webmcp

Implements and debugs browser WebMCP integrations in JavaScript or TypeScript web apps. Use when exposing imperative tools through document.modelContext (with a navigator.modelContext fallback), annotating HTML forms for declarative tools, handling agent-invoked form flows, or validating WebMCP behavior in the current Chrome preview. Don't use for server-side MCP servers, REST tool backends, or non-browser providers.

Quality

88%

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

Quality

Content

85%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 well-structured, actionable procedural skill with excellent workflow sequencing, validation checkpoints, and progressive disclosure via a verified bundle. The main improvement is centralizing the scattered Chrome version-number details into compatibility.md to tighten conciseness.

Suggestions

Consolidate the inline Chrome version-specific behavioral notes (146–149, 151, 153, 154, 148 transition) into references/compatibility.md and reference them from the steps, reducing time-sensitive detail in the body.

Inline one complete minimal registerTool() code block so the body is fully copy-paste ready without requiring the asset, or more explicitly signal that the asset holds the canonical template.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no concept padding), but inline time-sensitive version numbers (Chrome 146–149, 151.0.7922.0, 153+, 154.0.8017.0, 148 transition) are scattered throughout rather than centralized in the existing references/compatibility.md, which the rubric flags as a conciseness liability.	4 / 5
Actionability	Highly actionable with concrete commands ('node scripts/find-webmcp-targets.mjs .'), a copy-paste feature-detection one-liner, specific API calls (registerTool() with named params), annotation properties, and named error types with remediation; the only gap is that full executable code blocks live in the asset rather than inline.	4 / 5
Workflow Clarity	Five clearly sequenced steps with substeps, explicit stop conditions ('If the project is not a browser web app, stop and explain...'), a dedicated Step 5 validation phase (lifecycle, invalid-input, version confirmation, cancellation, build/typecheck/test), and an Error Handling section providing diagnose-and-fix feedback loops.	5 / 5
Progressive Disclosure	Clean overview body pointing to one-level-deep, conditionally-loaded bundle files — references/webmcp-reference.md, declarative-api.md, compatibility.md, troubleshooting.md, assets/model-context-registry.template.ts, and scripts/find-webmcp-targets.mjs — all verified to exist and clearly signaled with 'Read ... when ...' triggers.	5 / 5
	Total	18 / 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 strong, specific description that clearly states what the skill does and when to use it, with explicit boundary guidance. The only weakness is that trigger terms skew toward technical API identifiers rather than natural user phrasing.

Suggestions

Add a few natural-language trigger phrases a user might actually say (e.g. 'agent-submitting a form', 'exposing browser tools to an agent') alongside the API-identifier terms.

Consider including common paraphrases or synonyms users may use for WebMCP to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Implements and debugs browser WebMCP integrations', 'exposing imperative tools through document.modelContext', 'annotating HTML forms for declarative tools', 'handling agent-invoked form flows', 'validating WebMCP behavior' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what ('Implements and debugs browser WebMCP integrations in JavaScript or TypeScript web apps') and when ('Use when exposing imperative tools... annotating HTML forms... handling agent-invoked form flows, or validating WebMCP behavior'), with concrete trigger phrases and a 'Don't use for' exclusion.	5 / 5
Trigger Term Quality	Good keyword coverage with synonyms (imperative/declarative, document.modelContext with navigator.modelContext fallback, Chrome preview) and explicit anti-triggers, but the terms lean toward API identifiers and technical jargon rather than the natural paraphrases a user might say, with a few common variations missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche (browser WebMCP via document.modelContext) with distinct triggers and an explicit exclusion ('Don't use for server-side MCP servers, REST tool backends, or non-browser providers') that minimizes conflict with adjacent skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: webmaxru/web-ai-agent-skills
Path: skills/webmcp/SKILL.md
Commit: 89fee4a

Reviewed: 1 day 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.