CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

browser-use

Use this skill when the user asks the agent to open, browse, inspect, extract content from, click through, fill forms on, screenshot, or verify a web page with a browser. Also use it for MoviePilot scenarios that need browser interaction, such as checking a site page, confirming a JavaScript-rendered result, testing login state, capturing visible errors, or updating and validating tracker site cookies.

75

Quality

94%

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

88%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 highly actionable, well-sequenced skill body with concrete commands, explicit verification steps, and strong safety rules. The main weaknesses are mild redundancy in the captcha workflow and a single-file structure that inlines specialized MoviePilot workflows which would benefit from reference-file splitting.

Suggestions

Consolidate the repeated image-unavailability guidance in the captcha workflow (currently stated in the Tools section, step 2, step 4, and the closing paragraph) into one place to reduce token cost.

Move the detailed 'Login Page With A Graphic Captcha' procedure (~60 lines) into a references/ file (e.g. CAPTCHA.md) and keep a short trigger-and-pointer in SKILL.md, improving progressive disclosure.

Trim restatements of the session-cookie caveats that already appear in the Tools bullet for browse_webpage/view_image, keeping the workflow steps focused on actions and verification.

DimensionReasoningScore

Conciseness

Mostly efficient operational guidance Claude would not already know (ref-based actions, selector priority order, session-bound captcha handling), but the captcha workflow repeats the image-unavailability caution in three places and reiterates session/cookie caveats already stated in the Tools section. It fits 'efficient; minor instances of over-explanation that could be trimmed' rather than the lean top anchor, and is well above the 'some unnecessary explanation' midpoint anchor.

4 / 5

Actionability

Copy-paste-ready commands throughout: browse_webpage action blocks, an executable evaluate JavaScript snippet, full moviepilot_api call templates with path/body params, a concrete selector fallback order, and worked user examples (including Chinese prompts) mapped to step sequences. This matches the top anchor of fully executable guidance covering common cases.

5 / 5

Workflow Clarity

The six-step core workflow is clearly sequenced with explicit verification checkpoints ('Observe Before Acting', 'verify after each action', a dedicated 'Verify And Report' step) and feedback loops for error recovery (re-run site.test after cookie update, captcha attempt cap of three, re-inspect page after rejection). This matches the top anchor including checklists for the complex captcha process.

5 / 5

Progressive Disclosure

The single file is well-sectioned with clear headers and no buried or nested references (no bundle files exist), but at ~295 lines the specialized MoviePilot site workflows — especially the ~60-line graphic-captcha procedure — could be split into one-level-deep reference files to keep SKILL.md an overview. This sits between 'good structure, minor organization gaps' (4) and 'content that should be separate is inline' (3), closer to 4 given the genuinely navigable organization.

4 / 5

Total

18

/

20

Passed

Description

100%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 strong description: concrete verb-level actions, explicit and natural trigger guidance, and a distinctive MoviePilot/browser niche. Both the 'what' and 'when' are clearly and explicitly stated with no fluff or over-claims.

DimensionReasoningScore

Specificity

The description lists multiple specific concrete actions ("open, browse, inspect, extract content from, click through, fill forms on, screenshot, or verify a web page") plus scenario-level specifics ("testing login state, capturing visible errors, or updating and validating tracker site cookies"), giving comprehensive coverage with no generic filler.

5 / 5

Completeness

It explicitly answers both what (browser actions on web pages) and when ("Use this skill when the user asks the agent to..." plus "Also use it for MoviePilot scenarios that need browser interaction, such as...") with concrete trigger phrases, exactly matching the top anchor.

5 / 5

Trigger Term Quality

Natural user phrasings are comprehensively covered — "open", "browse", "click through", "fill forms", "screenshot", "verify a web page", "checking a site page" — sweeping the synonyms users would actually say for browser interaction. No significant natural term is missing, so this exceeds the 'good coverage, a few missing' anchor at 4.

5 / 5

Distinctiveness Conflict Risk

The 'with a browser' qualifier and the MoviePilot tracker-site scenarios (cookie updates, login-state diagnosis) carve a clear niche with minimal overlap risk against generic web-search or API skills.

5 / 5

Total

20

/

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

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

jxxghp/MoviePilot

Path

skills/browser-use/SKILL.md

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.