CtrlK
BlogDocsLog inGet started
Tessl Logo

playwright-cli

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

95

22.50x
Quality

Does it follow best practices?

Impact

90%

22.50x

Average score across 3 eval scenarios

SecuritybySnyk

Risky

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, token-efficient CLI reference with a clear core workflow and worked examples. Its main weakness is progressive disclosure: a large command catalog lives inline in SKILL.md with no split into a one-level-deep reference file.

Suggestions

Move the full command catalog (Core, Navigation, Keyboard, Mouse, Save as, Tabs, DevTools, Sessions) into a separate REFERENCE.md and keep SKILL.md as a concise overview plus key examples, with a clearly signaled link such as 'See [REFERENCE.md](REFERENCE.md) for the full command list'.

Add a one-line 'Reference' pointer near the top of the body so the command catalog is discoverable through one-level-deep navigation rather than only inline.

Consolidate the redundant Quick start block, which repeats `open`/`click`/`type`/`press` already shown under Commands, or replace it with a pointer to the worked Examples to reduce duplicate inline content.

DimensionReasoningScore

Conciseness

The body is a lean command reference with no explanation of browser/Playwright concepts Claude already knows; every block is an executable snippet rather than padded prose, matching the score-3 'every token earns its place' anchor.

3 / 3

Actionability

It is almost entirely concrete, copy-paste-ready commands (e.g. 'playwright-cli fill e5 "user@example.com"', 'playwright-cli tab-select 0') with specific worked examples, satisfying the score-3 fully-executable anchor.

3 / 3

Workflow Clarity

The 'Core workflow' gives a clear 3-step sequence (Navigate → Interact using refs → Re-snapshot after significant changes) with the re-snapshot acting as an explicit verification checkpoint, and the form example closes by re-snapshotting to confirm result; browser interaction is not a destructive/batch operation that would cap this at 2.

3 / 3

Progressive Disclosure

Sections are well organized, but the skill is ~153 lines with a ~70-line inline command catalog (Core, Navigation, Keyboard, Mouse, Tabs, DevTools, Sessions) and no external references; this exceeds the under-50-line simple-skill exception and matches the score-2 anchor where content that could be a separate reference file is inline.

2 / 3

Total

11

/

12

Passed

Description

100%

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, third-person description that states concrete capabilities and pairs them with an explicit 'Use when' trigger clause covering natural user phrasings. It is specific, complete, and clearly distinct from other skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'web testing, form filling, screenshots, and data extraction' — matching the score-3 anchor that enumerates specific capabilities rather than vague language.

3 / 3

Completeness

Explicitly answers both 'what' ('Automates browser interactions...') and 'when' via a clear 'Use when the user needs to...' clause, satisfying the score-3 anchor and avoiding the completeness cap of 2 for missing triggers.

3 / 3

Trigger Term Quality

Natural user-facing triggers are well covered: 'navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages' are phrases a user would plausibly say.

3 / 3

Distinctiveness Conflict Risk

Browser automation is a distinct niche with triggers scoped to web pages and browser interaction, making it unlikely to fire for document, spreadsheet, or PDF skills.

3 / 3

Total

12

/

12

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
Dicklesworthstone/pi_agent_rust
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.