CtrlK
BlogDocsLog inGet started
Tessl Logo

browserless

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

52

Quality

58%

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/browserless/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 well-structured, highly actionable integration guide with concrete CLI commands, a useful flags table, and a clear connection-state workflow including polling feedback. Its main weaknesses are mild redundancy between the action-listing sections and some over-explanation in the intro, with minor gaps in worked Browserless-specific examples.

Suggestions

Merge or differentiate the 'Searching for actions' and 'Popular actions' sections to remove the duplicated `membrane action list` command and avoid token waste.

Trim the opening Browserless marketing paragraph to one line or fold its concrete use cases (scraping, PDF, testing) into the description instead.

Add one fully worked Browserless example (e.g. a real `membrane action run` or `membrane request` call with concrete path/params) so the most common case is copy-paste ready without placeholders.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete commands and a tight flags table, but the 'Popular actions' section repeats the 'Searching for actions' command and the intro paragraph explains Browserless at a level Claude largely already knows, matching 'mostly efficient but includes some unnecessary explanation' rather than the 4-anchor's minor trims.

3 / 5

Actionability

It provides copy-paste-ready commands across install, auth, connection, action search/run, and proxy with a clear flags table, but uses generic placeholders (CONNECTION_ID, /path/to/endpoint) and shows two command forms (membrane vs npx) without a fully worked Browserless-specific example, fitting 'mostly executable with minor gaps' just below the 5-anchor.

4 / 5

Workflow Clarity

The connection flow is clearly sequenced (ensure → poll → branch on state → search → run) with a polling feedback loop and explicit state handling (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR), but the step numbering (1b, references to 'Step 2') is loose and a couple of checkpoints are implicit, matching the 4-anchor rather than the 5-anchor's fully explicit validation steps.

4 / 5

Progressive Disclosure

No bundle files exist and the content is a single cohesive CLI guide with well-organized sections (Install, Auth, Connecting, Searching, Running, Proxy, Best practices); the proxy options table and clientAction state detail are reasonably placed inline with only minor organization gaps, fitting the 4-anchor's good structure just below the 5-anchor's clean one-level-deep reference split.

4 / 5

Total

15

/

20

Passed

Description

48%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 names the Browserless product and includes an explicit 'Use when' trigger, but the capability language is generic ('manage data, records, automate workflows') rather than concrete, and it omits the natural trigger terms users would say for browser automation. It is adequate but under-specific.

Suggestions

Replace generic verbs with concrete capabilities, e.g. 'Scrape web pages, generate PDFs, take screenshots, and run headless browser scripts via Browserless.'

Add natural trigger terms users actually say — 'web scraping', 'headless browser', 'PDF generation', 'screenshots', 'browser automation' — to the 'Use when' clause.

Tighten the trigger to a specific condition, e.g. 'Use when the user wants to automate browser tasks or scrape websites via Browserless.'

DimensionReasoningScore

Specificity

Names the domain (Browserless) but the actions are generic — 'Manage data, records, and automate workflows' offers no concrete operations like scraping, PDF generation, or screenshots, matching the 'names domain but actions minimal/generic' anchor rather than the 3-anchor which requires 1-2 concrete actions.

2 / 5

Completeness

A 'Use when the user wants to interact with Browserless data' clause is present, but the 'what' is vague (generic manage/automate) and the 'when' is generic, so it does not reach the 4-anchor's requirement of a reasonably explicit what-and-when pair.

3 / 5

Trigger Term Quality

It surfaces 'Browserless', 'records', 'workflows', and 'automate workflows' as relevant keywords, but misses the natural phrases users actually say (web scraping, headless browser, PDF generation, screenshots), so it sits at 'some relevant keywords but missing common variations/synonyms' rather than the 4-anchor's good coverage.

3 / 5

Distinctiveness Conflict Risk

Naming the specific commercial product 'Browserless' gives it a clear niche with low conflict risk, but the generic 'manage data, records, automate workflows' tail leaves minor overlap with general automation skills, keeping it just below the 5-anchor's fully distinct triggers.

4 / 5

Total

12

/

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.