CtrlK
BlogDocsLog inGet started
Tessl Logo

browse-ai

Browse AI integration. Manage data, records, and automate workflows. Use when the user wants to interact with Browse AI data.

58

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/browse-ai/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 and a clear connection state-machine workflow, organized into clean sections. It is slightly held back by minor verbosity in the intro and best-practices prose.

DimensionReasoningScore

Conciseness

The body is mostly lean executable commands, but the intro paragraph and editorializing ("so you can focus on the integration logic", "burn less tokens") add unnecessary explanation that could be trimmed.

3 / 5

Actionability

Commands are copy-paste ready and cover the common cases end-to-end (install, login, connection ensure, action list/run, proxy request) with flags and JSON output documented.

5 / 5

Workflow Clarity

The connection readiness flow is clearly sequenced with explicit state checkpoints (READY, BUILDING, CLIENT_ACTION_REQUIRED, CONFIGURATION_ERROR) and a poll/handle/re-poll loop, though verifying action results after running is only implicit.

4 / 5

Progressive Disclosure

Content is a single self-contained file with well-organized sections and no external bundle references, which is appropriate given no reference files are provided or needed.

5 / 5

Total

17

/

20

Passed

Description

57%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 correctly uses third-person voice and provides both a what and a when clause, but its actions are generic and its trigger terms omit the natural use-case phrasing users would actually say. It is functional but lacks specificity.

Suggestions

Replace generic verbs with concrete Browse AI capabilities, e.g. "Extract and monitor structured data from websites on a recurring schedule."

Add natural trigger phrases users would say, such as "Use when the user wants to scrape or monitor websites, track prices, or collect data on a schedule."

Reference file extensions or product terms (e.g. robots, monitors, .csv exports) to strengthen trigger-term coverage.

DimensionReasoningScore

Specificity

Phrases like "Manage data, records, and automate workflows" name the Browse AI domain but the actions themselves are minimal and generic rather than concrete (no mention of scraping, monitoring, or extraction).

2 / 5

Completeness

It states both what ("Manage data, records, and automate workflows") and when ("Use when the user wants to interact with Browse AI data"), but the trigger guidance could be more specific with concrete scenarios.

4 / 5

Trigger Term Quality

The brand name "Browse AI" and the phrase "interact with Browse AI data" are present, but common natural variations (web scraping, monitor websites, extract data, recurring schedule) are missing.

3 / 5

Distinctiveness Conflict Risk

Naming the specific product "Browse AI" gives it a clear niche with minimal conflict risk, though the generic action vocabulary (manage data, records) leaves minor overlap with other data skills.

4 / 5

Total

13

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
membranedev/application-skills
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.