CtrlK
BlogDocsLog inGet started
Tessl Logo

browser-use

Use PilotDeck's browser-use plugin for browser automation, screenshots, form filling, and web UI checks.

60

Quality

70%

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/browser-use/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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, sensible pre-install validation, and concrete error-recovery guidance, all organized into clear sections. Its main weaknesses are redundancy in the install-avoidance messaging and near-duplicate usage bullets, plus content that could be split into reference files for a leaner overview.

Suggestions

Consolidate the repeated "check the cache before installing / do not reinstall" guidance into a single statement and merge the near-duplicate Usage Notes bullets ("Keep browser-use calls targeted" and "Keep browser tasks small and observable").

Move the Runtime Configuration env-var list and the multi-path install instructions into a reference file (e.g. references/install.md), keeping SKILL.md as a lean overview with one-level-deep links.

Present the install decision flow as a short numbered sequence (check cache -> verify preconditions -> install -> verify launch) so the workflow reads as one coherent ordered process instead of prose scattered across sections.

DimensionReasoningScore

Conciseness

The content is operational rather than padded with concepts Claude already knows, but "do not reinstall / try the existing setup first" is repeated at least four times across Availability, the installer note, and Usage Notes, and Usage Notes contains near-duplicate bullets ("Keep browser-use calls targeted" vs "Keep browser tasks small and observable"). This matches anchor 3: mostly efficient but could be tightened.

3 / 5

Actionability

Fully executable guidance throughout: a copy-paste cache-check script, concrete install commands for three distinct setup paths, env vars with defaults and example values (PILOTDECK_BROWSER_PROXY_SERVER=http://127.0.0.1:7890), and a concrete local URL (http://localhost:3001). Matches anchor 5: specific examples cover the common cases.

5 / 5

Workflow Clarity

There is an explicit validation checkpoint (cache check before any install), clearly stated install preconditions, and error-recovery loops (proxy retry on blocked downloads, alternative actions on screenshot/navigation timeouts). Not 5 because the sequence is distributed across prose sections rather than presented as one coherent ordered workflow; not 3 because validation and checkpoints are explicit, not implicit. No destructive or batch operations, so the workflow cap does not apply.

4 / 5

Progressive Disclosure

No bundle files exist, so all content lives inline in a single well-sectioned file with clear headers and no buried or nested references. Matches anchor 4: good structure with most content appropriately placed. Not 5 because at ~90 lines the multi-path install detail and the Runtime Configuration env-var reference could reasonably be split into reference files, keeping SKILL.md as a leaner overview.

4 / 5

Total

16

/

20

Passed

Description

66%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, concrete, and names a specific plugin with several real capabilities, but it omits any explicit "when to use this" trigger guidance. Adding a trigger clause with natural user phrases would raise both completeness and trigger-term coverage.

Suggestions

Add an explicit trigger clause, e.g. "Use when a task needs an interactive browser — web UI smoke tests, screenshots, clicking, form filling — rather than static HTTP or file retrieval."

Include common user synonyms such as "web scraping", "navigate/click", or "browser testing" in the trigger phrasing to broaden natural keyword coverage.

Consider mentioning DOM inspection or navigation in the capability list since the body covers them but the description does not.

DimensionReasoningScore

Specificity

"browser automation, screenshots, form filling, and web UI checks" lists several concrete actions tied to a named plugin, matching anchor 4. Not 5 because coverage has gaps (navigation, DOM inspection, scraping appear only in the body, not the description); not 3 because more than 1-2 concrete actions are named.

4 / 5

Completeness

The description clearly answers "what" (PilotDeck's browser-use plugin for the listed actions) but contains no "Use when..." clause or equivalent trigger guidance, capping completeness at 3 per the judging guidelines. Not 4 because "when" is entirely absent rather than just imprecise.

3 / 5

Trigger Term Quality

"browser automation", "screenshots", "form filling", and "web UI checks" are natural phrases users would say, giving good keyword coverage. Not 5 because common variations like web scraping, navigate/click, or browser testing are missing; not 3 because the terms present are natural rather than jargon or generic.

4 / 5

Distinctiveness Conflict Risk

Scoping to "PilotDeck's browser-use plugin" gives a mostly distinct niche with minor overlap risk against generic browser-automation or scraping skills. Not 5 because the action terms themselves (browser automation, screenshots, form filling) are generic enough to overlap with other browser skills.

4 / 5

Total

15

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
OpenBMB/PilotDeck
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.