agentlas-browser

Use when the user types /agentlas-browser <url-or-query>, /agentlas browser, or /hep-browser for browser-required tasks, rendering pages, form flows, or visual evidence.

Quality

56%

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 ./.agents/skills/agentlas-browser/SKILL.md

Quality

Content

33%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 skill body is lean and unpadded but essentially empty of guidance: it states only the skill's purpose and its command aliases. It lacks any executable instructions, workflow steps, or reference structure, so a reader cannot actually perform browser automation from it.

Suggestions

Add a concrete quick-start example showing how to launch a headless/CDP session and capture a page (e.g., a runnable snippet or exact command) to lift actionability.

Provide at least a minimal workflow with a validation checkpoint (e.g., navigate -> wait for load -> verify selector present -> capture evidence) since browser/form flows are stateful and failure-prone.

Either inline a short reference of supported operations or create a references/ file (e.g., BROWSER.md) and link to it so progressive disclosure has real structure.

Dimension	Reasoning	Score
Conciseness	The body is extremely short (two lines plus a heading) with no padding and no over-explanation of concepts Claude already knows, sitting above the midpoint; it is efficient but the redundancy of restating the aliases ('Alias for /hep-browser and /agentlas browser') already named in the frontmatter is a minor inefficiency.	4 / 5
Actionability	It only describes intent ('Browser interaction and headless/CDP automation runner for Agentlas tasks') with no concrete code, commands, configuration, or example invocation, so it provides high-level hints but none of the specific steps needed to execute a browser task.	2 / 5
Workflow Clarity	No multi-step sequence is present and, because browser automation routinely performs destructive/batch-style actions (form submission, navigation with state), the missing validation or checkpoint steps leave the workflow incoherent rather than merely simple.	1 / 5
Progressive Disclosure	There is no bundle (references/, scripts/, assets/ are empty) and the body offers no navigation to detailed material; the alias restatement is the only structural content, so content that would belong in separate files is absent rather than well split.	2 / 5
	Total	9 / 20 Passed

Description

78%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 concise, third-person, and provides explicit 'Use when...' trigger guidance with concrete slash-command aliases, hitting the key completeness and trigger-quality anchors well. Its main weakness is specificity: it lists outcome categories rather than enumerated concrete actions.

Suggestions

Replace broad outcome phrases with one or two more concrete capabilities (e.g., 'navigates multi-step form flows via CDP', 'captures full-page screenshots as visual evidence') to raise specificity.

Add common synonym trigger terms such as 'scraping', 'screenshots', or 'headless Chrome' so users searching those words still match.

Dimension	Reasoning	Score
Specificity	Names the browser-automation domain and a few concrete action categories ('rendering pages, form flows, or visual evidence'), but these are broad outcome phrases rather than enumerated specific actions, so it sits at the 3 anchor with minor coverage gaps.	3 / 5
Completeness	Opens with an explicit 'Use when...' clause enumerating the trigger commands and scenarios, and the preceding phrase states what the skill does ('browser-required tasks, rendering pages, form flows, or visual evidence'), satisfying both 'what' and 'when' with concrete trigger phrases.	5 / 5
Trigger Term Quality	Lists three explicit slash-command trigger forms ('/agentlas-browser <url-or-query>', '/agentlas browser', '/hep-browser') that a user would actually type, plus natural terms like 'browser-required tasks', 'rendering pages', and 'visual evidence'; coverage is good though it lacks synonyms like 'scraping' or 'screenshots'.	4 / 5
Distinctiveness Conflict Risk	The distinct command aliases (/agentlas-browser, /hep-browser, /agentlas browser) carve a clear niche and reduce mis-firing, but the general 'browser-required tasks' framing overlaps somewhat with generic web-fetch or scraping skills.	4 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: agentlas-ai/Agentlas-OS
Path: .agents/skills/agentlas-browser/SKILL.md
Commit: 7032c0b

Reviewed: 3 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.