CtrlK
BlogDocsLog inGet started
Tessl Logo

pantheon-ai/ui-debug-workflow

Debug UI changes with a repeatable evidence-first workflow. Use when validating visual regressions, reproducing frontend bugs, comparing baseline vs changed behavior, collecting screenshots/DOM/logs, or producing stakeholder-ready UI debug reports. Keywords: ui bug, visual regression, browser devtools, playwright, screenshot evidence, dom snapshot, frontend debugging.

71

Quality

89%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

Quality

Content

77%

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

The body delivers a clear, validated workflow with copy-paste-ready commands and good troubleshooting guidance. Its main weaknesses are token padding (per-command 'Expected result' annotations, restated principles) and dangling reference/script paths that are not backed by actual bundle files.

Suggestions

Remove the repetitive 'Expected result:' lines under each Quick Command or collapse them into a single note; the commands are self-explanatory.

Create the referenced references/ and scripts/ files (or remove the references) so progressive disclosure points to real artifacts, and consider moving the verbose Anti-Patterns and Troubleshooting sections into those reference files.

Tighten the Core Principles section so it does not restate the Deterministic Workflow steps.

DimensionReasoningScore

Conciseness

The body is mostly efficient and actionable, but padding such as an 'Expected result:' line after every command, a Core Principles section that restates the workflow, and verbose WHY/BAD/GOOD/Consequence anti-patterns keep it short of the level-3 'every token earns its place' anchor; it is well above the level-1 over-explaining anchor.

2 / 3

Actionability

Commands are fully executable and copy-paste ready with concrete arguments (e.g. 'npx playwright install chromium' and 'capture-evidence.sh baseline http://localhost:3000 ./baseline'), matching the level-3 'fully executable, specific examples' anchor rather than the pseudocode level-2.

3 / 3

Workflow Clarity

The Deterministic Workflow is a clear numbered sequence with an explicit validation/feedback loop in step 3 ('If comparison shows unexpected differences: 1) verify identical conditions... 2) check for flaky elements 3) re-capture'), matching the level-3 anchor; it is not capped at 2 because these capture operations are non-destructive.

3 / 3

Progressive Disclosure

Sections and a one-level-deep References list are present and signaled, but the referenced files (references/debugging-checklist.md, browser-devtools-guide.md, evidence-templates.md) and the scripts/ directory do not exist in the bundle, and substantial content (anti-patterns, troubleshooting) is inline rather than split out — fitting the level-2 anchor better than the well-split level-3.

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 well-triggered: it names concrete actions, provides a clear 'Use when' clause, and includes natural keyword coverage. It cleanly answers both what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions such as 'validating visual regressions, reproducing frontend bugs, comparing baseline vs changed behavior, collecting screenshots/DOM/logs', matching the level-3 anchor rather than the single-action level-2 anchor.

3 / 3

Completeness

It states what ('Debug UI changes with a repeatable evidence-first workflow') and when ('Use when validating visual regressions...') with explicit triggers, satisfying the level-3 'both what AND when' anchor rather than the 'when missing or implied' level-2.

3 / 3

Trigger Term Quality

The explicit 'Keywords:' list (ui bug, visual regression, browser devtools, playwright, screenshot evidence, dom snapshot, frontend debugging) covers natural terms a user would say, exceeding the partial-coverage level-2 anchor.

3 / 3

Distinctiveness Conflict Risk

The evidence-first UI debug niche with distinct trigger keywords is unlikely to overlap with other skills, matching the level-3 'clear niche' anchor rather than the still-overlapping level-2.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

14

/

16

Passed

Reviewed

Table of Contents