CtrlK
BlogDocsLog inGet started
Tessl Logo

browserstack

Run tests on BrowserStack. Use when user mentions "browserstack", "cross-browser", "cloud testing", "browser matrix", "test on safari", "test on firefox", or "browser compatibility".

66

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./engineering-team/playwright-pro/skills/browserstack/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.

A solid, actionable integration guide with clear sequenced workflows and a useful prerequisite/validation gate. The main efficiency cost is a heavily duplicated config block, and the local-testing workflow lacks concrete code.

Suggestions

Replace the three near-duplicate BrowserStack project blocks with one parameterized template plus a short table of browser/OS/version triples to cut roughly 40 lines.

Add concrete config/code for the Local Testing capability (the browserstack-local tunnel snippet) instead of the high-level 'Add local tunnel to config' step.

Add a short feedback loop for run failures (e.g., on a per-browser failure, fetch the session video/logs via the MCP tool before reporting) to strengthen workflow_clarity.

DimensionReasoningScore

Conciseness

Mostly efficient with no over-explanation of Playwright or BrowserStack concepts, but the ~60-line config block repeats three near-identical project definitions (chrome/firefox/webkit) that could be a parameterized template; this noticeably padded section keeps it below a 4.

3 / 5

Actionability

Provides complete, copy-paste-ready executable config, npm scripts, bash commands, named MCP tools, and slash commands; the Local Testing section stays high-level without tunnel config code, a minor gap that prevents a 5.

4 / 5

Workflow Clarity

Each capability has numbered steps with checkpoints (env-var presence check that explicitly stops, 'Verify credentials are set'); no failure feedback loop is given, but test execution is not destructive, so the batch/destructive cap does not apply.

4 / 5

Progressive Disclosure

Self-contained with no bundle files, organized into clear sections (Prerequisites, five Capabilities, MCP Tools table, Output); the large inline config block is reasonable here but is the kind of content that could optionally live in a reference file, a minor organization gap.

4 / 5

Total

15

/

20

Passed

Description

90%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.

A well-crafted description that crisply states the skill's purpose and provides rich, natural trigger terms with low conflict risk. Its only limitation is that the 'what' names a single action rather than enumerating the full capability set.

DimensionReasoningScore

Specificity

Names the domain ('BrowserStack') and one concrete action ('Run tests'), matching the anchor for 1-2 concrete actions without comprehensive coverage; it does not list several specific actions that would warrant a 4.

3 / 5

Completeness

Explicitly answers both 'what' ('Run tests on BrowserStack') and 'when' with concrete trigger phrases via the 'Use when user mentions ...' clause, matching the top anchor.

5 / 5

Trigger Term Quality

Comprehensive natural trigger terms including synonyms ('cross-browser', 'browser compatibility', 'cloud testing') and specific user phrasings ('test on safari', 'test on firefox', 'browser matrix'); no relevant terms are missing.

5 / 5

Distinctiveness Conflict Risk

Targets a clear niche (BrowserStack cloud grid) with distinct, brand-specific triggers; minimal overlap risk with other skills.

5 / 5

Total

18

/

20

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
alirezarezvani/claude-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.