talk-lamis-context-engineering-dreaming

Answers questions about Lamis's (Anthropic) AI Native DevCon talk on context engineering, agent memory systems, and dreaming — an asynchronous, out-of-band memory-curation process. Supports factual Q&A, framework application, system auditing, artifact drafting, and concept explanation based on the talk's content. Use when the user asks about context engineering, CLAUDE.md files, agent memory persistence, skills, multi-session memory, the dreaming process, hashing-based concurrency, or wants to apply, audit against, or draft artifacts from the frameworks described in this talk.

Quality

96%

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

92%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-structured reference skill with actionable, clearly sequenced workflows and exemplary one-level-deep progressive disclosure. The only weakness is redundant grounding guidance repeated across the 'Grounding rules' and 'Standard lookup procedure' sections.

Suggestions

Consolidate the overlap between 'Grounding rules' and 'Standard lookup procedure' — both repeat read-outline-then-transcript, quote-short-excerpts, cite-lines, and say-if-absent; reference one from the other to trim tokens.

Verify that outline.md, transcript.md, and quote.md actually ship in the skill's references/ bundle, since the body depends on them but no bundle files were present to confirm.

Dimension	Reasoning	Score
Conciseness	Lean, assumes Claude's intelligence (no padding about what context engineering is), but the 'Grounding rules' and 'Standard lookup procedure' sections overlap noticeably — both repeat read-outline-then-transcript, quote-short-excerpts, cite-lines, and say-if-absent guidance that could be consolidated.	4 / 5
Actionability	Concrete, specific procedural guidance throughout — e.g. 'Check quote.md first', 'Cite by transcript line range', verdicts 'covered / partial / missing', and the explicit '[not from talk — added as a starting placeholder]' marker — fully actionable for an instruction-only skill.	5 / 5
Workflow Clarity	Each use case is a clearly numbered sequence with grounding/verification checkpoints (cite line numbers, say 'doesn't address this' if absent, mark additions), and the audit workflow is an explicit checklist walking every dimension in order.	5 / 5
Progressive Disclosure	SKILL.md is an overview pointing one level deep to clearly signaled reference files (quote.md for highlights, outline.md for section location, transcript.md for content) with easy navigation; the referenced files were not present in the review bundle to verify existence, but the navigation structure is exemplary.	5 / 5
	Total	19 / 20 Passed

Description

100%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 well-crafted description that clearly states what the skill does and when to use it, with concrete actions and natural trigger terms. No fluff, third-person voice, and clearly distinct from other skills.

Dimension	Reasoning	Score
Specificity	Lists five concrete actions — 'factual Q&A, framework application, system auditing, artifact drafting, and concept explanation' — giving comprehensive coverage of the skill's capabilities in third person.	5 / 5
Completeness	Explicitly answers both 'what' (answers questions about the talk; supports Q&A/auditing/drafting/explanation) and 'when' ('Use when the user asks about...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive trigger list including natural synonyms — 'context engineering, CLAUDE.md files, agent memory persistence, skills, multi-session memory, the dreaming process' — alongside action verbs users would say.	5 / 5
Distinctiveness Conflict Risk	Clear niche — a specific talk by Lamis at AI Native DevCon — with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	20 / 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-lamis-context-engineering-dreaming/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.