To run this task you must have the following required information:

> Writing samples in state:session.style.samples

If you don't have all of this information, exit here and respond asking for any extra information you require, and instructions to run this task again with ALL required information.

---

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 Profile Extraction Guidelines]: Read the documentation in: `skills/sauna/[skill_id]/references/context.profile.extraction.md` (Guidelines for extracting persistent patterns without overfitting)

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

3. [Read Writing Samples]: Read the file at `session/writing-samples.json` into context

4. Analyze writing samples for persistent patterns about the user.

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 (`documents/user/profile/[file=personal|goals|interests|ideology].md` with files personal.md, goals.md, interests.md, or `documents/work/overview.md`) based on what you discover. Add source attribution like 'From Slack:' or 'From Gmail:' to new facts.

Be specific but don't overfit. If patterns are weak, write brief notes.


5. Briefly tell the user what you found: 'Based on your messages, you work in [domain] and seem interested in [topics].' Or if weak: 'Still learning about you - will build this up over time.'