Navigate to ...", "Verify ...") with executable commands and no padding of concepts Claude already knows; the only minor trim is line 22 restating the description's purpose. It is not a 5 because of that redundant introductory sentence, and not a 3 because nearly every line earns its place.	4 / 5
Actionability	Concrete, copy-paste-ready guidance is present throughout — `cargo run ...`, exact gateway URLs, a real ClawHub download URL, specific search terms ("markdown"), and explicit per-step assertions. It is not a 5 because some steps rely on manual judgment ("Send a simple message") and cleanup is loosely specified ("Ctrl+C or by killing the process").	4 / 5
Workflow Clarity	A numbered 7-step checklist with explicit per-step "Verify" checkpoints, startup gating ("Wait for 'Agent ironclaw ready and listening' before proceeding"), and error-recovery diagnostics for each fragile step. It is not a 5 because the destructive `rm -rf ~/.ironclaw/installed_skills/...` cleanup step lacks a verification guard; it is not capped at 3 because validation is pervasive across the core workflow rather than missing.	4 / 5
Progressive Disclosure	Content is well-organized into clearly headed sections (Prerequisites, Starting the Server, numbered Test Checklist, Cleanup, Known Issues) in a single file with no bundle files present and no nested references. It is not a 5 because the body exceeds the ~50-line simple-skill threshold, so the well-organized-sections exception does not strictly apply, though no external references are actually needed.	4 / 5
	Total	16 / 20 Passed

Description

56%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 is clear and reasonably distinct, but it is thin on specificity — it states only a single generic action ("Test") and omits any explicit "Use when..." trigger guidance, which caps completeness at 3. Trigger-term coverage is good but lacks the synonym/extension breadth of a top score.

Suggestions

Enumerate concrete capabilities instead of the bare verb "Test" — e.g., "Verify gateway connection, exercise the Chat/Skills/Memory/Jobs/Routines/Extensions tabs, and validate skill install/remove flows via the Claude for Chrome browser extension."

Add an explicit trigger clause, e.g., "Use when manually testing the IronClaw web gateway UI or when the user asks to browser-test IronClaw's chat or skills tabs."

Broaden trigger terms with synonyms and an artifact reference (e.g., "IronClaw gateway", "web UI smoke test", "GATEWAY_ENABLED") to improve distinctiveness and trigger-term quality.

Dimension	Reasoning	Score
Specificity	The description names the domain ("IronClaw web UI") but relies on the single generic action verb "Test" with no enumerated sub-actions, matching the anchor for naming the domain with minimal/generic actions. It is not a 3 because it lists no concrete capabilities, and not a 1 because the domain and a concrete-ish action are present.	2 / 5
Completeness	It gives a clear "what" ("Test the IronClaw web UI using the Claude for Chrome browser extension") but no "Use when..." trigger clause, so completeness is capped at 3 per the missing-trigger-guidance rule. It is not a 4 because the "when" is entirely absent rather than merely implicit.	3 / 5
Trigger Term Quality	Natural terms a user would say appear — "test", "web UI", "browser", "Chrome", "extension" — giving good keyword coverage matching the anchor-4 example. It is not a 5 because it lacks the synonym/extension spread (e.g., no ".ironclaw" or alternate phrasings) that characterizes comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	The pairing of "IronClaw web UI" with "Claude for Chrome browser extension" carves a mostly distinct niche with only minor overlap risk against generic browser/UI-testing skills, matching anchor 4. It is not a 5 because trigger phrasings like "browser test" / "test the ui" could plausibly match other UI-testing skills.	4 / 5
	Total	13 / 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
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: 2831516

Reviewed: 8 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.