ワンクリックで
phira-paper-summary-pipeline
How Phira roles collaborate to summarise papers and archive outcomes.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
How Phira roles collaborate to summarise papers and archive outcomes.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Deterministic Graphviz/DOT derivation + validation for archive records.
Canonical per-record archive format (YAML front matter + Markdown body).
Pointer semantics for "since last record" and detected-change bookkeeping.
Checklist for proving baseline behavior is unchanged (or changes are intentional) via controlled A/B runs.
Fast, compute-aware verification checklist for implementation changes (imports, configs, tiny runs).
Workflow for conference/venue paper search and short reading lists.
| name | phira-paper-summary-pipeline |
| description | How Phira roles collaborate to summarise papers and archive outcomes. |
Use this skill when the user asks to summarise one or more research papers.
You MUST load and follow the summarise-paper skill.
phira orchestrates and does the heavy lifting (PDF->images, arXiv source download/unpack).phira-hypothesizer drafts the main note content (faithful, cited, math-aware) but does not write files.phira-reviewer-2 is used both:
phira into files directly.phira-archivist produces a concise bookkeeping record.note/<paper_slug>/main.texpaper_slug should be stable and ASCII:
arxiv-<id> for arXiv papers (e.g. arxiv-2601.07372)authorYYYY-short-title.cache/<paper_slug>/[1..N].png..cache/downloads/<paper_slug>/, unpack into .cache/<paper_slug>/, locate entry tex file.note/<paper_slug>/main.tex.summarise-paper skill structure).phira for onward routing.Stage A (parallel limitations package):
phira as a standalone limitations section.Stage B (gate audit):
phira.phira-archive-dagphira-archive-formatphira-archive-pointersnote/<paper_slug>/main.tex)