Delegate independent tasks to specialized agents working concurrently with isolated context.
Food Journal Database
Describes the structure of the Food Journal database that allows to store and read food journal entries
SKILL.md
Full skill instructions
Overview
The Food Journal Database is a structure of Markdown notes that help store information about daily food records with detailed nutritional information.
Whenever writing into the Food Journal, you must recalculate the nutritional facts details and brief analysis as explained in this document.
Root Folder
Store all the information under:
{root}/food-journal
Daily Note File
A journal entry for a given day is store as a Markdown file inside the root folder:
YYYY-MM-DD.md
Daily Note Content
The journal entry should be structured as the following example:
# Monday 22nd, 2025
{brief nutritional analysis of the day}
## Nutritional Facts
| Nutritional Facts | Goal | Consumed | Progress |
|-------------------|-----:|---------:|---------:|
| Calories | 2000 | 2000 | 100% |
| Carbs | 60g | 150g | 250% |
| Fats | 60g | 150g | 250% |
| Proteins | 60g | 150g | 250% |
| Fibers | 60g | 150g | 250% |
## Entries
### Breakfast
### Morning Snack
### Lunch
### Afternoon Snack
### Dinner
### Night Snack
For each of the entries, follow this structure:
### Lunch
{brief evaluation of the entry impact on day and life}
| Nutritional Facts | Consumed | Impact |
|-------------------|----------|--------|
| Calories | 2000 | 100% |
| Carbs | 150g | 250% |
| Fats | 150g | 250% |
| Proteins | 150g | 250% |
| Fibers | 150g | 250% |
- pizza capricciosa
_570cal, 26g carbs, 55g fat, 10g proteins_
- huge beer
_300cal, 250g carbs_
- peanut butter
_250cal, 200g fats, 30g proteins_
The "Impact" information should be computed in relation with the daily totals.
How to Write to the DB
- Create the daily entry file, or read the existing one if already existing
- Break down the user provided data into the proper
Entries - Understand if the user intention is to add new information, remove, or update existing information
- Compile the full list of consumed items in each section of the
Entries - Estimate each section's items nutritional facts
- Calculate each section's nutritional facts totals
- Calculate the day's nutritional facts totals
- Update each section's
Impactcolumn based on the calculated daily totals - Read the
GOALS.md(if it exists) to learn about the user's goals. (If not available, assume medium values for an average adult) - Update the daily's
GoalandProgresscolumns - Compute each
Entriessection brief evaluation section - Compute the day's brief evaluation section
IMPORTANT: You can write the information back into the file, or into a temporary version of the file, multiple times so to guarantee no loss of contextual information.
Expected Outcome
At the end of the process, the daily note is updated with the new information integrating existing information and the user's prompt request.
A brief recap of the operation and the daily's Nutritional Facts table is produced also in the chat output.
How to Analyze an Incoming Prompt
A user prompt can contain serveral references to multiple entries section over several days.
Example n1:
Today I had one apple for breakfast
The user intention is to provide the full list of items consumed "today" for "breakfast"
Example n2:
Today I also had one apple for breakfast
The user intention is to integrate today's breakfast section ADDING one apple
Example n3:
Today I had pasta for lunch, and I forgot to tell you that yesterday I also ate pizza for dinner.
The user is provinding information that is relevant to 2 notes:
- today: write the "lunch" section
- yesterday: integrate the "dinner" section adding an entry for a pizza
How to Guess the Proper "Entry" section
If the user prompt doesn't provide an explicit reference to the section, use the time of the day to make your assumption.
Keep the title of the section so that it matches one of the sections provided in the examples.
More Other skills
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Fundamental design principles for writing maintainable, testable Python code.
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
Generate Playwright tests from scenarios using interactive browser exploration and validation.
Automated website exploration and test case generation using Playwright.
Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
