메뉴
Import Paperpile JSON export into bip library, rebuild database, and clean up.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Check remote server CPU, memory, and GPU availability via SSH
Cold-start into a worktree/clone from a fresh conversation — read the PR, issue, and any status files, figure out where things stand, then STOP and ask the user what to do next. Use for a fresh conversation dropped into a bip-spawn or bip-epic-spawn worktree/clone that already has history (a PR, an in-progress phase, or a stalled worker).
Quick poll of tracked EPICs and code repos for new manuscript-relevant results
Persist manuscript session state before context reset
Cold-start for a manuscript session — the paper is the source of truth and shared context; discuss results, orchestrate research through issues/PRs, and update the paper as threads complete
Spawn a Claude session in a clone for an EPIC issue
| name | bip-lit-import |
| description | Import Paperpile JSON export into bip library, rebuild database, and clean up. |
Import a Paperpile JSON export from ~/Downloads/ into the bip reference library.
/bip-lit-import # Auto-detect latest Paperpile JSON in ~/Downloads
/bip-lit-import ~/path.json # Explicit file path
If no path argument given, look for ~/Downloads/Paperpile*.json or ~/Downloads/*.json:
ls -lt ~/Downloads/Paperpile*.json 2>/dev/null || ls -lt ~/Downloads/*.json
If multiple files match, ask the user which one.
Always dry-run first to show what will change:
bip import --format paperpile "<file>" --dry-run --human
Report the counts (new, updated, skipped, warnings) to the user. By default, entries missing required fields (title, author, published.year) are imported with sentinel placeholders ([no title], Unknown, year 0) and listed under warnings so they're not silently dropped — review the warning list and fix the affected Paperpile records when convenient. Entries with no useful metadata at all (no title, author, year, or DOI — typically Paperpile auto-stubs for unparsed web pages) are still skipped and counted under skipped. Pass --strict to revert to the old behavior of dropping any entry with a missing required field.
bip import --format paperpile "<file>" --human
bip rebuild --human
rm "<file>"
Summarize: new refs added, total count, file deleted. Notes from Paperpile are preserved and searchable via bip search.
If the import reported a non-zero warnings count, recommend the cleanup query so the user can fix the upstream Paperpile records when convenient:
bip search --tag paperpile:incomplete
Every reference imported with a sentinel field ([no title], Unknown, year 0) is auto-tagged paperpile:incomplete. Once the user fixes the entry in Paperpile and re-imports, the next import replaces the stored reference and the tag disappears automatically, so the list shrinks until empty without any manual untagging step.