CtrlK
BlogDocsLog inGet started
Tessl Logo

playwright-cli

Drive a browser from the command line with the `playwright-cli` binary — open pages, snapshot the accessibility tree, click and type by ref, read network and console, manage sessions, cookies, storage state, tracing and video — and run or debug Node/TypeScript Playwright Test projects (`npx playwright test`, attach-to-paused-page, spec-driven plan/generate/heal). Use for interactive browser work at a prompt: exploring a page, validating a locator before committing it, inspecting element attributes, reproducing a UI bug, or debugging a `.spec.ts` run. NOT for authoring this repository's committed browser tests — this repo contains no `.spec.ts` Playwright specs at all; its browser journeys are pytest + pytest-playwright under tests/stand/ui/, run with uv, and belong to stand-ui-test. For getting an authenticated browser onto an Insight stand and capturing evidence, drive-ui owns the acquisition and this skill owns the commands.

72

Quality

88%

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

77%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 highly actionable, well-organized command reference with concrete examples and real one-level-deep reference files. Its main weakness is that it functions more as a comprehensive inlined catalog than a lean overview pointing to detail, with one orphaned bundle file.

Suggestions

Link references/annotated-gif.md from the body (e.g. under Specific tasks or the Interactive session example) so every bundle file is discoverable.

Move the lower-frequency command groups (Mouse, Keyboard, Save as, Tabs) into a reference file and summarize them inline, shrinking SKILL.md toward an overview that delegates detail.

Add an explicit validate-then-proceed checkpoint to the locator/targeting workflow (e.g. snapshot -> confirm ref resolves -> act -> re-snapshot) to turn implicit verification into a stated feedback loop.

DimensionReasoningScore

Conciseness

The body is lean command-reference material with terse inline comments and no over-explanation of concepts Claude already knows, but the sheer volume of inlined command catalog (~400 lines) could be partially offloaded to reference files. Not a 5 because some bulk lives inline that an overview might delegate; not a 3 because what is written is efficient and unpadded.

4 / 5

Actionability

Fully executable, copy-paste-ready commands throughout, with worked examples (form submission, multi-tab, debugging) covering common cases and concrete flag syntax for every action.

5 / 5

Workflow Clarity

Examples are clearly sequenced and use `snapshot` after interactions as an implicit verification checkpoint, and the video note ('read references/video-recording.md before relying on them') warns of a silent-failure trap. Not a 5 because there are no explicit validate->fix->retry feedback loops for the riskier operations (e.g. locator validation before committing).

4 / 5

Progressive Disclosure

Good structure with a Quick start, organized command sections, and a 'Specific tasks' block linking 9 one-level-deep reference files — all of which exist on disk. Not a 5 because the body itself is a large inlined command catalog rather than a lean overview, and references/annotated-gif.md is present but never linked from the body.

4 / 5

Total

17

/

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.

The description is exemplary: third-person voice, comprehensive concrete actions, natural trigger terms, explicit what/when guidance, and clear boundary disambiguation against sibling skills. It is concise despite covering a broad surface area.

DimensionReasoningScore

Specificity

Lists many concrete actions — 'open pages, snapshot the accessibility tree, click and type by ref, read network and console, manage sessions, cookies, storage state, tracing and video' plus test-project actions — giving comprehensive coverage of capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (drive a browser with playwright-cli, enumerating actions) and 'when' ('Use for interactive browser work at a prompt: exploring a page, validating a locator...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural phrases a user would actually say — 'exploring a page', 'validating a locator', 'reproducing a UI bug', 'debugging a .spec.ts run' — alongside synonyms and file extensions, with strong keyword coverage.

5 / 5

Distinctiveness Conflict Risk

Provides explicit boundary guidance — 'NOT for authoring this repository's committed browser tests... belong to stand-ui-test' and 'drive-ui owns the acquisition and this skill owns the commands' — giving a clear niche with minimal conflict risk.

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
constructorfabric/insight
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.