Name: browser-debug-setup
Rating: 66.4 (1 reviews)
Author: udecode

browser-debug-setup

One-time setup for a persistent debug browser on `127.0.0.1:9222` for `dev-browser --connect`. Use when browser work is needed but no reusable debug browser is running yet.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

The canonical home for this skill is browser-debug-setup in udecode/plate

Quality

Content

81%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 setup skill with strong validation and error-recovery steps. Its weaknesses are redundancy — the core rules about not reusing the daily profile and keeping the debug browser alive are stated three times — and inline detail (profile enumeration, troubleshooting) that could be split into reference files to shorten the main body.

Suggestions

Consolidate the repeated rules: the 'do not point 9222 at the daily Default profile' guidance and the 'keep reusing the debug browser' guidance each appear in Rules, Preferred Shape/Chrome Path, and After Setup — state each once to tighten the body.

Consider moving the profile-enumeration snippet and the wrong-listener troubleshooting (lsof/kill/relaunch) into a references/ file, keeping SKILL.md as a shorter overview with one-level-deep, clearly signaled pointers.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with no explanations of concepts Claude already knows, but the same guidance is repeated across sections: "do not point 9222 at the user's daily Chrome" appears in Rules (twice, as two overlapping bullets about the Default profile), again after the Chrome path block, and "keep reusing the debug browser" recurs in Rules, Preferred Shape, and After Setup. This fits the 3 anchor (could be tightened) better than 4, whose over-explanation is only minor.	3 / 5
Actionability	Guidance is fully executable and copy-paste ready: a python3 snippet to enumerate profiles, the rsync clone with correct Singleton/lockfile exclusions, the `open -na "Google Chrome" --args` launch, curl sanity checks, and dev-browser heredocs including a websocket fallback. Common cases are covered, matching the 5 anchor.	5 / 5
Workflow Clarity	The Google Chrome Path section gives a clear 5-step numbered sequence, followed by explicit validation checkpoints (curl `/json/version`, verify `webSocketDebuggerUrl`, test `dev-browser --connect`) and an error-recovery loop for the wrong process owning 9222 (lsof, kill, relaunch). This matches the 5 anchor's explicit validation and feedback-loop criteria.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent), so all content is inline by necessity, and it is well organized into Goal, Rules, Preferred Shape, Google Chrome Path, and After Setup sections. At ~120 lines it exceeds the under-50-line simple-skill exception, and the profile-mapping/troubleshooting detail could plausibly live in a separate reference file, which keeps this at the 4 anchor rather than 5.	4 / 5
	Total	17 / 20 Passed

Description

80%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, explicit about both what it does and when to use it, and occupying a clear niche. Its main weakness is trigger-term breadth — it relies on tool-specific jargon rather than the broader vocabulary (remote debugging, Chrome, CDP) a user might naturally use.

Dimension	Reasoning	Score
Specificity	"One-time setup for a persistent debug browser on `127.0.0.1:9222` for `dev-browser --connect`" names a concrete action with a specific host, port, and target tool. It stays at one action (setup) rather than the multiple actions of the 5 anchor, but is far more concrete than the 3 anchor's generic pairing.	4 / 5
Completeness	It explicitly answers both: what ("One-time setup for a persistent debug browser on 127.0.0.1:9222 for dev-browser --connect") and when ("Use when browser work is needed but no reusable debug browser is running yet") with a concrete trigger clause. This matches the 5 anchor exactly; the 4 anchor's weaker/less-explicit 'when' does not apply.	5 / 5
Trigger Term Quality	"Use when browser work is needed but no reusable debug browser is running yet" gives some natural phrases ("browser work", "debug browser", "running yet") but misses common variations users would say, such as "remote debugging", "Chrome", "CDP", or "headless". Matches the 3 anchor (some relevant keywords, missing synonyms) rather than 4, whose coverage is noticeably broader.	3 / 5
Distinctiveness Conflict Risk	The niche is narrow and specific (one-time setup of a persistent debug browser for dev-browser on port 9222), with triggers unlikely to fire for unrelated skills. Clear distinct niche with minimal conflict risk, matching the 5 anchor.	5 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: udecode/plate
Path: templates/plate-template/.agents/skills/browser-debug-setup/SKILL.md
Commit: babb3c2

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.