メニュー
Assesses citations in the paper draft against source papers in literature/. Runs as a background agent.
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
Identifies key references for the paper based on notebook summary and paper composition. Runs as a background agent.
Reshapes the paper draft to match the user's authentic prose style. Runs as a background agent.
Produces an independent critical review of the paper draft. Runs as a background agent.
Writes a full first draft of the paper based on the pipeline files. Runs as a background agent.
Interactive dialogue to define the paper's scholarly identity using the APFRQMC framework. Use when the user invokes /make-composition. Expects pipeline/notebook_summary.md to exist.
Interactive dialogue to work out the paper's argumentative structure. Use when the user invokes /make-structure. Expects pipeline files from steps 1 and 2 to exist.
| name | assess-citations |
| description | Assesses citations in the paper draft against source papers in literature/. Runs as a background agent. |
| context | fork |
| agent | citation-assessor |
| disable-model-invocation | true |
When invoked, ALWAYS use the Agent tool to run the agent: '/citation-assessor' Do NOT execute the agent's task inline.
The agent walks through every citation and placeholder in pipeline/paper_draft.md, checks each one against the source papers in literature/, and produces a structured report with proposed actions (KEEP / REVISE / REPLACE / REMOVE). The result is written to pipeline/citation_report.md.
Before proceeding: is there anything specific I should know — citations you're already aware are wrong, new papers you've added to literature/, or sections to prioritize? If not, just say go.
