talk-overweg-one-brain-no-filtering

Explains Robert Overweg's One Brain, No Filtering talk and helps design safe knowledge-memory systems: context maps, retrieval rules, provenance labels, local knowledge-store structure, and review checkpoints. Use when the user asks about agent memory, unified knowledge bases, reducing context loss, or designing inspectable knowledge workflows.

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

75%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, token-efficient instruction skill with clear sequencing and output templates, consistently just below the top anchor. The principal defect is that the body references outline.md, quote.md, and transcript.md, but no bundle files are present, so those references are dangling.

Suggestions

Add the referenced bundle files (outline.md, quote.md, transcript.md) under references/, or remove the references and inline the essential content so no links are dangling.

Consolidate the redaction-boundary guidance into a single statement to remove the three-way repetition across Read Order, the Core Workflow paragraph, and the Redacted Request template.

Make at least one output template fully concrete (e.g., a filled-in example artifact) so the guidance crosses from abstract placeholders to copy-paste-ready output.

Dimension	Reasoning	Score
Conciseness	The body is lean and does not over-explain concepts Claude already knows, but the redaction-boundary policy is restated three times (Read Order #4, the operational-mechanics paragraph, and the Redacted Request template), which is minor redundancy that could be tightened.	4 / 5
Actionability	Numbered workflows and output templates with named fields (Goal, Boundaries, Review points, Evidence) plus example response shapes give mostly concrete guidance, though the placeholder templates remain abstract rather than copy-paste ready.	4 / 5
Workflow Clarity	Read Order and the two Core Workflow sub-procedures are clearly sequenced, and 'State when the bundle does not cover a requested detail' acts as a soft checkpoint, but there is no explicit validate-and-retry feedback loop. No destructive/batch operations are present, so the workflow-clarity cap does not apply.	4 / 5
Progressive Disclosure	References to outline.md, quote.md, and transcript.md are well-signaled and one level deep in a lean overview, but the bundle directories (references/, scripts/, assets/) are absent, so those referenced files do not actually exist — navigation is structurally clean but the links do not resolve.	4 / 5
	Total	16 / 20 Passed

Description

88%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 strong, complete description that clearly states both capability and trigger conditions with concrete deliverables. Main weakness is trigger-term breadth (no synonyms) and some overlap risk on the broad memory/knowledge-base terms.

Dimension	Reasoning	Score
Specificity	Enumerates five concrete deliverables ('context maps, retrieval rules, provenance labels, local knowledge-store structure, and review checkpoints'), giving comprehensive specific actions rather than vague language.	5 / 5
Completeness	Explicitly answers both 'what' (explains the talk and helps design safe knowledge-memory systems) and 'when' (concrete 'Use when...' trigger phrases), matching the anchor-5 example.	5 / 5
Trigger Term Quality	'Use when the user asks about agent memory, unified knowledge bases, reducing context loss, or designing inspectable knowledge workflows' offers good natural keyword coverage, but each concept has only one phrasing with no synonyms, falling short of anchor 5.	4 / 5
Distinctiveness Conflict Risk	The named talk ('Robert Overweg's One Brain, No Filtering') gives a clear niche, but broad triggers like 'agent memory' and 'unified knowledge bases' could overlap with other memory-related skills, so it is not minimal conflict risk.	4 / 5
	Total	18 / 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-overweg-one-brain-no-filtering/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.