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

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

92%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tightly-scoped, actionable, well-sequenced procedural skill with strong feedback loops and no token waste. Its only real weakness is that the progressively-disclosed references and asset template it points to are absent from the bundle, so the disclosure structure is promised but not delivered.

Suggestions

Add the referenced bundle files (references/webmcp-reference.md, references/declarative-api.md, references/compatibility.md, references/troubleshooting.md, and assets/model-context-registry.template.ts) so the signaled progressive-disclosure paths resolve to real content.

If a file is intentionally not shipped, remove or qualify its reference in the body rather than leaving a dangling pointer (e.g. Step 3.1's assets/model-context-registry.template.ts).

Consider adding a one-line bundle manifest or 'References' index near the top so the available supporting files are discoverable at a glance.

Dimension	Reasoning	Score
Conciseness	Lean procedural prose with no conceptual padding (no 'what a model context is' exposition); nearly every numbered item is an executable directive that earns its token.	3 / 3
Actionability	Provides exact, executable patterns: the feature-detection line 'const modelContext = document.modelContext \|\| navigator.modelContext;', registerTool() signatures, name constraints (1–128 ASCII alphanumeric/_/-/.), and named error types (InvalidStateError, NotAllowedError, TypeError) with fixes.	3 / 3
Workflow Clarity	Five sequentially numbered steps with a dedicated validation step (Step 5) and explicit feedback loops (duplicate-name checks, re-validate, 'Run the workspace build, typecheck, or tests after editing'), plus an Error Handling section mapping failure signatures to remedies.	3 / 3
Progressive Disclosure	The body cleanly signals one-level-deep references (references/webmcp-reference.md, references/declarative-api.md, references/compatibility.md, references/troubleshooting.md, assets/model-context-registry.template.ts) with read-trigger conditions, but none of these bundle files actually exist in the skill, so the signaled navigation resolves to nothing.	2 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 specific, trigger-rich, complete on both what and when, and well-bounded against conflicts. It hits the top anchor on every dimension with no padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Implements and debugs', 'exposing imperative tools', 'annotating HTML forms', 'handling agent-invoked form flows', 'validating WebMCP behavior') rather than vague language.	3 / 3
Completeness	Explicitly answers what ('Implements and debugs browser WebMCP integrations') and when (an explicit 'Use when…' clause plus a 'Don't use for…' exclusion), satisfying both halves.	3 / 3
Trigger Term Quality	Strong natural-term coverage a user would say: 'WebMCP integrations', 'JavaScript or TypeScript web apps', 'HTML forms', 'agent-invoked form flows', 'Chrome preview'.	3 / 3
Distinctiveness Conflict Risk	A clearly defined browser-WebMCP niche with explicit exclusions ('Don't use for server-side MCP servers, REST tool backends, or non-browser providers') makes conflicting triggers unlikely.	3 / 3
	Total	12 / 12 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
referenced_paths_exist	Referenced path issues: 10 missing	Warning

	Total	15 / 16 Passed

Repository: webmaxru/web-ai-agent-skills
Path: skills/webmcp/SKILL.md
Commit: f4c5a23

Reviewed: 13 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.