메뉴
Two-layer memory system with grep-based recall for research sessions.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
Search HuggingFace Hub for datasets by keyword. Use when the user wants to find training data, benchmarks, or evaluation datasets for ML/NLP/CV research.
Fetch the FULL TEXT of an arXiv paper (all sections — introduction, method, results, conclusion). Use when you need to read beyond the abstract into the paper's actual content. Only works for arXiv papers. For metadata/abstract only, use paper-read. For local PDFs, use paper-read-pdf.
Track specific scientific claims across the literature over time — who made it, who replicated it, who challenged it, whether it still stands. Use when verifying a key assumption before building on it, or when checking whether a published result has been updated or superseded.
Scan papers for conflicting empirical claims, methodological disagreements, or opposing conclusions on the same topic. Use when writing discussion sections, evaluating conflicting results, or checking if a claim is contested before building on it.
Synthesize findings across multiple papers into a coherent narrative, structured comparison table, or temporal evolution. Use after collecting papers via survey or paper-search. Goes beyond summarizing individual papers to produce insights that only emerge when reading across the corpus as a whole.
Full end-to-end deep research pipeline on a topic. Use when the user wants thorough, rigorous research — not just a survey. Orchestrates all research skills in sequence: collect → synthesize → critique claims → grade evidence → find gaps → assess reproducibility → optionally reproduce → write report.
SOC 직업 분류 기준
| name | memory |
| description | Two-layer memory system with grep-based recall for research sessions. |
| always | true |
memory/MEMORY.md — Long-term research facts (papers, gaps, decisions, preferences). Always loaded into your context.memory/HISTORY.md — Append-only research log. NOT loaded into context. Search it with grep or exec tool. Each entry starts with [YYYY-MM-DD HH:MM].memory/HISTORY.md: use read_file, then search in-memoryexec tool for targeted searchExamples:
findstr /i "transformer" memory\HISTORY.md (Windows)grep -i "transformer" memory/HISTORY.md (Linux/macOS)python -c "from pathlib import Path; text = Path('memory/HISTORY.md').read_text(encoding='utf-8'); print('\n'.join([l for l in text.splitlines() if 'transformer' in l.lower()][-20:]))"Write important research facts immediately using write_file or edit_file:
Old conversations are automatically summarized and appended to HISTORY.md when the context grows large. Long-term facts are extracted to MEMORY.md.