CtrlK
BlogDocsLog inGet started
Tessl Logo

stagehand-automation

AI-powered browser automation using Stagehand v3 and Claude. Use when building self-healing tests, AI agents, dynamic web automation, or when traditional selectors break frequently due to UI changes.

60

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/stagehand-automation/SKILL.md

The canonical home for this skill is stagehand-automation in fernandezbaptiste/Skrillz

SKILL.md
Quality
Evals
Security

Quality

Content

57%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.

The body is action-rich with solid executable examples, but it is undermined by marketing fluff, unsegregated version-sensitive details, a missing validation checkpoint in the main workflow, and broken/mismatched reference file citations that hurt navigation.

Suggestions

Fix the References section: cite the actual bundle files (api-reference.md, troubleshooting.md) as markdown links and remove the three nonexistent file references.

Add a verify/validate checkpoint to the Quick Start workflow (e.g., assert the extracted data or confirm navigation succeeded) and gate destructive actions behind it.

Strip marketing fluff ('state-of-the-art', 'Always works', the closing tagline) and move version-sensitive details (model IDs, '44% faster than v2') into a clearly labeled version/deprecated section.

DimensionReasoningScore

Conciseness

Mostly code-driven and efficient, but padded with marketing fluff ('state-of-the-art', 'Always works', closing tagline) and unsegregated time-sensitive claims (model IDs dated 20250514, 'Stagehand v3', '44% faster than v2') that the rubric penalizes when not placed in a deprecated/old-patterns section.

3 / 5

Actionability

Provides abundant copy-paste-ready TypeScript across act/extract/observe, hybrid Playwright usage, and error handling; minor gaps include an undefined `complexSchema` variable and a missing `z` import in the hybrid snippet.

4 / 5

Workflow Clarity

The Quick Start is a clear 4-step sequence (install, configure, write, run) but has no validation/verification checkpoint, and because browser automation drives destructive/batch operations (form filling, cross-site workflows), the rubric caps workflow clarity at 3.

3 / 5

Progressive Disclosure

Section structure is good, but the References section cites three files that do not exist (stagehand-v3-guide.md, claude-integration.md, self-healing-patterns.md) while the actual bundle files (api-reference.md, troubleshooting.md) are never cited, and references are plain backtick text rather than navigable links.

3 / 5

Total

13

/

20

Passed

Description

83%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 well-crafted: third-person voice, clear what-and-when structure with an explicit trigger clause, and a distinct niche. It is held back from full marks only by slightly incomplete action coverage and missing synonym-level trigger terms.

DimensionReasoningScore

Specificity

Names the domain ('AI-powered browser automation using Stagehand v3 and Claude') and several concrete actions ('building self-healing tests, AI agents, dynamic web automation'), with minor gaps (no explicit mention of extraction/observation APIs).

4 / 5

Completeness

Explicitly states what it does and provides an explicit 'Use when building self-healing tests, AI agents, dynamic web automation, or when traditional selectors break frequently due to UI changes' trigger clause with concrete triggers.

5 / 5

Trigger Term Quality

Includes natural phrases users would say ('self-healing tests', 'AI agents', 'dynamic web automation', 'traditional selectors break', 'UI changes') but omits some synonyms and package-level terms; good but not comprehensive.

4 / 5

Distinctiveness Conflict Risk

The Stagehand v3 + Claude self-healing niche is mostly distinct from generic automation skills, with only minor overlap risk against broad browser-automation skills.

4 / 5

Total

17

/

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

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

15

/

16

Passed

Repository
fernandezbaptiste/Skrillz
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.