Skip to content

angushushu/shu-academic-writing-skill / core/polish-prose

polish-prose

Verified

Diagnose why prose is hard to read at the sentence and paragraph level, using Joseph Williams's principles — characters as subjects, old before new, the stress position, topic strings, nominalization, hedging, and passive voice used fairly. Use when someone wants writing tightened, clarified, or line-edited, or asks why a passage feels dense, clunky, wordy, stiff, bureaucratic, or hard to follow — methods sections, technical documentation, reports, memos, cover letters, grant prose, and emails, not only academic papers. Also use when someone asks how to cut length without losing content or how to make an already-sound argument easier to read. Default behavior is naming patterns with quoted evidence and drills, not rewriting. If the draft's argument or contribution is what is actually in question, `core/engineer-argument/SKILL.md` handles that layer first.

FileKindSize
SKILL.mdskill md11.8 KB
references/drills.mdmarkdown4.8 KB
references/sentence-craft.mdmarkdown9.5 KB
references/style-guide.mdmarkdown2.7 KB

references/style-guide.md

View on GitHub
# Scientific prose style guide

## Priority order

Accuracy > inferential calibration > clarity > concision > elegance.

Never sacrifice a necessary boundary or qualifier merely to shorten a sentence.

## Sentence principles

- Put the main actor near the subject and the main action in the verb.
- Prefer `we analyzed` to `an analysis was conducted`, unless actorless phrasing serves a real purpose.
- Keep old/contextual information before new/emphatic information when possible.
- Keep subject and verb close; move long conditions after the main clause or into a preceding sentence.
- Use one main claim per sentence. A sentence may be long when its logical structure remains visible.
- Make pronoun referents explicit, especially `this`, `it`, `they`, and `which`.
- Use parallel grammar for parallel concepts.

## Paragraph principles

- One paragraph, one argumentative function.
- First sentence: orient or claim; middle: evidence/reasoning; final sentence: consequence or transition.
- Avoid citation-led paragraphs and strings of study summaries.
- Delete sentences that only announce obvious structure (`It is important to note that...`).

## Concision replacements

| Avoid when unnecessary | Prefer |
|---|---|
| utilize | use |
| in order to | to |
| due to the fact that | because |
| a number of | several / give the number |
| has the ability to | can |
| it is worth noting that | delete; state the point |
| the present study | this study / we |
| conducted an examination of | examined |
| provides evidence demonstrating | shows / provides evidence that |
| plays a crucial role | specify the relation |
| novel / innovative / groundbreaking | state what is new and useful |
| robust | name the robustness test or delete |

## Calibration ladder

Strongest claims require the strongest design.

`causes` > `changes` > `predicts` > `is associated with` > `is consistent with` > `suggests`.

Do not use a weaker-looking hedge to disguise an unsupported claim. Fix the proposition itself.

## Numbers and statistics

- Preserve signs, decimals, denominators, units, labels, and uncertainty.
- Use participant `N` for people and describe repeated rows as observations.
- Pair effect sizes with confidence/credible intervals when available.
- Use exact `p` values above .001 and `p < .001` below .001 under current journal guidance.
- Avoid `trend toward significance`, `marginally significant`, and binary supported/unsupported language when estimates and uncertainty tell a clearer story.

## Accessibility

- Define necessary technical terms once in plain language.
- Prefer a short concrete example over a second abstract definition.
- Keep standard field terms when substitution would reduce precision.
- Do not vary terms for stylistic variety when they denote the same construct.

rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 198kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 198kUpdated Claude CodeCodexVerifiedInstall