CtrlK
BlogDocsLog inGet started
Tessl Logo

browser-form-workflows

Use for complex Agent Zero Browser form workflows involving selects, checkboxes, radios, file uploads, contenteditable fields, multi-step validation, or visually verified submission.

71

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 concise, actionable instruction-only skill with a clear workflow and explicit verification steps. Adding a worked command example, an explicit verify-fail retry loop, and section headers would lift it to top marks.

Suggestions

Include one or two worked examples of a full tool call (e.g. a select_option or upload_file invocation with arguments) to make guidance copy-paste ready.

Add an explicit feedback loop: state what to do when post-submission verification shows the form did not submit or changed unexpectedly (re-capture refs and retry).

Break the prose into short section headers (e.g. '## Capture', '## Act', '## Verify') to improve scanability and structure.

DimensionReasoningScore

Conciseness

Lean prose where every line gives actionable guidance; it avoids explaining what forms or checkboxes are and the screenshot/vision_load note covers non-obvious operational detail Claude would not already know, matching the 5 anchor.

5 / 5

Actionability

Concrete tool primitives are named throughout ('browser:content', 'browser:detail', 'select_option', 'set_checked', 'upload_file', 'vision_load') with clear ordering rules, but no worked example of a full call is given, fitting the 4 anchor over the 5 anchor's copy-paste-ready examples.

4 / 5

Workflow Clarity

A clear sequence (capture refs, disambiguate, act, verify after submission) with explicit verification checkpoints and a path-exists guard for uploads, but the error-recovery feedback loop on verification failure is only implicit, fitting the 4 anchor below the 5 anchor's explicit retry loops.

4 / 5

Progressive Disclosure

A short single-file skill organized by concern into logical paragraphs with no need for external references, but it lacks section headers, so it sits at 4 rather than the 5 anchor's clearly sectioned organization.

4 / 5

Total

17

/

20

Passed

Description

92%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 specific, well-triggered description that clearly answers both what and when for a distinct niche. Minor room for improvement only in trigger-term synonym/extension coverage.

DimensionReasoningScore

Specificity

Enumerates multiple concrete form-interaction actions ('selects, checkboxes, radios, file uploads, contenteditable fields, multi-step validation, or visually verified submission'), matching the comprehensive-coverage anchor rather than the 4 anchor's 'minor gaps'.

5 / 5

Completeness

'Use for complex Agent Zero Browser form workflows involving...' states what, and the frontmatter triggers plus 'Use for' opening provide explicit when-guidance with concrete trigger phrases, matching the 5 anchor.

5 / 5

Trigger Term Quality

Natural keywords like 'checkbox', 'radio button', 'dropdown', 'file upload', 'form validation' appear in triggers with some synonyms, but a few common variations/extensions are missing, fitting the 4 anchor over the 5 anchor's full synonym-and-extension coverage.

4 / 5

Distinctiveness Conflict Risk

Scoped to 'Agent Zero Browser form workflows' with form-specific triggers, giving it a clear niche and minimal overlap with generic browser-automation skills, matching the 5 anchor.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
agent0ai/agent-zero
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.