메뉴
Structured literature review workflow. Use when the user asks to "do a lit review", "review this paper", "triage these papers", "compare papers", or mentions arXiv, research papers, or academic literature.
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
Manage a bookmark research pipeline — fetch new bookmarks, triage against research interests, spawn parallel deep-dive agents, and review results. Use when the user says "bookmark sync", "check bookmarks", "review bookmarks", "triage bookmarks", "deep dive bookmarks", "run bookmark pipeline", or asks about setting up the bookmark system.
Update project context files when reality has drifted from docs. Use when a milestone is hit, the plan has changed, CLAUDE.md feels stale, or the user says "update the docs", "sync context", "evolve context". Walks through ledger, plan, CLAUDE.md, README, and architecture docs.
Create a new project with consistent structure and documentation. Use when the user says "new project" or "start a project" or when building something new. Sets up for agent-assisted development from day one.
Turn any question into an automated feedback loop. The pattern — design a sensor (eval), an actuator (code the agent modifies), and launch an evolutionary optimization loop. Works on any (code → run → score) problem — model training, software optimization, prompt tuning, eval design, data pipelines, agent harnesses. The eval function IS the research.
Mine session logs for skill usage patterns, corrections, and failures to propose improvements. Use when the user says "improve skills", "review skill usage", "what have we learned about our skills", or periodically to evolve skills based on real usage data.
Design and improve harnesses — the environments, constraints, feedback loops, and control systems that make AI agents do reliable work. Use when setting up a new project for agent-assisted development, diagnosing why agents are producing bad output, reviewing architectural constraints, or thinking about how to scale human oversight of agent workflows. Synthesizes OpenAI's harness engineering principles with cybernetic control theory.
| name | lit-review |
| description | Structured literature review workflow. Use when the user asks to "do a lit review", "review this paper", "triage these papers", "compare papers", or mentions arXiv, research papers, or academic literature. |
Structured capture of research papers for a knowledge base. Reviews enable conceptual reconstruction of studies and synthesis across the field.
Quick 2-3 sentence summary for go/no-go decisions. Use when screening multiple papers.
Format: Title, authors, venue -> what it claims -> why it might matter (or not).
Comprehensive structured capture. Default mode when asked to "review" or "do a lit review."
See references/review-template.md for full structure.
Pull scores across multiple reviews for synthesis. Use when asked to compare papers or do meta-analysis.
Generate comparison table from frontmatter fields, then narrative synthesis of patterns.
references/cybernetic-rubric.mdWeave quotable passages inline where they strengthen other sections.
Hybrid: YAML frontmatter (structured, queryable) + markdown prose (nuanced analysis).
---
title: "Paper Title"
authors: [Author One, Author Two]
venue: Conference/Journal Name
date: YYYY-MM-DD
arxiv: "XXXX.XXXXX"
paper_type: empirical | theoretical | system | survey | benchmark
tags: [tag1, tag2]
cybernetics:
feedback_loops: true | false | partial
learning_level: 0 | I | II | III
requisite_variety: true | false | partial
self_regulation: true | false | partial
human_in_loop: explicit | implicit | none
---
Empty — add failure modes here as they're discovered in real use.
references/review-template.md - Full review structure with section guidancereferences/cybernetic-rubric.md - Scoring rubric with analysis dimensionsexamples/saga-review.md - Complete review demonstrating the format