Menu
Assesses citations in the paper draft against source papers in literature/. Runs as a background agent.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| 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.
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.
