CtrlK
BlogDocsLog inGet started
Tessl Logo

agentcore

Run agent-browser on AWS Bedrock AgentCore cloud browsers. Use when the user wants to use AgentCore, run browser automation on AWS, use a cloud browser with AWS credentials, or needs a managed browser session backed by AWS infrastructure. Triggers include "use agentcore", "run on AWS", "cloud browser with AWS", "bedrock browser", "agentcore session", or any task requiring AWS-hosted browser automation.

66

Quality

80%

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

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 highly actionable with executable commands covering the common cases and a clean section structure. The main weakness is mild redundancy between the Setup and Credential Patterns sections and the absence of explicit validation feedback loops.

Suggestions

Consolidate the credential-resolution content so Setup and Credential Patterns do not both enumerate env-var/SSO/profile options, reducing token redundancy.

Add a brief validate/retry cue for the persistent-profile login flow (e.g., snapshot after login to confirm authentication before relying on the profile).

DimensionReasoningScore

Conciseness

The body is mostly lean and assumes Claude's competence (no padding about what AWS or a browser is), but the Setup and Credential Patterns sections overlap on env-var/SSO/profile handling and could be tightened.

4 / 5

Actionability

Provides copy-paste-ready commands across the common cases (open, snapshot, click, screenshot, close, persistent profiles, region selection, credential patterns, provider env var), all fully executable.

5 / 5

Workflow Clarity

Core and persistent-profile workflows are clearly sequenced with concrete commands, and the Common Issues section gives error-recovery guidance; it stops short of explicit validate-then-retry checkpoints, though browser automation is not a destructive/batch operation requiring the cap.

4 / 5

Progressive Disclosure

Well-organized into clearly headed sections with no nested references and easy navigation; at ~110 lines (above the under-50 simple-skill exception) some content like credential patterns could live in a reference file, but the single-file structure is appropriate for this scope.

4 / 5

Total

17

/

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 clearly answers both what the skill does and when to use it, with strong concrete trigger phrases and third-person voice. Specificity is the weakest dimension because only one high-level action is named rather than the full browser-automation capability set.

Suggestions

Expand the capability statement to name the concrete browser-automation actions supported (e.g., open pages, take snapshots, click, fill forms, screenshot) so specificity reaches comprehensive coverage.

Soften or qualify the generic "run on AWS" trigger to reduce overlap with non-browser AWS skills.

DimensionReasoningScore

Specificity

Names the tool and platform concretely ("Run agent-browser on AWS Bedrock AgentCore cloud browsers") but lists only that single action; it does not enumerate the underlying browser-automation capabilities, so coverage is not comprehensive.

3 / 5

Completeness

Explicitly states what the skill does and gives a clear "Use when..." clause with concrete trigger phrases, matching the anchor for answering both what and when.

5 / 5

Trigger Term Quality

Good coverage of natural trigger phrases and synonyms ("use agentcore", "run on AWS", "cloud browser with AWS", "bedrock browser", "agentcore session"), though "run on AWS" is somewhat generic and a few natural phrasings are absent.

4 / 5

Distinctiveness Conflict Risk

The AgentCore / bedrock-browser niche is distinct, but the generic "run on AWS" trigger creates minor overlap risk with other AWS-oriented skills.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
vercel-labs/agent-browser
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.