CtrlK
BlogDocsLog inGet started
Tessl Logo

talk-firtman-web-mcp-agentic-web

Use when the user asks about Maximiliano Firtman's ("Maxi") AI Native DevCon talk on Web MCP and the agentic web — including questions about how Web MCP differs from MCP, exposing frontend tools to AI agents, the imperative vs declarative Web MCP APIs, tool design guidance (name/description/input schema/execute), the Chrome 149 origin trial, using Chrome DevTools MCP or Puppeteer as a bridge today, the Doom demo, or applying Firtman's "pick one high-value page state" adoption approach to current work.

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

77%Scale 1-3

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

This is a well-crafted skill with strong actionability and workflow clarity — each use case has a clear, numbered sequence with explicit validation steps and guardrails against hallucination. The main weaknesses are moderate verbosity from repeated quoting/citation instructions across sections and the inability to verify the referenced bundle files (outline.md, transcript.md, quotes.md). The grounding rules and speaker-attribution guidance are particularly well done for a talk-based knowledge skill.

Suggestions

Consolidate the repeated verbatim-quoting and citation instructions into a single shared section (e.g., under 'Grounding rules') and reference it from each workflow, rather than restating in every sub-section.

Ensure bundle files (outline.md, transcript.md, quotes.md) are included so the progressive disclosure structure can be fully validated and the skill is self-contained.

DimensionReasoningScore

Conciseness

The skill is reasonably well-structured but contains some verbosity, particularly in the repeated emphasis on verbatim quoting rules and the detailed sub-sections that overlap significantly (e.g., the quoting/citation instructions are restated in nearly every section). Some consolidation would reduce token usage without losing clarity.

2 / 3

Actionability

The skill provides highly concrete, step-by-step guidance for each use case (factual Q&A, drafting artifacts, applying frameworks, teaching concepts, proactive surfacing). It specifies exact file lookup sequences, quoting protocols, artifact structure (name/description/inputSchema/execute), and clear decision rules (e.g., 'if the framework doesn't fit, say so').

3 / 3

Workflow Clarity

Each workflow is clearly sequenced with numbered steps, explicit validation checkpoints (e.g., 'read outline.md first to locate section, then read transcript.md'), and guardrails (e.g., 'if the answer isn't in the transcript, say so explicitly'). The grounding rules establish a clear pre-flight checklist before any answer is produced.

3 / 3

Progressive Disclosure

The skill references external files (outline.md, transcript.md, quotes.md) appropriately and signals when to use each, but no bundle files were provided to verify these references exist. The SKILL.md itself is somewhat long and could benefit from splitting some repeated guidance (e.g., quoting rules) into a shared reference file rather than restating in each section.

2 / 3

Total

10

/

12

Passed

Description

100%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.

This is a very well-crafted skill description that clearly defines its narrow scope around a specific conference talk. It excels at listing concrete subtopics as trigger terms, includes an explicit 'Use when' clause, and is so niche that conflict risk is essentially zero. The only minor concern is that the description is quite long as a single sentence, but the density of specific trigger terms justifies the length.

DimensionReasoningScore

Specificity

The description lists multiple specific concrete topics and actions: Web MCP vs MCP differences, exposing frontend tools to AI agents, imperative vs declarative APIs, tool design guidance with specific sub-elements (name/description/input schema/execute), Chrome 149 origin trial, Chrome DevTools MCP, Puppeteer bridge, the Doom demo, and the 'pick one high-value page state' adoption approach.

3 / 3

Completeness

The description explicitly answers both 'what' (knowledge about Firtman's talk on Web MCP and the agentic web, covering specific subtopics) and 'when' with a clear 'Use when the user asks about...' clause that enumerates specific trigger scenarios.

3 / 3

Trigger Term Quality

Excellent coverage of natural terms a user would say: 'Web MCP', 'MCP', 'agentic web', 'Chrome DevTools MCP', 'Puppeteer', 'origin trial', 'Chrome 149', 'Doom demo', 'Firtman', 'Maxi', 'AI Native DevCon'. These are highly specific and natural keywords someone familiar with this talk would use.

3 / 3

Distinctiveness Conflict Risk

This is extremely niche — it's about a specific person's specific talk at a specific conference on a specific topic (Web MCP). The combination of 'Maximiliano Firtman', 'AI Native DevCon', 'Web MCP', and 'Chrome 149 origin trial' makes it virtually impossible to conflict with other skills.

3 / 3

Total

12

/

12

Passed

Validation

81%

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

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

9

/

11

Passed

Repository
AINativeDev/aidevcon-2026-ldn
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.