papermill/skills/outline/SKILL.md
Design paper structure: generate a section-by-section outline with purpose, key content, estimated length, and narrative arc. Adapts to paper type and venue conventions. Updates .papermill/state.md.
npx skillsauth add queelius/claude-anvil outlineInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Help the researcher design the structure of their paper. A good outline is the skeleton that determines whether the paper's argument flows logically. Produce a section-by-section plan that is specific to this paper, not a generic template.
Read .papermill/state.md (Read tool) for:
latex, markdown, or rmarkdown (affects section conventions).If .papermill/state.md does not exist, outlining can still proceed — ask the user to describe the thesis and intended contribution type directly. Suggest running /papermill:init afterward to persist the outline.
Also scan existing paper files (Glob/Read tools). If there is already a partial draft, read it to understand what exists.
Different paper types have different conventional structures. Identify which applies:
Ask the user if you are unsure. The structure should match the contribution type.
For each section, specify:
| Field | Description | |-------|-------------| | Section title | The heading as it will appear in the paper | | Purpose | What this section accomplishes for the reader (1 sentence) | | Key content | Bullet points of what goes here (3-5 items) | | Estimated length | Approximate page/paragraph count | | Dependencies | What must be established before this section |
Example:
3. Preliminaries
Purpose: Establish notation and recall the key definitions the reader needs. Key content:
- Series system model (Definition 2.1)
- Masked failure time observation model
- Exponential lifetime assumption and its implications
- Notation table for symbols used throughout
Estimated length: 1.5 pages Dependencies: None (self-contained background)
After drafting the outline, verify the story:
Raise any structural issues with the user. Common problems:
Present the complete outline to the user. Ask:
Does this structure capture the argument you want to make? Would you reorder, merge, or split any sections?
Iterate until the user approves.
Once approved, update .papermill/state.md (Edit tool):
stage to outlining (or drafting if progressing).## Outline heading.Append a timestamped note documenting the outline creation.
Based on what the outline reveals, suggest the most relevant next step:
/papermill:thesis to refine the claim before drafting."/papermill:prior-art/papermill:experiment or /papermill:simulation/papermill:prooftools
This skill should be used when the user asks about research directions, open problems, future work, or follow-up research from the academic literature. Trigger phrases include "open problems in X", "what's next for Y", "future work for paper Z", "research directions on T", "salient follow-up research", "what should I work on next in", "find me follow-up research unrelated to my prior work", "broad survey of W", "neglected directions in V". Routes the request to the right Vista MCP tool, reads back the structured paper sections, and synthesizes research directions in the conversation.
testing
Discover latent themes in the metafunctor corpus. Use when the user wants to find implicit through-lines across their blog posts, surface recurring ideas they have not consciously framed as a series, or get candidate themes for a synthesis post. Reads titles, descriptions, and tags; proposes 3 themes that connect 4+ posts each, each with a single-sentence through-line. Output is a proposal, not a draft. Trigger phrases include "find themes in my posts", "what threads connect my writing", "latent themes in my corpus", "scribe".
development
Use when drafting prose sections for a bookwright (technical non-fiction) project. Encodes the Bernoulli-textbook workflow: atom-outward design, deferral discipline, running threads, page budgets, Path A subagent pattern, header comment block convention.
testing
Use when drafting or executing a paired notebook for a bookwright chapter. Covers when notebooks are required vs optional, numerical-sanity-target convention, exec-from-fresh-kernel requirement, and stack-specific execution commands (Jupyter/R Markdown/Quarto).