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

62%

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 conceptual/policy skill that clearly defines its scope and limitations (redacted bundle). Its strengths are the clear workflow for evaluating user setups and the concrete checklist template. Its weaknesses are moderate verbosity (especially around explaining the redaction pattern multiple times) and inherently limited actionability since it deliberately avoids implementation details.

Suggestions

Reduce repetition of the redaction explanation — state it once in Safety Scope and reference that section elsewhere instead of re-explaining the pattern in the example interaction.

Consider adding a second checklist example (e.g., the Team Rollout Checklist mentioned in Safe Outputs) to increase actionability within the conceptual constraints.

DimensionReasoningScore

Conciseness

The content is mostly efficient but includes some unnecessary elaboration. The 'Safety Scope' and 'How To Help' sections are reasonably lean, but the example interaction is somewhat verbose and the overall framing could be tightened. The explanation of what redaction means is repeated in multiple places.

2 / 3

Actionability

The skill provides a concrete checklist template and a clear six-step process for evaluating a user's setup, which is good. However, by design it explicitly avoids executable commands, setup instructions, or concrete implementation details. The actionability is limited to conceptual checklists and policy reviews rather than copy-paste-ready artifacts.

2 / 3

Workflow Clarity

The six-step 'applying the talk to the user's setup' workflow is clearly sequenced and logically ordered (read → write → network → secrets → audit → review). The checklist example includes validation checkpoints (least privilege review, flagging overly broad permissions). For a conceptual/policy skill, this is well-structured.

3 / 3

Progressive Disclosure

The content is well-organized with clear sections and headers, but everything is in a single file with no bundle files to reference. The skill mentions redacted content but doesn't point to any supplementary files. For a skill of this length (~80 lines), the single-file approach is borderline acceptable, but the repeated references to redacted content without any actual bundle structure to support it weakens navigation.

2 / 3

Total

9

/

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 a well-crafted skill description that excels across all dimensions. It opens with an explicit 'Use when...' clause containing highly specific trigger terms (speaker name, conference, topic areas), clearly enumerates what the skill does (summarize, answer questions, provide checklists), and lists the specific domains covered. The narrow, well-defined scope makes it virtually impossible to conflict with other skills.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: 'Summarizes key concepts, answers questions, and provides safety checklists covering hard isolation, file-sharing boundaries, network policy, sensitive-value isolation, audit expectations, and safe team rollout.' These are detailed, enumerated capabilities.

3 / 3

Completeness

Clearly answers both 'what' (summarizes key concepts, answers questions, provides safety checklists on specific topics) and 'when' (explicit 'Use when the user asks about...' clause with multiple trigger scenarios). The 'Use when...' clause is present and detailed.

3 / 3

Trigger Term Quality

Includes highly specific natural trigger terms users would say: 'Oleg Selajev', 'AI Native DevCon', 'sandboxing local AI agents', 'AI security', 'container isolation', 'secure AI deployment'. These cover both the speaker name, event, and topical keywords a user would naturally mention.

3 / 3

Distinctiveness Conflict Risk

Extremely distinctive due to the specific speaker name, conference, and narrow topic of sandboxing local AI agents. Very unlikely to conflict with other skills given the unique combination of triggers. The note about being 'safety-redacted' further distinguishes it.

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

Reviewed

Table of Contents