talk-batey-building-product-teams-age-of-ai

Use when the user asks about Christopher Batey's talk 'Building Product Teams in the Age of AI: What We Had to Relearn Every Quarter' (Latent Space, 2026) — including questions about running AI-assisted product engineering teams, his three pillars (path to production at AI speed, training/evaluating AI-enabled engineers, designing workflow for parallel change), ADR-first workflows with agents, why review becomes the bottleneck, the producer 'black box' (harness/host/model), vanity metrics vs adoption, two-to-four-person sub-streams, one-complex-task-at-a-time, 'you build it, you run it, you drive adoption', or applying his approach to current work.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

71%Weight 40%Scale 1-5

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

A well-organized, concise reference skill with a clear grounding workflow and explicit safety rules, but its progressive disclosure is undermined because the bundle files it depends on (outline.md, transcript.md, quote.md) are missing from the bundle.

Suggestions

Ship the referenced bundle files (outline.md, transcript.md, quote.md) in references/ so the grounding workflow can actually execute; the skill's core value depends on them.

Remove the placeholder '[safe excerpts from transcript.md]' in the example and show a real (or clearly-marked representative) excerpt so the expected output format is unambiguous.

Trim the redundancy between the 'Grounding rules' numbered list and the 'Example' workflow, which repeats the same outline-then-transcript steps.

Dimension	Reasoning	Score
Conciseness	Lean body with no generic concept explanations, but the 'Example' workflow section restates the grounding rules (read outline.md then transcript.md) already given above, which could be trimmed.	4 / 5
Actionability	Concrete, file-specific instructions (read outline.md, locate the section, read that section of transcript.md, quote short excerpts, flag missing claims) with an output-format example; the example uses a '[safe excerpts from transcript.md]' placeholder rather than real content, a minor gap.	4 / 5
Workflow Clarity	Clear numbered sequence (locate via outline, read transcript section, quote, then verify claim presence) with an explicit grounding checkpoint ('If a claim isn't in transcript.md, say so explicitly — do not speculate'), though no retry/feedback loop is present.	4 / 5
Progressive Disclosure	The SKILL.md is structured as a clean overview pointing one level deep to outline.md, transcript.md, and quote.md with clear per-file descriptions, but none of these referenced bundle files actually exist in references/, scripts/, or assets/ — so the disclosed detail content is absent and navigation cannot resolve.	3 / 5
	Total	15 / 20 Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A highly specific, well-triggered reference-skill description that clearly names the talk, speaker, and podcast while listing concrete covered topics. It uses the correct 'Use when...' trigger form and third-person voice with no over-claims.

Dimension	Reasoning	Score
Specificity	Names a single concrete action (answering questions about the talk) but enumerates many specific sub-topics — three pillars, ADR-first workflows, review bottleneck, producer 'black box', vanity metrics vs adoption, two-to-four-person sub-streams — giving comprehensive topic coverage with only a minor gap in action variety.	4 / 5
Completeness	Explicitly states what the skill does ('Use when the user asks about...') and when to use it, with concrete trigger phrases and an extensive list of covered topics, satisfying both 'what' and 'when' clearly.	5 / 5
Trigger Term Quality	Includes exactly the natural terms a user would say — the speaker name (Christopher Batey), the verbatim talk title, the podcast (Latent Space, 2026), plus topic phrases like 'review becomes the bottleneck' and 'ADR-first workflows'.	5 / 5
Distinctiveness Conflict Risk	Targets one uniquely named talk by a specific person on a named podcast, creating a clear niche with distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: jscraik/Agent-Skills
Path: Plugins/aidevcon/skills/talk-batey-building-product-teams-age-of-ai/SKILL.md
Commit: a3808a9

Reviewed: ~4 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.