CtrlK
BlogDocsLog inGet started
Tessl Logo

browser-use

Existing Chrome automation: Chrome plugin first, mcporter fallback.

59

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/browser-use/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 strong, operational skill: concrete executable commands, a clearly sequenced flow, and explicit validation/recovery loops for fragile attach steps. Its main weaknesses are repeated restatements of the same anti-isolation rule and a dangling reference to a non-existent mcporter-config.md.

Suggestions

Consolidate the 'never use isolated browser tooling' rule into a single stated-once section and cross-reference it, instead of restating it in Route, Live UI Proof, and elsewhere.

Either add the referenced mcporter-config.md to the bundle and link it properly, or remove the 'Config repair details live in mcporter-config.md' line so there are no dangling references.

Consider moving the lengthy Peekaboo attach-prompt recovery block into a references file (e.g. attach-recovery.md) to keep the core route/flow overview lean while keeping it one level deep.

DimensionReasoningScore

Conciseness

The body is largely lean and command-driven, but the 'avoid isolated browser / prefer existing profile' rule is restated three or more times across Route, Live UI Proof, and adjacent prose, so it could be tightened.

2 / 3

Actionability

It provides fully executable, copy-paste-ready mcporter and Peekaboo bash commands with real flags and realistic placeholders (pageId, uid, allow coordinates) throughout every section.

3 / 3

Workflow Clarity

The Typical Flow is a clear sequenced process, and Check MCP includes explicit validation ('list_pages must show the user's real open tabs') plus feedback loops for attach-prompt and DevToolsActivePort recovery.

3 / 3

Progressive Disclosure

Sections are well-organized with clear headers, but the only external reference ('mcporter-config.md') is a dangling code-span to a file absent from the bundle, and all content lives inline in SKILL.md.

2 / 3

Total

10

/

12

Passed

Description

57%

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 signals a specific Chrome-automation niche with a routing strategy, but lacks explicit 'when to use' triggers and leans on internal jargon ('mcporter') rather than natural user terms. It is specific enough to avoid conflicts but incomplete as trigger guidance.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers such as 'Use when the user asks to control or automate their existing Chrome browser, navigate logged-in pages, or debug a live UI.'

Replace or gloss internal jargon ('mcporter fallback') with user-facing terms like 'browser control' or 'Chrome automation' so the description reads as something a user would actually say.

Mention concrete actions (e.g. navigate, click, fill forms, take page snapshots) so the capability list is comprehensive rather than just a routing note.

DimensionReasoningScore

Specificity

Names the domain ('Existing Chrome automation') and a concrete two-route strategy ('Chrome plugin first, mcporter fallback'), but lists no user-facing actions like navigate/click/fill, so it is not comprehensive.

2 / 3

Completeness

It states what the skill does (Chrome automation via two routes) but has no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2.

2 / 3

Trigger Term Quality

'Chrome automation' is a term a user might say, but 'mcporter' and 'Chrome plugin' are internal jargon and common variations like 'browser', 'browser control', or 'navigate' are missing.

2 / 3

Distinctiveness Conflict Risk

The specific toolchain niche (existing Chrome session, Codex plugin, mcporter fallback) is clearly distinguishable and unlikely to trigger for unrelated skills.

3 / 3

Total

9

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
steipete/agent-scripts
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.