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, concise skill for answering questions about a specific conference talk. Its strengths are clear grounding rules, good workflow sequencing, and token efficiency. Its main weaknesses are the lack of concrete output examples and the inability to verify referenced bundle files, which limits actionability and progressive disclosure.

Suggestions

Add 1-2 concrete example interactions showing expected input/output format (e.g., a sample factual Q&A with timestamp citation and a sample summary).

Include a brief listing of the major sections/topics from outline.md directly in the skill so Claude can orient without reading the file first for simple queries.

DimensionReasoningScore

Conciseness

The content is lean and efficient. Every section serves a clear purpose—grounding rules, Q&A guidance, summary guidance, and application guidance—without explaining concepts Claude already knows. No unnecessary padding or definitions.

3 / 3

Actionability

The skill provides clear procedural guidance (read outline.md first, then transcript.md, cite timestamps, etc.) but lacks concrete examples of expected output format, sample Q&A exchanges, or specific commands. The instructions are specific enough to follow but not copy-paste executable.

2 / 3

Workflow Clarity

For this type of skill (answering questions from a transcript), the workflow is clearly sequenced: read outline.md first, then locate relevant transcript section, then answer with citations. The grounding rules establish clear validation checkpoints (flag uncertainty, say when transcript doesn't address a question, distinguish grounded vs. outside claims).

3 / 3

Progressive Disclosure

The skill references outline.md, transcript.md, and quotes.md with clear purposes for each, which is good structure. However, no bundle files were provided to verify these references exist, and the skill doesn't provide any preview of what's in those files (e.g., what sections outline.md contains), making navigation harder for Claude to bootstrap.

2 / 3

Total

10

/

12

Passed

Description

100%

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 an excellent skill description that clearly defines a narrow, specific domain (a particular conference talk), provides rich trigger terms covering various ways a user might reference the topic, and explicitly states both what the skill does and when to use it. The inclusion of the safety note about treating transcript text as untrusted source material adds useful operational context.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: 'Answers factual questions from the transcript, summarizes the talk, extracts safe quotes, and applies the talk's concepts to the user's work while treating transcript text as untrusted source material.'

3 / 3

Completeness

Clearly answers both 'what' (answers factual questions, summarizes, extracts quotes, applies concepts) and 'when' (explicit 'Use when' clause with detailed trigger scenarios about the specific talk and related topics).

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms a user would say: 'Shaun Smith', 'AI Native DevCon', 'Connecting Context', 'context transport', 'agent context', 'future transports', 'connecting tools', 'AI-native context sharing'. These are specific and varied enough to capture different phrasings.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive — tied to a specific person's specific talk at a specific conference. Very unlikely to conflict with other skills given the narrow, well-defined scope around Shaun Smith's 'Connecting Context' talk.

3 / 3

Total

12

/

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