# Credo Paper Plan > Plan a research paper before any prose is written: the one idea, the reader and what they believe now, the best-case conclusion, the introduction's story arc, a figure storyboard, and why each section sits where it does; then critique a draft against that plan. Use when the user is about to write a paper or section, or has a draft that reads as two papers. The agent plans and critiques; the author drafts. NOT for line editing, submission checks (credo-release), or short reports and tickets. - Skill: `gigio1023/credo-paper-plan` (Agent Skill) - Install (CLI): `npx skillmds@latest add gigio1023/credo-paper-plan` - Raw SKILL.md: https://api.skillmd.com/api/skills/gigio1023/credo-paper-plan/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: AI & ML - Author: gigio1023 (https://skillmd.com/u/gigio1023) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/gigio1023/credo-paper-plan --- # Paper Plan Outcome: a written plan the author can draft from, and, when a draft exists, a critique of the draft against that plan. Writing is not sequential; deciding what goes where, for whom, and why is the work. The agent does that work with the author and leaves the sentences to them unless asked otherwise. Scope: long-horizon work only (an uncertain claim or direction, a quarter or longer or a multi-month improvement the user owns, no deadline inside the next few weeks). A short report or a deliverable due this month is not planned here; say so and stop. Adapted from the writing sections of Carlini's essay. The episodes referred to below are in the credo-taste package, file episodes.md under its references; read one only when you cite it. ## Build the plan Ask in this order, one at a time, and write the plan as answers arrive. 1. The one idea, in one sentence. An "and" means two papers; settle which one before continuing. If two attempts do not produce one sentence, stop the plan and say the project needs the credo-taste gate first. 2. The reader. Default: the author six months ago. What did that person believe? What would they have needed to hear to think this idea was worth pursuing? If the paper argues against a community's belief, the reader is one member of that community, and the claim may need to arrive last (see episode E8 in the credo-taste references). 3. The best-case conclusion. What does the reader take away beyond the results? If it restates the abstract, the plan is not done. 4. The introduction as a story. Where does the reader stand in paragraph one? How far is the journey to the setting where the idea makes sense: one sentence, a paragraph, or two pages? Two pages is the ceiling. 5. The figure storyboard. Which figure shows the problem, which the method, which the results? Each must carry a one-sentence takeaway in its caption and be understood without the text. 6. Section order with reasons. For each section, one line: what it does for this reader and why it sits here. Background exists to widen who "the reader" is; after it, assume they know what it taught. 7. Abstract shape. Topic, problem, result or method, the one not yet covered, why it matters; or claim, evidence, impact for a broad topic or narrow audience. It will contain at least one specific number and no hedge the evidence does not require. Write the plan as a short document with those seven parts. Stop there unless the author asks for prose. ## Critique a draft against the plan When a draft exists, read it only against the plan: does each section do what the plan says, for the stated reader? Report mismatches as questions, not rewrites. Check the fixed points: one idea, reader met in paragraph one, introduction within two pages, captions standalone, conclusion answers "so what", abstract has a number and no unearned hedge. Do not change claims, numbers, or the scope the evidence supports. Suggest the author read the draft aloud or through text-to-speech and mark what does not land. ## Output The seven-part plan, then, when a draft exists, the list of mismatches as questions. Nothing else.