A tight, instruction-only skill that reads like operational guidance rather than documentation: named commands, explicit preconditions, conditional escalation to visual verification, and post-submission checks, all in a dozen lines. The only gaps are the absence of full command call syntax and an error-recovery loop after failed verification.

Dimension	Reasoning	Score
Conciseness	The body is ~12 lean lines with zero padding: every sentence names a tool, a condition, or a guard ("Prefer ref-based form actions before coordinates", "no-path screenshots return chat-scoped artifact paths for `vision_load`"). Nothing explains concepts Claude already knows, matching the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	Concrete named commands throughout (`select_option`, `set_checked`, `upload_file`, `type`, `type_submit`, `submit`, `browser:content`, `browser:detail`, `browser:screenshot`, `vision_load`) with explicit conditions for each, satisfying 'mostly executable guidance; concrete code or commands with minor gaps'. It stops short of the 5 anchor because no full call syntax or argument examples are shown — only command names are given.	4 / 5
Workflow Clarity	A clear sequenced workflow is present: capture refs with `browser:content` → `browser:detail` on ambiguous fields → act via ref-based commands → visual verification when needed → "Verify after submission with `browser:content`, `browser:state`, or ... `browser:screenshot` plus `vision_load`", plus a pre-flight check ("Verify that every path exists before calling `upload_file`"). It fits 'clear sequence with most checkpoints present; minor validation gaps' rather than 5 because no error-recovery loop is described for what to do when verification fails.	4 / 5
Progressive Disclosure	The skill is under 50 lines with no external references needed (no references/, scripts/, or assets/ bundle exists, and the body references no files), so the simple-skill guideline applies: well-organized, appropriately scoped inline sections earn a 5. All content belongs in SKILL.md and nothing is buried or nested.	5 / 5
	Total	18 / 20 Passed

Description

73%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 concise, third-person, and specific about form capabilities, backed by an excellent natural-language trigger list. Its main weakness is the missing 'Use when...' clause inside the description field itself, which caps completeness at 3 despite the strong trigger coverage in the surrounding frontmatter.

Suggestions

Add a 'Use when...' clause to the description itself, e.g. "Use when filling or submitting web forms with selects, checkboxes, radios, file uploads, or contenteditable fields", to lift completeness above the cap of 3.

Enumerate more concrete form actions and controls in the description (e.g., checkboxes, radio buttons, dropdowns) so its capability coverage matches the comprehensive trigger list.

State the browser-automation relationship in the description (e.g., "as the form-specific extension of browser-automation") to sharpen distinctiveness against the parent skill.

Dimension	Reasoning	Score
Specificity	"Fill and submit web forms: uploads, selects, validation and contenteditable fields" names the domain and several specific actions (fill, submit, uploads, selects, contenteditable), matching the 'several specific actions; minor gaps' anchor. It falls short of the 5 anchor because some actions are field-type enumerations rather than distinct operations, and common form controls like checkboxes and dropdowns are absent from the description itself.	4 / 5
Completeness	The description field has a clear 'what' ("Fill and submit web forms: uploads, selects, validation and contenteditable fields") but no 'Use when...' clause or equivalent within the description itself, which caps completeness at 3 per the judging guidelines. The separate `triggers` frontmatter block provides explicit trigger guidance, which keeps this from scoring lower, but the description field alone only weakly implies 'when'.	3 / 5
Trigger Term Quality	The frontmatter trigger list ("browser form", "web form", "fill form", "select option", "dropdown", "checkbox", "radio button", "file upload", "contenteditable", "form validation") comprehensively covers natural user phrasing including synonyms (dropdown / select option, checkbox, radio button), matching the 'comprehensive coverage of natural terms including synonyms' anchor.	5 / 5
Distinctiveness Conflict Risk	"Fill and submit web forms: uploads, selects, validation and contenteditable fields" carves out a clear form-filling niche, but as a declared extension of `browser-automation` it has minor overlap risk with that closely related parent skill. This matches 'mostly distinct; minor overlap risk with closely related skills' rather than the 5 anchor, since generic terms like 'validation' could pull triggers away from sibling skills.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: agent0ai/agent-zero
Path: plugins/_browser/skills/browser-form-workflows/SKILL.md
Commit: e3051fb

Reviewed: 10 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.