Skip to content

docs: expand dashboard check-in prompts #119

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Jammy2211 merged 1 commit into from
Oct 7, 2026
Merged

docs: expand dashboard check-in prompts #119

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
35 changes: 27 additions & 8 deletions scripts/board.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -754,14 +754,33 @@ def _repo_url(snapshot: dict) -> str:


CHECKIN_PROMPT = (
"Review the Memory knowledge board in this chat. Read PyAutoMemory/AGENTS.md, "
"its index and relevant domain indexes; then inspect the reading queue, digest "
"freshness, unresolved canonical keys and stub work. Read at most two or three "
"relevant pages after each index. Summarize priorities and propose one bounded "
"next step, retaining missing evidence as unknown. Apply my direction while "
"keeping the queue in view. Follow existing catch-up selection approval and "
"development workflow for writes; do not bulk-ingest papers, commit source "
"PDFs or post issues automatically."
"Use this chat as an ongoing place to work with PyAutoMemory: retrieve existing "
"knowledge, discuss papers and improve the knowledge base. Read PyAutoMemory/AGENTS.md, "
"its index and the relevant domain indexes. Start with a small selection of relevant "
"pages and expand as the question requires.\n\n"
"When I give no particular direction, review the reading queue, arXiv inbox and "
"interests, digest freshness, citation work, incomplete pages and filings awaiting merge. "
"Summarize what needs attention and suggest useful next steps, distinguishing new "
"material from work already processed.\n\n"
"When I supply a paper, topic, question or idea, make that the main focus. Help me find "
"prior knowledge, recall recorded decisions, understand a paper, compare methods or "
"identify gaps in existing coverage. Bring in related material where useful; do not "
"repeat the full queue review on every follow-up.\n\n"
"Ground answers in cited sources. Distinguish what a paper establishes, what our existing "
"notes say and any interpretation you offer. Make uncertainty and conflicting evidence "
"explicit. Discuss connections to our work without treating a published claim as "
"something we have independently verified.\n\n"
"Help me select what to read, work through a paper in depth, develop notes or plan "
"improvements to wiki pages and citations. Follow the existing reading, catch-up and "
"filing procedures. Agree the selection before bulk processing, and avoid duplicating "
"existing entries.\n\n"
"When I ask you to preserve knowledge, update the appropriate canonical pages, "
"bibliography or queue records through the repository’s workflow. Keep source attribution "
"and distinguish proposed ideas from accepted project decisions. Do not commit source "
"PDFs.\n\n"
"Carry clearly authorized work through its workflow, retaining approvals already given in "
"this conversation. After changes, report what was recorded, where it lives and what "
"remains to read or resolve."
)


Expand Down
Loading