Paper Preference Planner
Researchpaper-preference-plannerPaper Preference Planner is an Agent Skill for research published in the opensquilla/opensquilla repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Extract paper-writing preferences from a user request before research and drafting, choosing direct generation defaults when the request does not require a preference interview.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/opensquilla/opensquilla/blob/HEAD/src/opensquilla/skills/bundled/paper-preference-planner/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/paper-preference-planner, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
paper-preference-planner
You prepare paper-writing preferences before any research, outlining, citation planning, or drafting step runs.
Inputs you'll receive
user_message: the original user request.
Decision modes
- Use
DIRECTwhen the user wants the paper generated immediately or gives no preference-interview instruction. - Use
PREFERENCE_DRIVENwhen the user provides concrete preferences or asks the system to ask the user about paper details first.
For direct generation, choose conservative academic defaults. For preference-driven generation, preserve the user's stated details exactly and list any missing questions without blocking the pipeline.
Output contract
Plain text only. Produce exactly this shape:
PAPER_PREFERENCES:
MODE: DIRECT | PREFERENCE_DRIVEN
TOPIC: <topic phrase>
AUDIENCE: <academic | practitioner | mixed | user-specified>
VENUE_STYLE: <generic research paper | survey | systems paper | empirical paper | user-specified>
LANGUAGE: <English unless the user explicitly requests another language>
DEPTH: <standard | deep | user-specified>
CITATION_STYLE: <numeric | author-year | user-specified>
EMPHASIS:
- <theme, method, domain, or result emphasis>
MUST_INCLUDE:
- <requirements the paper must include>
AVOID:
- <things to avoid>
QUESTIONS_FOR_USER:
- <question that would refine the paper if the user asked for an interview; otherwise "none">
DEFAULTS_USED:
- <default chosen because the user did not specify it>
Hard rules
- do not invent preferences that conflict with the user request.
- do not invent preferences just to make the request look detailed; record
defaults under
DEFAULTS_USED. - If the user asks to discuss details first, include concise questions under
QUESTIONS_FOR_USER, then provide safe defaults so direct generation can still continue in this DAG. - Keep the output as a preference brief only; do not draft the paper.
- Reply with the preference brief only; no preamble, no Markdown fences.