CtrlK
BlogDocsLog inGet started
Tessl Logo

neomatrix369/content-distiller

Extract actionable insights and valuable artifacts from web posts, articles, and technical documentation. Use when summarizing content, extracting key ideas from URLs/articles, preserving code snippets and diagrams, or creating visual summaries. Triggers on requests like "summarize this post", "extract insights from", "distill this article", "what are the key takeaways", or when a URL is shared for analysis.

97

1.25x

Quality

100%

Does it follow best practices?

Impact

94%

1.25x

Average score across 5 eval scenarios

Overview
Skills
Evals
Files

rubric.jsonevals/scenario-3/

{
  "context": "Tests whether the agent adapts summary length and included sections based on content density: simple content gets only MUST sections, technical content gets MUST+SHOULD, deep content gets all sections including COULD.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "Simple: minimal sections",
      "description": "Simple article summary includes only MUST sections (core thesis, insights, takeaways) without extensive extra sections",
      "max_score": 12
    },
    {
      "name": "Simple: no code sections",
      "description": "Simple article summary does NOT include code/config sections since none present in source",
      "max_score": 8
    },
    {
      "name": "Technical: includes code",
      "description": "Technical article summary includes the code examples in full",
      "max_score": 10
    },
    {
      "name": "Technical: code complete",
      "description": "Code in technical summary is preserved completely without truncation",
      "max_score": 8
    },
    {
      "name": "Technical: code context",
      "description": "Code blocks include purpose description, requirements/dependencies notes, or key insights about non-obvious aspects",
      "max_score": 10
    },
    {
      "name": "Deep: extended sections",
      "description": "Deep dive article summary includes optional COULD sections such as mental models, gotchas, or follow-up questions since content warrants it",
      "max_score": 12
    },
    {
      "name": "Deep: mental model",
      "description": "Deep dive summary includes the mental model (distributed systems as unreliable components) with framework name and explanation",
      "max_score": 10
    },
    {
      "name": "Deep: gotchas present",
      "description": "Deep dive summary calls out gotchas/caveats (e.g., event sourcing challenges, two-phase commit problems)",
      "max_score": 10
    },
    {
      "name": "All: core thesis",
      "description": "All three summaries include a one-sentence core thesis capturing the main idea",
      "max_score": 10
    },
    {
      "name": "All: concise insights",
      "description": "Insights across all summaries are kept to 2 lines or fewer each",
      "max_score": 10
    }
  ]
}

Install with Tessl CLI

npx tessl i neomatrix369/content-distiller

evals

SKILL.md

tile.json