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 strong, actionable skill that provides concrete schemas, templates, and workflows for implementing Groetzinger's framework. Its main weakness is being somewhat monolithic — all content lives in one file when some sections (JSONL schema details, skill template, pipeline steps) could be split out. Minor verbosity in narrative framing could be trimmed, but the core instructional content is lean and well-structured.

Suggestions

Trim the narrative framing in the opening paragraph and 'Key Frameworks' section — Claude doesn't need persuasive context about why skills matter, just the operational patterns.

Consider splitting the JSONL schema, skill file template, and KB-to-skill pipeline into separate referenced files to improve progressive disclosure and reduce the monolithic feel.

DimensionReasoningScore

Conciseness

The content is mostly efficient and well-structured, but includes some unnecessary framing (e.g., explaining what Groetzinger 'argues' and contextual narrative about Cisco teams). The 'Applying to Your Team' section is useful but somewhat verbose — the audit checklist and distributed teams guidance could be tighter. Claude doesn't need the narrative setup about frontier models being 'capable enough.'

2 / 3

Actionability

The skill provides concrete, copy-paste-ready artifacts: a JSONL schema with example entries, a complete skill file template with frontmatter, a 6-step pipeline with specific gate decisions, an audit checklist with specific yes/no questions, and a semantic versioning table. These are all directly executable or immediately usable.

3 / 3

Workflow Clarity

The KB-to-skill pipeline is a clear 6-step sequence with explicit validation checkpoints (gate decision logged, eval re-run logged pass/fail, sync logged as confirmed) and a feedback loop (high severity requires eval dataset update before merge). The semantic versioning progression provides clear graduation criteria. The audit checklist is sequenced logically.

3 / 3

Progressive Disclosure

The content is well-organized with clear section headers and logical grouping, but it's a monolithic file with no references to supporting files. The JSONL schema, skill template, and pipeline details could be split into separate referenced files. The 'See evals.jsonl co-located with this file' reference in the template is good modeling but no actual bundle files exist to support progressive disclosure.

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 a very strong description that clearly defines a narrow, specific domain — a particular conference talk and its frameworks. It excels at completeness with an explicit 'Use when' clause covering multiple trigger scenarios, lists highly specific and concrete capabilities, and has virtually zero conflict risk due to its unique subject matter. The only minor concern is that the description is quite long and dense, though the verbosity is justified by the specificity of the content.

DimensionReasoningScore

Specificity

The description lists numerous specific concrete actions and concepts: KB-to-skill conversion with LLM-gated diffs, evals as unit tests, JSONL dataset schemas, semantic versioning of skills, syncing skill READMEs to agent registries and Confluence, drafting eval datasets, and more.

3 / 3

Completeness

The description explicitly answers both 'what' (knowledge about Groetzinger's talk, frameworks, and prescribed artifacts) and 'when' with a clear 'Use when...' clause at the beginning covering multiple trigger scenarios including asking about the talk, auditing against the framework, and drafting prescribed artifacts.

3 / 3

Trigger Term Quality

Includes highly specific natural trigger terms a user would actually say: 'John Groetzinger', 'Skills Everywhere', 'Cisco Customer Experience', 'context pipelines', 'knowledge-base-article-to-skill', 'evals', 'semantic versioning', 'agentic development'. These are the exact phrases someone familiar with this talk would use.

3 / 3

Distinctiveness Conflict Risk

Extremely distinctive — it is scoped to a specific person's specific talk with named concepts (LLM-gated diffs, KB-to-skill pipelines, Cisco CX context pipelines). This is highly unlikely to conflict with any other skill due to its narrow, well-defined niche.

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