CtrlK
BlogDocsLog inGet started
Tessl Logo

ainativedev/aidevcon-2026-ldn

AI Native DevCon 2026 London — all conference sessions as interactive skills

71

Quality

89%

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

Overview
Quality
Evals
Security
Files

Quality

Content

77%

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-structured knowledge skill with strong safety boundaries and clear organization. Its main weakness is the lack of concrete examples (e.g., sample Q&A pairs or a brief summary of key talk concepts inline) that would make it more immediately actionable. The referenced bundle files are not available, making it hard to fully assess progressive disclosure.

Suggestions

Add 1-2 example Q&A pairs showing how to answer a factual question and how to handle a request for redacted implementation details.

Include a brief inline summary of the talk's 3-5 key concepts so Claude has immediate context without needing to read bundle files first.

DimensionReasoningScore

Conciseness

The content is lean and well-structured. It doesn't over-explain concepts Claude already knows, and every section serves a clear purpose—safety scope, read order, and response patterns are all tightly written.

3 / 3

Actionability

The skill provides structured guidance on how to answer questions and apply the talk's concepts, including a clear read order and response shapes. However, it lacks concrete examples of actual Q&A pairs or sample outputs, making it somewhat abstract rather than fully executable.

2 / 3

Workflow Clarity

For a knowledge/Q&A skill, the workflow is clear and well-sequenced: read order is explicit (1-2-3), response categories are distinct (Factual Q&A, Applying The Talk, Safe Output Shapes), and the safety boundary acts as a validation checkpoint for what can and cannot be disclosed.

3 / 3

Progressive Disclosure

The skill references outline.md, transcript.md, and quotes.md with a clear read order, which is good structure. However, no bundle files were provided to verify these references exist, and the SKILL.md itself doesn't provide a quick-start summary of the talk's key concepts—it relies entirely on external files for substance.

2 / 3

Total

10

/

12

Passed

Description

75%

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-structured with a clear 'Use for' clause and a highly distinctive niche tied to a specific talk. Its main weakness is that the capability description is somewhat generic ('explains and answers questions') rather than listing more specific actions, and the trigger terms, while relevant, are fairly narrow and technical.

Suggestions

Expand the specific actions beyond 'explains and answers questions' — e.g., 'Summarizes key concepts, compares architectural patterns, explains trade-offs discussed in...' to improve specificity.

Add more natural trigger term variations users might use, such as 'DevCon talk', 'browser agents talk', 'Trieloff presentation', or 'AI Native DevCon 2024' to improve discoverability.

DimensionReasoningScore

Specificity

The description names the domain (Lars Trieloff's AI Native DevCon talk) and lists several topic areas (browser context, agent UX, skills, event-driven UI, sub-agents, safety-aware product architecture), but the actions are limited to 'explains and answers questions' rather than listing multiple distinct concrete actions.

2 / 3

Completeness

The description clearly answers both 'what' (explains and answers questions about the Trieloff talk on browser-native agents, covering specific topics) and 'when' (explicit 'Use for' clause mentioning Trieloff talk, browser agent architecture, and AI Native conference questions).

3 / 3

Trigger Term Quality

Includes some useful trigger terms like 'Trieloff talk', 'browser agent architecture', 'AI Native conference', 'browser-native agents', and 'sub-agents', but these are fairly niche and may miss natural user phrasings. Terms like 'browser context' and 'event-driven UI' are somewhat technical and may not match how users naturally ask questions.

2 / 3

Distinctiveness Conflict Risk

This skill is highly distinctive — it's about a specific person's specific talk at a specific conference. The combination of 'Lars Trieloff', 'AI Native DevCon', and 'browser-native agents' creates a very clear niche that is unlikely to conflict with other skills.

3 / 3

Total

10

/

12

Passed

Validation

100%

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

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents