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

100%

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

This is an excellent skill that demonstrates strong design across all dimensions. It is concise yet comprehensive, providing concrete workflows for four distinct task types (Q&A, auditing, drafting, and explaining dreaming) without unnecessary verbosity. The five-dimension framework is clearly articulated and consistently threaded through the audit and drafting workflows, and the progressive disclosure between the SKILL.md and its bundle files is well-structured with clear navigation instructions.

DimensionReasoningScore

Conciseness

The content is lean and efficient throughout. It avoids explaining what context engineering or memory systems are in generic terms, instead jumping straight to actionable frameworks and procedures. Every section serves a clear purpose with no padding or redundant explanation.

3 / 3

Actionability

The skill provides concrete, step-by-step procedures for every task type: lookup, audit, drafting, and dreaming explanation. The audit workflow includes a specific table format with an example row, the memory-store layout is a concrete directory structure, and the dreaming workflow has numbered steps. The lookup procedure is precise about when to quote verbatim and when to mark content as 'not from the talk.'

3 / 3

Workflow Clarity

Multi-step processes are clearly sequenced with explicit validation checkpoints. The Standard Lookup Procedure has a clear 5-step sequence with a verification gate (step 5: say so if not covered). The Audit Workflow includes a structured output format and ends with a prioritized recommendation step. The Dreaming Workflow includes a human/policy gate (step 5) before applying changes. Missing file detection is addressed upfront.

3 / 3

Progressive Disclosure

The skill clearly identifies three bundle files (outline.md, transcript.md, quotes.md) with their purposes, and the Standard Lookup Procedure describes exactly when and how to navigate between them. The SKILL.md itself serves as a well-organized overview with the detailed content appropriately delegated to the bundle files. However, no bundle files were provided for verification, so this is scored based on the structure as described.

3 / 3

Total

12

/

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 is highly specific, comprehensive, and distinctive. It clearly enumerates concrete capabilities, names specific frameworks and concepts, and provides an explicit 'Use when...' clause with diverse natural trigger terms. The scoping to a specific talk and its unique frameworks makes it virtually conflict-free with other skills.

DimensionReasoningScore

Specificity

The description lists multiple specific concrete actions: retrieving verbatim quotes, applying named frameworks (versioning, concurrency, permissioning, portability, progressive disclosure), auditing memory architectures, drafting specific artifacts (CLAUDE.md files, memory store layouts, dreaming orchestrator specs), and explaining named concepts (in-band vs out-of-band memory, hashing-based concurrency, dreaming process).

3 / 3

Completeness

Clearly answers both 'what does this do' (answers questions, retrieves quotes, applies frameworks, audits architectures, drafts artifacts, explains concepts) AND 'when should Claude use it' with an explicit 'Use when...' clause listing seven distinct trigger scenarios.

3 / 3

Trigger Term Quality

Includes a rich set of natural trigger terms users would actually say: 'context engineering', 'long-term memory for agents', 'CLAUDE.md', 'progressive disclosure', 'multi-agent memory coordination', 'dreaming workflow', 'agent memory systems'. These cover both high-level concepts and specific terminology a user familiar with the talk would use.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive — it is scoped specifically to Lamis's AI Native DevCon talk and its particular frameworks and concepts. The combination of the specific talk reference, named frameworks, and domain-specific artifacts like 'dreaming orchestrator specs' makes it very unlikely to conflict with other skills.

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