CtrlK
BlogDocsLog inGet started
Tessl Logo

open-notebook

Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis. Use when organizing research materials into notebooks, ingesting diverse content sources (PDFs, videos, audio, web pages, Office documents), generating AI-powered notes and summaries, creating multi-speaker podcasts from research, chatting with documents using context-aware AI, searching across materials with full-text and vector search, or running custom content transformations. Supports 16+ AI providers including OpenAI, Anthropic, Google, Ollama, Groq, and Mistral with complete data privacy through self-hosting.

67

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with complete, executable code across all features, but it front-loads a lot of inline examples that duplicate the bundled references and lacks explicit verification checkpoints in its deployment workflow.

Suggestions

Trim inline Python examples and move full endpoint detail into references/api_reference.md and references/examples.md, keeping SKILL.md to a concise overview that links out clearly.

Add explicit validation checkpoints to the Quick Start workflow, e.g. 'curl http://localhost:5055/docs' to confirm the API is up before configuring a provider.

Add a brief 'References' section that signals all bundled files (architecture.md, configuration.md, examples.md, api_reference.md) with one-line descriptions so each is clearly navigable.

DimensionReasoningScore

Conciseness

The body largely avoids explaining concepts Claude already knows, but it is ~277 lines with sizable inline Python examples for every feature that partly duplicate the bundled examples.md and api_reference.md, so it could be tightened by offloading detail to references.

2 / 3

Actionability

Provides concrete, executable Python code with specific endpoints for notebooks, sources, notes, chat, search, podcasts, transformations, and credentials — copy-paste ready and complete rather than pseudocode.

3 / 3

Workflow Clarity

Quick Start sequences the install (download compose, set encryption key, docker-compose up) and provider config as a numbered list, but there are no validation/verification checkpoints (e.g. confirm the container is healthy or the API responds) for the deployment or provider setup.

2 / 3

Progressive Disclosure

Real reference files exist and the API reference is explicitly signaled ('see references/api_reference.md'), but much inline content overlaps those references and only one reference is clearly navigated to, so content that should be separate remains inline.

2 / 3

Total

9

/

12

Passed

Description

100%

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, third-person description that clearly states what the skill does and gives explicit, natural 'Use when...' triggers covering the major capabilities. It is specific and distinctive with minimal fluff.

DimensionReasoningScore

Specificity

Lists many concrete actions — 'organizing research materials into notebooks, ingesting diverse content sources (PDFs, videos, audio, web pages, Office documents), generating AI-powered notes and summaries, creating multi-speaker podcasts... chatting with documents... searching across materials... running custom content transformations' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both 'what' ('Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis') and 'when' via a clear 'Use when organizing... ingesting... generating... creating... chatting... searching... or running...' clause.

3 / 3

Trigger Term Quality

Includes natural trigger terms a user would say — 'organizing research materials,' 'ingesting content sources (PDFs, videos, audio),' 'creating podcasts,' 'chatting with documents,' 'full-text and vector search' — giving good coverage of common phrasings.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche as a self-hosted NotebookLM alternative with distinct, domain-specific triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
K-Dense-AI/scientific-agent-skills
Reviewed

Table of Contents

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.