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 reference/lookup skill with clear grounding rules, a concrete workflow, and good example responses. Its main weaknesses are minor redundancy between the grounding rules and lookup workflow sections, and an inconsistency in which companion files are declared (quotes.md is referenced but not listed in the bundle note). Overall it provides strong, actionable guidance for answering questions about Foxwell's talk.

Suggestions

Reconcile the bundle note to list all three companion files (outline.md, transcript.md, quotes.md) consistently, since quotes.md is referenced in grounding rules and the Key Quotes section but omitted from the bundle declaration.

Consolidate the 'Cite safely' guidance that appears in both grounding rules and the lookup workflow to reduce redundancy and save tokens.

DimensionReasoningScore

Conciseness

The content is mostly efficient but includes some redundancy — the grounding rules and lookup workflow overlap (e.g., 'cite safely' appears in both), and the edge-case handling section partially restates rules already covered. Some phrasing could be tightened, but it doesn't over-explain concepts Claude already knows.

2 / 3

Actionability

The skill provides a concrete, step-by-step lookup workflow (Locate → Read → Cite safely → Cite), clear grounding rules with specific do/don't instructions, and two worked example responses showing expected approach and format. Claude knows exactly what to do for each query type.

3 / 3

Workflow Clarity

The lookup workflow is clearly sequenced with explicit steps. The grounding rules serve as validation checkpoints (e.g., verify claim exists in transcript before answering, redact sensitive values, distinguish attribution from paraphrase). Edge-case handling covers multi-section spans and ambiguous questions with clear guidance.

3 / 3

Progressive Disclosure

The skill references three companion files (outline.md, transcript.md, quotes.md) with clear roles, which is good structure. However, no bundle files were provided to verify these exist, and quotes.md is mentioned in grounding rule 2 and the Key Quotes section but not in the initial bundle note listing (which only mentions outline.md and transcript.md), creating an inconsistency. The content itself is well-organized with clear sections.

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 strong skill description that clearly identifies its niche (a specific talk by a specific person), lists numerous concrete concepts and frameworks covered, and includes an explicit 'Use when' clause with rich trigger terms. The description is well-structured, uses third person voice, and would be easily distinguishable from other skills in a large collection.

DimensionReasoningScore

Specificity

The description lists multiple specific concrete actions and concepts: answering questions about agentic software development, engineering team composition, AI-driven velocity, dev-to-PM ratios, three anchors framework, Keep/Trash/Try inventory, on-call sustainability, broken-comb skills, and auditing teams against the framework.

3 / 3

Completeness

Clearly answers both 'what' (assists with questions about Foxwell's talk and its specific concepts) and 'when' (explicit 'Use when' clause listing numerous trigger scenarios including asking about specific arguments, frameworks, and auditing teams).

3 / 3

Trigger Term Quality

Excellent coverage of natural terms a user would say: 'Hannah Foxwell', 'Reinvention of the Dev Team', 'agentic software development', 'dev-to-PM ratios', 'broken-comb skills', 'Keep/Trash/Try inventory', 'three anchors', 'on-call sustainability'. These are highly specific terms that users familiar with the talk would naturally use.

3 / 3

Distinctiveness Conflict Risk

Extremely distinctive — tied to a specific person's specific talk with highly unique terminology like 'Keep/Trash/Try inventory', 'broken-comb skills', and 'three anchors'. Very unlikely to conflict with any other skill.

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