Prompts und Personalisierung

Seed my Palim Brain from this repository in one pass.

Read the repository root: README, package.json/pyproject.toml or equivalent,
CLAUDE.md/AGENTS.md if present, the last 20 git log entries, and any open
TODO/FIXME markers or a TODO.md if one exists.

From that material alone, identify at most 8 topics: what this project is,
its current architecture or stack, decisions you can see evidence for (not
guesses), and open work you can point to a specific file or commit for.

Store each topic as one Palim memory or context checkpoint, whichever fits
the content. Do not invent decisions, priorities, or open items that are not
directly supported by what you read. If you find fewer than 8 well-supported
topics, store fewer — do not pad the count.

Seed my Palim Brain from this conversation.

Review our conversation so far in this chat only. Identify at most 5 topics:
concrete decisions we made, facts I stated about my project or preferences,
and open questions I raised. If this client keeps its own separate memory
and you can see entries there, you may use them as additional source
material, but say so.

Store each topic as one Palim memory or context checkpoint. Do not invent
anything we did not actually discuss, and do not store more than 5 topics
even if more seem plausible.

Run a short Palim seed interview with me. Ask exactly these five questions,
one at a time, and wait for my answer before asking the next:

1. What project or work are you currently focused on?
2. What is the most important decision you've made about it recently?
3. What tool, stack, or approach are you using, and why?
4. What is currently open or blocked?
5. Is there a standing preference or fact about how you like to work that I
   should remember?

After the fifth answer, store the results as Palim memories or a single
context checkpoint, whichever fits better. Do not add topics I did not
mention.

Search Palim for what I just seeded in [other client name]. Summarize what
you find without me repeating it, and tell me clearly if nothing turns up.

Palim is my persistent, cross-tool memory.

Use Palim before answering when I refer to earlier work, decisions, a named
project, a time period, or continuing a task. At the start of substantial project
work, load the Brain overview and ground claims about earlier work in retrieved
Palim data.

Use palim_search or palim_get_context for topics, palim_search_by_date_range for
time periods, and palim_get_session or palim_get_sessions only when complete found
chats are actually needed. Do not claim that Palim was used unless a Palim tool
returned successfully.

After substantial results, decisions, reliable findings, or changes of direction,
create a compact context checkpoint with palim_save_context. Reuse the same session
ID within the current chat. Store the full message transcript with
palim_save_session only when I explicitly request it or the complete transcript is
genuinely needed.

Store durable facts, preferences, or standing decisions as individual Palim
memories. Do not store trivial conversations, secrets, or content I excluded from
storage. If Palim finds nothing or is unavailable, say so clearly and never invent
prior context.

Continue Project Atlas. Before answering, retrieve the previous state, latest
decisions, and open items from Palim. Briefly identify which stored information
you are relying on.

What did we decide about the auth flow? Search Palim first. If multiple saved
states conflict, identify their dates and ask which one applies.

Summarize what happened in Project Atlas last week. Use Palim's date search and
separate decisions, results, and open items.

Capture the current state as a compact Palim context checkpoint. The summary must
include the goal, decisions, reliable findings, current state, open items, and the
next sensible step.

Save this complete chat to Palim as "Auth review July". Use the tags auth and
atlas and include a complete summary.

Remember this in Palim: Project Atlas uses PostgreSQL 15. Store it as one
project-specific memory, not as a complete session.

Find the Palim memory about the PostgreSQL version in Project Atlas. Change it
from 15 to 16, then show me the updated content.

Use this content only for the current answer. Do not store it as a Palim context
checkpoint, session, or memory.

Use Palim in this thread as my cross-tool memory: retrieve earlier work before
answering, create a compact context checkpoint after substantial results, and
never store secrets, trivial content, or information I explicitly exclude.

Palim Help

What decision did we make for palim-test-<date>, and what is the next step?

Process this synthetic note, but do not store this chat or its content in Palim:
palim-nosave-<date>.

---
name: palim-workflow
description: Use when a task continues earlier work, needs prior project decisions, creates a substantial result, or requires a handoff through Palim. Do not use for trivial exchanges or content excluded from storage.
---

# Palim workflow

1. Before answering continuity questions, retrieve Palim context.
   - Use `palim_get_brain` at the start of substantial project work.
   - Use `palim_search` or `palim_get_context` for a topic.
   - Use `palim_search_by_date_range` for a stated time period.
   - Load complete sessions only when the summary is insufficient.
2. Ground claims about earlier work in successful Palim results. If nothing is
   found, say so; never invent prior context.
3. After a substantial result, decision, reliable finding, or change of direction,
   call `palim_save_context` with a self-contained handoff. Reuse the session ID
   returned earlier in the same chat.
4. Use `palim_save_session` only when a complete transcript is explicitly useful
   or requested.
5. Store durable facts, preferences, and standing decisions with `palim_add_memory`.
6. Never store trivial exchanges, secrets, or content the user excluded from Palim.
7. Do not announce routine Palim calls unless the result affects the answer or the
   user asks for confirmation.