AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Note Taking

skill-jmlozano1990-cowork-starter-kit-note-taking · by jmlozano1990

Convert reading material into organized, concise study notes using a hybrid framework auto-selected from source type (Cornell, Outline, Zettelkasten, or Lightweight bulleted).

No reviews yet
0 installs
11 views
0.0% view→install

Install

$ agentstack add skill-jmlozano1990-cowork-starter-kit-note-taking

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-jmlozano1990-cowork-starter-kit-note-taking)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
13d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Note Taking? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

When to use

Use this skill when the user asks for notes from a source — article, textbook chapter, academic paper, lecture, or long excerpt. Also use it when the user shares reading material with no specific ask and the source is long enough to benefit from structure (> 200 words). If the user shares dense study material under exam pressure, offer note-taking alongside flashcard generation. Prefer this skill over raw summarization when the user will need to review the material later — structured notes are more useful for review than a flat summary paragraph.

Cowork auto-selects a note-taking framework based on the source type and states the selection at the top of the output so the user can override it.

Triggers

  • User says "Take notes on" or "Make notes from" with an explicit source reference — highest-confidence direct invocation.
  • User shares an article, PDF chapter, or long excerpt with no specific ask — proactively offer note-taking when the source exceeds ~200 words.
  • User says "I need to study [X]" or "I'm reading [Y] for class" without naming a skill — offer note-taking as one option alongside flashcards.
  • User pastes a long excerpt and asks "What's important here?" or "Summarise this" — offer structured notes as an alternative to raw summary, framing it as more useful for later review.

Instructions

  1. Read the full source before choosing a framework.
  2. Apply the framework decision rule:

| Source type | Framework | Why | |-------------|-----------|-----| | Dense study material with concepts/definitions (textbook, academic paper) | Cornell (Cues + Notes + Summary) | Generates review cues naturally; matches exam-prep use case | | Lecture or chapter with natural hierarchy (section headers, bullet structure) | Outline (nested bullets) | Source already has hierarchy; low-ceremony fit | | Multi-source research needing cross-linking (papers citing each other) | Zettelkasten (atomic notes + cross-references) | Cross-source synthesis requires linkable atoms | | Short excerpt ( Working memory is a limited-capacity cognitive system responsible for temporary storage and manipulation of information. The dominant model, proposed by Baddeley and Hitch (1974), divides working memory into three components: the central executive, the phonological loop, and the visuospatial sketchpad. Later revisions added the episodic buffer (Baddeley, 2000). Capacity limits are typically estimated at 7±2 items (Miller, 1956), though more recent estimates suggest 4 items for active manipulation (Cowan, 2001).

Framework auto-selected: Cornell (dense definitions + citations).

Output:

# Notes: Working Memory Model (Baddeley & Hitch)

**Framework auto-selected:** Cornell (dense definitions + citations).

## Cues
- What does working memory do?
- Who proposed the main model? When?
- What are the components?
- What was added later?
- What is the capacity limit?

## Notes
- **Working memory**: limited-capacity system for temporary storage + manipulation of information
- **Baddeley & Hitch (1974) model** — 3 components:
  - Central executive (attention/control)
  - Phonological loop (verbal info)
  - Visuospatial sketchpad (visual/spatial info)
- **Baddeley (2000) revision** — added *episodic buffer*
- **Capacity limits:**
  - Classic: 7±2 items (Miller, 1956)
  - Modern (active manipulation): 4 items (Cowan, 2001)

## Summary
Working memory is a limited-capacity cognitive system. The Baddeley & Hitch (1974) three-component model (central executive, phonological loop, visuospatial sketchpad) was later extended with an episodic buffer. Capacity estimates shifted from 7±2 (Miller) to approximately 4 items for active manipulation (Cowan).

Writing-profile integration

Three-tier rule based on note section and word count:

  • Cues column (Cornell): Always terse — question fragments, not prose. Writing profile is not consulted; cues are question-mode keywords, not sentences.
  • Notes body: Neutral reference style by default. If any single note-item paragraph exceeds approximately 80 words, consult context/writing-profile.md for tone and sentence-length guidance.
  • Summary: Typically meets or exceeds 100 words — full writing-profile consultation applies. Apply the user's tone, sentence-length preferences, and pet peeves from context/writing-profile.md.

For Outline and Zettelkasten notes: apply writing-profile only to any closing synthesis paragraph that exceeds 100 words. Bullet content remains neutral reference style.

Example prompts

  • "Take notes on this biology chapter."
  • "Make notes from my Notes/psychology-reading.md."
  • "I'm reading this paper for class — can you help me study it?"
  • "What's important in this article? Give me something I can review later."

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.