talk-lamis-context-engineering-dreaming

Welcome to AI Native DevCon — Context Engineering, Memory Systems, and Dreaming

Quality

38%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./talk-lamis-context-engineering-dreaming/SKILL.md

Quality

Content

77%Scale 1-3

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-crafted reference skill for answering questions about a specific talk. Its greatest strength is actionability — each use case has clear, specific, numbered workflows with explicit guardrails against hallucination and misattribution. The main weakness is moderate verbosity: the repeated pattern of 'read outline.md → read transcript.md → quote verbatim' across multiple sections could be consolidated, and the introductory summary paragraph is longer than necessary for Claude's comprehension.

Suggestions

Consolidate the repeated 'read outline.md → read transcript.md → quote verbatim' pattern into a single shared procedure referenced by each use case section, reducing redundancy across the six workflow sections.

Trim the introductory paragraph — Claude doesn't need the full talk summary to follow the instructions; a one-line description of the talk's topic would suffice.

Dimension	Reasoning	Score
Conciseness	The content is reasonably well-structured but includes some verbose explanations that could be tightened. For example, the long introductory paragraph summarizing the talk and some of the step-by-step instructions repeat similar patterns across sections (read outline.md, read transcript.md, quote verbatim) that could be consolidated into a shared preamble.	2 / 3
Actionability	Each use case (factual Q&A, applying frameworks, auditing, drafting artifacts, teaching concepts, proactive surfacing) has concrete, numbered step-by-step instructions with specific actions (e.g., 'read outline.md first', 'quote verbatim', 'give a clear verdict per dimension: covered / partial / missing'). The guidance is specific and directly executable by Claude.	3 / 3
Workflow Clarity	Each workflow is clearly sequenced with explicit steps. The grounding rules serve as validation checkpoints (e.g., 'If a claim isn't in transcript.md, say the talk doesn't address this'). The audit workflow includes completeness checks ('walk the user through every dimension — don't skip ones that seem weak') and the artifact drafting workflow includes a verification step ('quote verbatim the speaker's prescription so the user can see what the draft is grounded in') and an explicit 'ask rather than invent' guardrail.	3 / 3
Progressive Disclosure	The skill references external files (outline.md, transcript.md, quotes.md) appropriately and signals when to use each. However, no bundle files were provided, so we can't verify these references exist. The SKILL.md itself is somewhat long and could benefit from splitting some of the repeated patterns into a shared reference, but the section organization is clear.	2 / 3
	Total	10 / 12 Passed

Description

0%Scale 1-3

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 description reads like a conference session title rather than a functional skill description. It fails on every dimension: it specifies no concrete actions, includes no natural trigger terms, answers neither 'what' nor 'when', and is too generic to be distinguishable from other skills. It needs a complete rewrite to function as a skill description.

Suggestions

Rewrite the description to specify concrete actions the skill performs, e.g., 'Manages context windows, implements memory persistence across sessions, and configures agent dreaming workflows.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about context engineering, long-term memory for agents, or session persistence.'

Remove the conference-style greeting ('Welcome to AI Native DevCon') and use third-person voice describing capabilities instead.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. It reads like a conference title or welcome message rather than a skill description. There are no verbs describing what the skill does.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. There is no 'Use when...' clause, no description of capabilities, and no explicit trigger guidance.	1 / 3
Trigger Term Quality	The terms 'Context Engineering', 'Memory Systems', and 'Dreaming' are abstract/buzzwordy and not natural keywords a user would say when needing a specific task performed. 'AI Native DevCon' is an event name, not a trigger term.	1 / 3
Distinctiveness Conflict Risk	The description is so vague and broad ('Context Engineering, Memory Systems, and Dreaming') that it could overlap with virtually any AI-related skill. It provides no clear niche or distinct triggers.	1 / 3
	Total	4 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: AINativeDev/aidevcon-2026-ldn
Path: talk-lamis-context-engineering-dreaming/SKILL.md
Commit: 1887349

Reviewed: ~2 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.