talk-stoneham-product-brain

Explains the Product Brain talk and helps design curated product-memory systems for AI-assisted product work: knowledge structure, provenance, synthesis cadence, ownership, and agent-ready context packets. Use when the user asks about product context for AI, product knowledge management, product documentation for LLMs, or building a maintained product brain.

Quality

81%

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

78%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.

The body is well-structured, lean, and actionable for a reference skill, with clear sequenced workflows and useful output templates. Its main weakness is progressive disclosure: the skill repeatedly points to outline.md, quote.md, and transcript.md, but none of those files are bundled, so navigation breaks.

Suggestions

Add the missing referenced files (outline.md, quote.md, transcript.md) under references/, or remove the references and inline the needed content, so the signaled navigation resolves to real files.

Add an explicit verification step to the 'applying the talk' workflow — e.g., confirm each curated category has recorded provenance and an owner before generating the agent-ready packet — to create a checkpoint/feedback loop.

Either add a one-line description to each item in 'What This Skill Produces' or fold that list into 'Output Templates' to remove redundancy with the Core Workflow.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding or explanation of concepts Claude already knows, but the 'What This Skill Produces' list and 'Output Templates' overlap somewhat with the 'Core Workflow', so a few tokens could be trimmed.	4 / 5
Actionability	Gives concrete, specific guidance — file references (outline.md, quote.md), bounded step counts ('Answer in 2-5 sentences'), and clear decision rules for redacted requests — with only minor gaps; appropriate for an instruction-only reference skill where code absence is not penalized.	4 / 5
Workflow Clarity	Both workflows are cleanly numbered and the factual-question flow includes a coverage check ('State when the bundle does not cover a requested detail'), but the 'applying the talk' workflow lacks an explicit validation/feedback checkpoint before producing context packets.	4 / 5
Progressive Disclosure	The Read Order signals one-level-deep references (outline.md, quote.md, transcript.md) clearly, but no references/ directory or those files exist in the bundle, so the signaled navigation does not resolve to real files.	3 / 5
	Total	15 / 20 Passed

Description

83%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.

The description is strong: it clearly states what the skill does and when to invoke it, with concrete design facets and natural trigger phrases. The main gaps are slightly abstract action verbs and minor overlap risk with adjacent knowledge-management skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete design facets — 'knowledge structure, provenance, synthesis cadence, ownership, and agent-ready context packets' — but the verbs ('Explains', 'helps design') stay somewhat abstract, leaving minor coverage gaps versus a fully comprehensive action list.	4 / 5
Completeness	Explicitly answers both 'what' (explains the talk and helps design curated product-memory systems) and 'when' (a concrete 'Use when the user asks about...' clause with multiple trigger phrases), matching the top anchor.	5 / 5
Trigger Term Quality	Provides good natural-phrase coverage — 'product context for AI', 'product knowledge management', 'product documentation for LLMs', 'building a maintained product brain' — but a few common variations a user might say are missing, and there are no file extensions (none apply to a talk-based skill).	4 / 5
Distinctiveness Conflict Risk	Carves a clear product-memory-for-AI niche with distinct triggers, but terms like 'product documentation for LLMs' and 'product knowledge management' create minor overlap risk with general documentation or knowledge-management skills.	4 / 5
	Total	17 / 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-stoneham-product-brain/SKILL.md
Commit: a3808a9

Reviewed: ~3 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.