You MUST use a todo list to complete these steps in order. Never move on to one step if you haven't completed the previous step. If you have multiple CONSECUTIVE read steps in a row, read them all at once (in parallel). Otherwise, do not read a file until you reach that step.

Add all steps to your todo list now and begin executing.

## Steps

1. [Read Gmail Profile Extraction Guidelines]: Read the documentation in: `skills/sauna/[skill_id]/references/gmail.discovery.extraction.md` (Guidelines for what to extract from each data source)

2. [Read User Profile Facts]: Discover relevant information in the user's filesystem at `documents/user/profile/[file=personal|goals|interests|ideology].md`. (Existing profile to merge with)

3. [Read Gmail Profile Analysis]: Read the file at `session/gmail-profile-analysis.json` into context (Contains discovery section with emails grouped by search category)

4. [Read Writing Samples]: Read the file at `session/writing-samples.json` into context (Contains sent email content for work domain and interests extraction)

5. Analyze discovery results and writing samples for user facts.

Read existing `documents/user/profile/[file=personal|goals|interests|ideology].md` files first. Merge new findings with existing content - don't overwrite facts from other sources.

Write to whichever state locations are appropriate based on what you discover:
- `documents/user/profile/[file=personal|goals|interests|ideology].md` (file: personal.md): location, family, pets, birthday, social accounts
- `documents/work/overview.md`: work domain, industry, role
- `documents/user/profile/[file=personal|goals|interests|ideology].md` (file: interests.md): hobbies, topics, platforms
- `documents/user/profile/[file=personal|goals|interests|ideology].md` (file: goals.md): if any emerge

Add source attribution like 'From Gmail discovery:' to new facts. Be specific but don't overfit.


6. Briefly confirm: 'Saved insights to your user profile.'