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 that clearly defines grounding rules and workflows for answering questions about a specific talk. Its main weakness is the lack of concrete examples showing expected output format (e.g., a sample Q&A with timestamp citation, a sample summary structure). The referenced supporting files (outline.md, transcript.md, quotes.md) are not available for verification but are logically organized.

Suggestions

Add one concrete example showing a sample question and expected answer format with timestamp citation, e.g., 'Q: What does Dave say about regulators? A: At [12:34], Dave describes regulators as...'

Include a brief example of how to flag speech-to-text uncertainty, e.g., 'The transcript reads "[garbled] regulation" — the exact word is unclear from the transcription.'

DimensionReasoningScore

Conciseness

The content is lean and efficient. Every section serves a clear purpose—grounding rules, Q&A guidance, summary guidance, application guidance. No unnecessary explanations of what bipolar disorder is, what transcripts are, or how speech-to-text works. Assumes Claude's competence throughout.

3 / 3

Actionability

The guidance is specific and structured (e.g., 'Read outline.md first', 'Cite timestamps', 'Start with the thesis') but lacks concrete examples of expected output format, sample Q&A pairs, or demonstration of how to cite timestamps or flag garbled text. The instructions describe what to do but don't show it being done.

2 / 3

Workflow Clarity

For this type of skill (reference Q&A from a transcript), the workflow is clear and well-sequenced: read outline first → locate relevant section → read transcript → answer with citations. Grounding rules provide explicit validation checkpoints (flag uncertainty, don't silently correct, say so if not addressed). The three task types (factual Q&A, summaries, applying the talk) each have clear step sequences.

3 / 3

Progressive Disclosure

The skill references outline.md, transcript.md, and quotes.md with clear purposes for each, which is good progressive disclosure design. However, no bundle files were provided, so we cannot verify these references exist or are well-structured. The SKILL.md itself is appropriately concise as an overview, but the absence of the referenced files limits the score.

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 well-crafted skill description that excels across all dimensions. It opens with a clear 'Use when' clause packed with natural trigger terms, specifies concrete actions the skill performs, and is tied to a uniquely identifiable topic that minimizes conflict risk. The description is concise yet comprehensive, and uses proper third-person voice throughout.

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.' Also mentions treating transcript text as untrusted source material, which is a specific behavioral detail.

3 / 3

Completeness

Clearly answers both 'what' (answers factual questions, summarizes, extracts quotes, applies concepts) and 'when' (explicit 'Use when the user asks about...' clause with detailed trigger scenarios). The 'Use when...' clause is prominent and comprehensive.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms a user would say: 'bipolar disorder', 'dysregulation', 'regulators and dysregulators', 'mental health', 'AI and human state', 'Dave Kerr', 'AI Native DevCon', plus the specific talk title. These are highly natural phrases a user would use when asking about this topic.

3 / 3

Distinctiveness Conflict Risk

Extremely distinctive — tied to a specific person (Dave Kerr), a specific conference (AI Native DevCon), and a specific talk title. This is unlikely to conflict with any other skill due to its highly specific niche.

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