add-webmcp

Analyze an existing web application, identify safe user-visible capabilities across routes, forms, server actions, handlers, and schemas, then implement first-party WebMCP tools and validate discovery and invocation with Stagehand. Use when the user asks to make a codebase agent-ready, expose website features as WebMCP tools, or add WebMCP directly to an app rather than generating a standalone injection script from a URL.

Quality

92%

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

92%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-engineered skill body: executable commands, a clearly sequenced multi-step workflow with built-in validation and adversarial verification, and clean progressive disclosure to real reference and script files. The only minor weakness is some length in the step-6 prose that could be trimmed.

Dimension	Reasoning	Score
Conciseness	Dense, high-signal content that assumes Claude's competence (no basic-concept padding) and concentrates on real gotchas, but step 6's adversarial prose is lengthy enough that a few passages could be tightened without losing clarity.	4 / 5
Actionability	Provides copy-paste-ready commands with exact paths and flags (scan-codebase.mjs, pnpm install, validate-stagehand.mjs, browse CLI), concrete JS for modelContext access, and specific examples covering the common discovery/invocation cases.	5 / 5
Workflow Clarity	A clear 7-step sequence with explicit validation checkpoints (step 5: tests/typecheck/build + Stagehand validation) and a feedback loop in step 6 ("Treat every discrepancy as a defect... and fix it there"), with consequential operations gated and verified — well above the destructive-ops cap of 3.	5 / 5
Progressive Disclosure	SKILL.md is an overview that signals one-level-deep references to real bundle files ([references/implementation-and-validation.md], [references/quality-rubric.md]) and scripts (scan-codebase.mjs, validate-stagehand.mjs) with no nested references, keeping navigation shallow and easy.	5 / 5
	Total	19 / 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 covers what and when with concrete trigger phrases and explicit disambiguation from a related skill. The only minor gap is trigger-term breadth, which is good but not as lexically exhaustive as the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Analyze an existing web application", "identify safe user-visible capabilities across routes, forms, server actions, handlers, and schemas", "implement first-party WebMCP tools", "validate discovery and invocation with Stagehand" — covering the full lifecycle with comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (analyze, identify, implement, validate) and when via a concrete "Use when the user asks to make a codebase agent-ready, expose website features as WebMCP tools, or add WebMCP directly to an app" trigger clause.	5 / 5
Trigger Term Quality	Includes natural phrases users would say — "make a codebase agent-ready", "expose website features as WebMCP tools", "add WebMCP directly to an app" — but lacks the synonym/file-extension breadth of the top anchor; strong but not maximally comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (first-party WebMCP tools from source code) and explicitly disambiguates from the sibling skill via "rather than generating a standalone injection script from a URL", giving it distinct triggers and minimal conflict risk.	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: browserbase/skills
Path: skills/add-webmcp/SKILL.md
Commit: 6811ca3

Reviewed: 2 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.