Is the Project Notetaker skill free?

Yes. The skill itself is free from bonigarcia/context-engineering. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Project Notetaker SkillProof Score?

7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.

How do I install Project Notetaker?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Project Notetaker with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Project Notetaker

12-line skill pinning meeting notes to attendees, decisions, action table

by bonigarcia · bonigarcia/context-engineering

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 7.6/10
Tested: Aug 10, 2026
Environment: Claude Code 2.x (agent harness)

Fed the same 18-line standup scrawl to a no-skill run and a skill run and diffed the two reports. The skill's action-item table is a genuine improvement: it forced two ownerless tasks into explicit Unassigned rows, where prose buries them. But its four-section template has no slot for anything that is not a decision or a task, and four facts the baseline kept vanished: the consequence of the risk (Stripe could flag the account), the next sync time, the note that nobody volunteered for the escalation, and the silent attendee. Worse, it filed two non-decisions under Key decisions, including an item the notes explicitly say was parked and not decided. Net a wash at 179 words versus 189, which is why the score is 5 and not a pass: the table gains about as much as the fixed structure loses. Installs in one copy with nothing to configure, and it is a book example rather than a maintained tool.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 5/10
Docs & honesty 4/5

What Project Notetaker does

A minimal Agent Skill from the Context Engineering book that reformats raw meeting notes into four fixed sections: title, attendees, key decisions, and an action-item table with task, owner and due-date columns. It triggers when you paste messy notes or ask for a meeting summary. There are no scripts or references, just the four-step instruction, so it constrains layout rather than adding analysis.

How to install Project Notetaker

git clone --depth 1 https://github.com/bonigarcia/context-engineering.git
mkdir -p ~/.claude/skills
cd context-engineering && cp -r ch02/agent-skills/project-notetaker ~/.claude/skills/project-notetaker

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Project Notetaker

/project-notetaker 12-line skill pinning meeting notes to attendees, decisions, action table

It also activates on plain-language prompts like these:

Turn these messy standup notes into a clean meeting summary
Summarize this meeting transcript into decisions and action items
Reformat my raw notes into attendees, decisions, and owed tasks

Frequently asked questions

Is the Project Notetaker skill free?: Yes. The skill itself is free from bonigarcia/context-engineering. SkillProof publishes the install command and an independent test verdict at no cost.
Does Project Notetaker work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Aug 10, 2026. Verdict: Works with setup. Fed the same 18-line standup scrawl to a no-skill run and a skill run and diffed the two reports. The skill's action-item table is a genuine improvement: it forced two ownerless tasks into explicit Unassigned rows, where prose buries them. But its four-section template has no slot for anything that is not a decision or a task, and four facts the baseline kept vanished: the consequence of the risk (Stripe could flag the account), the next sync time, the note that nobody volunteered for the escalation, and the silent attendee. Worse, it filed two non-decisions under Key decisions, including an item the notes explicitly say was parked and not decided. Net a wash at 179 words versus 189, which is why the score is 5 and not a pass: the table gains about as much as the fixed structure loses. Installs in one copy with nothing to configure, and it is a book example rather than a maintained tool.
What is the Project Notetaker SkillProof Score?: 7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.
How do I install Project Notetaker?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Project Notetaker with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.