원클릭으로
bip-lit-extract
Extract paper references and concepts from a LaTeX repository for the bipartite knowledge graph.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Extract paper references and concepts from a LaTeX repository for the bipartite knowledge graph.
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-extract |
| description | Extract paper references and concepts from a LaTeX repository for the bipartite knowledge graph. |
Analyze a LaTeX repository to extract papers and concepts for the bipartite knowledge graph.
/bip-lit-extract <path-to-tex-repo>
main.bib and main.tex from the specified repositoryGiven a path like ../dasm-tex-1, perform this analysis:
cat <repo>/main.bib
Extract citation keys (the part after @article{ or @inproceedings{, etc.).
cat <repo>/main.tex
Look for:
\cite{...} commands and their surrounding contextLook for recurring themes that could become concept nodes:
Produce a structured summary:
{
"papers": [
{"id": "Smith2026-ab", "role": "foundational", "context": "Defines the X model"},
{"id": "Jones2025-xy", "role": "applies", "context": "Uses X for Y analysis"}
],
"suggested_concepts": [
{"id": "x-model", "name": "X Model", "description": "Statistical framework for..."},
{"id": "y-analysis", "name": "Y Analysis", "description": "Method for..."}
],
"suggested_edges": [
{"source": "Smith2026-ab", "target": "x-model", "type": "introduces", "summary": "Foundational paper"},
{"source": "Jones2025-xy", "target": "x-model", "type": "applies", "summary": "Application to Y"}
]
}
Skip these citation types:
Prioritize these:
After running this skill, use the output to update the knowledge graph:
# Check which papers exist in bip
bip get Smith2026-ab
# Create suggested concepts
bip concept add x-model --name "X Model" --description "..."
# Add edges
bip edge add -s Smith2026-ab -t x-model -r introduces -m "Foundational paper"
User: /bip-lit-extract ../dasm-tex-1
Claude: I'll analyze the LaTeX repository to extract references and concepts.
[Reads main.bib and main.tex]
Found 45 citations in main.bib. Here's my analysis:
**Key Papers** (12 identified as significant):
1. Halpern1998-yc - introduces mutation-selection model
2. Yaari2013-dg - introduces S5F targeting model
...
**Suggested Concepts** (4):
1. `mutation-selection-model` - Framework for codon substitution
2. `shm-targeting` - Somatic hypermutation targeting patterns
...
**Suggested Edges** (8):
- Halpern1998-yc --[introduces]--> mutation-selection-model
- Yaari2013-dg --[introduces]--> shm-targeting
...
Would you like me to:
1. Check which papers are already in your bip library?
2. Create these concepts and edges?