CtrlK
BlogDocsLog inGet started
Tessl Logo

browser-harness

Direct browser control via CDP. Use when the user wants to automate, scrape, test, or interact with web pages. Connects to the user's already-running Chrome.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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 clear, validated workflows and good reference signaling, but is held back by near-verbatim duplicated sections and several in-body references to bundle paths that are not present.

Suggestions

Remove the duplicated 'Hermes Agent integration' and 'Authenticated content extraction' sections (the second copy of each is redundant), which will tighten conciseness toward a 3.

Either add the referenced interaction-skills/*.md files and agent-workspace/domain-skills/ to the bundle, or note in the body that these live outside the skill bundle so navigation is unambiguous.

Consider moving the detailed 'Authenticated content extraction' pattern into a reference file and keeping only a one-line pointer in SKILL.md to deepen progressive disclosure.

DimensionReasoningScore

Conciseness

The prose is generally lean and assumes Claude's competence, but the 'Hermes Agent integration' and 'Authenticated content extraction' sections are each duplicated nearly verbatim (including a full repeated code block), wasting roughly 60 tokens of duplicated content.

2 / 3

Actionability

Provides fully executable, copy-paste-ready code blocks (browser-harness -c '...') and names concrete helpers (capture_screenshot(), click_at_xy(), cdp('Domain.method')) rather than abstract descriptions.

3 / 3

Workflow Clarity

Multi-step processes are clearly sequenced with explicit validation checkpoints — the screenshot→click→re-screenshot verify loop, the new_tab→wait_for_load→sleep→extract extraction pattern, and the 'auth wall → stop and ask' feedback rule.

3 / 3

Progressive Disclosure

Structure is good with one-level-deep, clearly signaled references (install.md for setup, which exists in references/), but several signaled paths — the interaction-skills/*.md files and agent-workspace/domain-skills/ — are referenced in the body yet absent from the provided bundle, so navigation does not fully resolve.

2 / 3

Total

10

/

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.

The description is specific, complete, and uses third-person voice with an explicit 'Use when' trigger clause. It clearly communicates both capability and invocation conditions with natural trigger terms.

DimensionReasoningScore

Specificity

Names the concrete mechanism ('Direct browser control via CDP'), lists multiple specific actions ('automate, scrape, test, or interact with web pages'), and states a concrete capability ('Connects to the user's already-running Chrome').

3 / 3

Completeness

It explicitly answers both what ('Direct browser control via CDP') and when ('Use when the user wants to automate, scrape, test, or interact with web pages') with an explicit 'Use when' clause.

3 / 3

Trigger Term Quality

Natural user-facing terms are well covered — 'automate, scrape, test, or interact with web pages' are phrases users would actually say; 'via CDP' is mildly technical but does not undermine the otherwise natural trigger set.

3 / 3

Distinctiveness Conflict Risk

A clear niche — CDP control of the user's already-running Chrome — with distinct triggers; unlikely to be selected for unrelated 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
mishatojk/davidskills
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.