CtrlK
BlogDocsLog inGet started
Tessl Logo

browser-automation

Local iPolloWork Electron browser automation with CDP. Use when driving a local Electron dev app, browser_list, browser_snapshot, browser_eval, composer automation, or local UI smoke tests.

70

Quality

86%

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

72%

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

The content is highly actionable with concrete commands and a complete automation script, and it is well-organized into clear sections without redundant external references. The main gaps are minor verbosity from repeated env-var examples and a missing explicit error-recovery feedback loop around the smoke-test confirmation step.

Suggestions

Collapse the three near-identical pnpm dev env-var shell blocks (default, override, disable) into one block plus a one-line note on each variation, and replace the hard-coded macOS temp path with a portable placeholder.

Add an explicit validate->fix->retry feedback loop after the 'confirm the session response' step, e.g. 'If the expected response is missing or the Run task button is disabled, re-check the editor selector and the CDP target, then re-run the eval snippet.'

DimensionReasoningScore

Conciseness

The body is mostly lean and assumes competence, but it repeats the CDP-port env-var pattern across three near-identical shell blocks (default, override, disable) and hard-codes a macOS temp path, so it could be tightened rather than fully earning the 'every token earns its place' anchor.

2 / 3

Actionability

Provides copy-paste-ready, executable guidance — real shell commands (pnpm dev, nohup, lsof), a complete browser_eval JS snippet, exact CSS selectors, and exact URLs — matching the fully-executable anchor.

3 / 3

Workflow Clarity

The 'Browser Tool Flow' is a clear numbered 6-step sequence, but its only checkpoint is a passive confirmation ('check innerText or current URL') with no explicit validate->fix->retry feedback loop, so it sits at the anchor where sequence is present but checkpoints are missing or implicit.

2 / 3

Progressive Disclosure

No bundle files exist and the body has no reference links; the single-purpose skill is organized into well-signaled sections (What I Do, Local Dev Setup, Browser Tool Flow, Send A Session, Notes) with content kept appropriately inline, satisfying the well-organized-sections exception for skills with no need for external references.

3 / 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 well-targeted: it states concrete capabilities and an explicit 'Use when' trigger list scoped to the iPolloWork Electron automation niche. It is highly distinguishable from generic browser skills.

DimensionReasoningScore

Specificity

Names multiple concrete actions and tools — 'browser automation with CDP', 'browser_list, browser_snapshot, browser_eval, composer automation, or local UI smoke tests' — matching the anchor that lists multiple specific concrete actions rather than a single domain.

3 / 3

Completeness

Explicitly answers both what ('Local iPolloWork Electron browser automation with CDP') and when ('Use when driving a local Electron dev app...'), matching the anchor requiring both an explicit 'Use when...' clause and a clear capability statement.

3 / 3

Trigger Term Quality

Triggers are natural to the niche ('driving a local Electron dev app', 'local UI smoke tests', 'composer automation') alongside the CDP tool names a developer would actually say, giving good coverage of real terms rather than generic jargon.

3 / 3

Distinctiveness Conflict Risk

Scoped tightly to the iPolloWork Electron app with distinctive triggers (iPolloWork, local CDP, specific browser tools), making it unlikely to fire 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
Devin-AXIS/iPolloWork
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.