scientific-prose-style

Name: scientific-prose-style
Author: Boom5426

7installs28forks

How to install scientific-prose-style?

boom5426/nature-paper-skills/scientific-prose-style

$npx -y skills add Boom5426/Nature-Paper-Skills --skill scientific-prose-style

Installs into the current project.

Summary

Prose-quality rules for writing scientific manuscript text — abstract, introduction, results, discussion. The headline rule is a strict em-dash budget: the long dash (—) is overused and reads as a stylistic tic, so cap it and rewrite with commas, colons, parentheses, or a period.

Files · 1

View on GitHub

SKILL.md

1	# scientific-prose-style
2
3	Rules for the prose of a scientific paper — the sentences of the abstract,
4	introduction, results, and discussion. Load this whenever you draft or revise
5	manuscript text. (Figure planning lives in `figure-planner`; this skill
6	is about words on the page.)
7
8	## Rule 1 — Em-dash budget (the headline rule)
9
10	The long em-dash (`—`) is the single most overused mark in generated scientific
11	prose. It feels punchy in isolation but a reader hits three or four per paragraph
12	and it reads as a stylistic tic, not as writing. Cap it.
13
14	- At most one em-dash per paragraph, and none in the abstract. If a sentence
15	already has one, the next clause that wants a dash gets a different mark.
16	- *Never use a pair* of em-dashes to bracket an aside** if a comma pair or
17	parentheses would do — the double dash is the worst offender.
18	- Prefer, in rough order: comma (mild pause), colon (a list or an
19	expansion of what precedes), parentheses (a true aside the sentence reads
20	fine without), or split into two sentences (the strongest fix for a long
21	dash-spliced line).
22
23	### Substitution table
24
25	\| Em-dash use \| Replace with \| Example fix \|
26	\|---\|---\|---\|
27	\| Pause before a summary/payoff \| colon \| `...never been tested — this is our entry point.` → `...never been tested. This is our entry point.` \|
28	\| Bracketed aside (pair of dashes) \| commas or parentheses \| `no model — including ESM — beats chance` → `no model, including ESM, beats chance` \|
29	\| Appositive / renaming \| comma \| `allele-resolution prediction — telling apart variants` → `allele-resolution prediction, i.e. telling variants apart,` \|
30	\| Abrupt contrast \| period + connective, or "but" \| `real but sub-threshold — the effect vanishes` → `real but sub-threshold: the effect vanishes` \|
31	\| Range or span (this is fine) \| keep an en-dash `–`, not em \| `370–1000 cells` stays `370–1000` \|
32
33	### Before → after (from a real over-dashed abstract)
34
35	Before (5 em-dashes, tic-heavy):
36	> Starting from the hardest instance of the problem — allele-resolution
37	> prediction, distinguishing many coding variants of the same gene — we assemble
38	> a benchmark, and find this is a measurement limit, not a model limit — a
39	> split-half floor shows the distance is no larger than sampling noise.
40
41	After (0 em-dashes, same content):
42	> We start from the hardest instance of the problem: allele-resolution
43	> prediction, which distinguishes many coding variants of the same gene. On the
44	> benchmark we assemble, the ceiling turns out to be a measurement limit rather
45	> than a model limit. A split-half floor analysis shows the perturbation-versus-
46	> control distance is no larger than the sampling noise between two halves of a
47	> variant's own cells.
48
49	Note what the rewrite does: promotes one clause to its own sentence, turns the
50	bracketed aside into a relative clause, and swaps the contrast dash for "rather
51	than." The prose is calmer and each sentence carries one idea.
52
53	## Rule 2 — Don't trade the dash for a colon tic
54
55	Colons are the natural replacement, but the same overuse applies: at most one
56	colon per sentence, and if every sentence in a paragraph ends `...: <expansion>`
57	you've just moved the tic. Vary the repair — some become periods, some commas.
58
59	## Rule 3 — Hedge once, not thrice
60
61	Scientific prose stacks hedges (`may possibly suggest that ... could in principle
62	...`). State the claim with one qualifier and the confidence level, then stop.
63	`These results suggest X` — not `These results may tentatively be taken to
64	suggest that X could hold`.
65
66	## Rule 4 — Vary sentence length; one idea per sentence
67
68	A paragraph of uniformly long, clause-heavy sentences is as fatiguing as the
69	dash tic. Follow a long sentence with a short one. If a sentence has three
70	clauses joined by dashes, semicolons, and "and," it is three sentences.
71
72	## Rule 5 — Openers and connectives
73
74	- Don't open consecutive paragraphs with the same word (`We ... We ... We ...`).
75	- Prefer plain connectives (`but`, `so`, `because`, `here`) over heavy ones
76	(`moreover`, `furthermore`, `additionally`) unless enumerating.
77
78	## Self-check before you hand prose back
79
80	Run this on any abstract/intro/section you write:
81
82	1. Count em-dashes. More than one per paragraph, or any in the abstract →
83	rewrite the excess with the substitution table.
84	2. Count paragraph-opening words. Repeated opener → vary it.
85	3. Read the longest sentence aloud. If you run out of breath, split it.
86	4. En-dashes in numeric ranges (`5–

People who liked this also viewed

6 picks

Type

scientific-prose-style

7installs28forks

View on GitHub

How to install scientific-prose-style?

boom5426/nature-paper-skills/scientific-prose-style

$npx -y skills add Boom5426/Nature-Paper-Skills --skill scientific-prose-style

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# scientific-prose-style
2
3	Rules for the prose of a scientific paper — the sentences of the abstract,
4	introduction, results, and discussion. Load this whenever you draft or revise
5	manuscript text. (Figure planning lives in `figure-planner`; this skill
6	is about words on the page.)
7
8	## Rule 1 — Em-dash budget (the headline rule)
9
10	The long em-dash (`—`) is the single most overused mark in generated scientific
11	prose. It feels punchy in isolation but a reader hits three or four per paragraph
12	and it reads as a stylistic tic, not as writing. Cap it.
13
14	- At most one em-dash per paragraph, and none in the abstract. If a sentence
15	already has one, the next clause that wants a dash gets a different mark.
16	- *Never use a pair* of em-dashes to bracket an aside** if a comma pair or
17	parentheses would do — the double dash is the worst offender.
18	- Prefer, in rough order: comma (mild pause), colon (a list or an
19	expansion of what precedes), parentheses (a true aside the sentence reads
20	fine without), or split into two sentences (the strongest fix for a long
21	dash-spliced line).
22
23	### Substitution table
24
25	\| Em-dash use \| Replace with \| Example fix \|
26	\|---\|---\|---\|
27	\| Pause before a summary/payoff \| colon \| `...never been tested — this is our entry point.` → `...never been tested. This is our entry point.` \|
28	\| Bracketed aside (pair of dashes) \| commas or parentheses \| `no model — including ESM — beats chance` → `no model, including ESM, beats chance` \|
29	\| Appositive / renaming \| comma \| `allele-resolution prediction — telling apart variants` → `allele-resolution prediction, i.e. telling variants apart,` \|
30	\| Abrupt contrast \| period + connective, or "but" \| `real but sub-threshold — the effect vanishes` → `real but sub-threshold: the effect vanishes` \|
31	\| Range or span (this is fine) \| keep an en-dash `–`, not em \| `370–1000 cells` stays `370–1000` \|
32
33	### Before → after (from a real over-dashed abstract)
34
35	Before (5 em-dashes, tic-heavy):
36	> Starting from the hardest instance of the problem — allele-resolution
37	> prediction, distinguishing many coding variants of the same gene — we assemble
38	> a benchmark, and find this is a measurement limit, not a model limit — a
39	> split-half floor shows the distance is no larger than sampling noise.
40
41	After (0 em-dashes, same content):
42	> We start from the hardest instance of the problem: allele-resolution
43	> prediction, which distinguishes many coding variants of the same gene. On the
44	> benchmark we assemble, the ceiling turns out to be a measurement limit rather
45	> than a model limit. A split-half floor analysis shows the perturbation-versus-
46	> control distance is no larger than the sampling noise between two halves of a
47	> variant's own cells.
48
49	Note what the rewrite does: promotes one clause to its own sentence, turns the
50	bracketed aside into a relative clause, and swaps the contrast dash for "rather
51	than." The prose is calmer and each sentence carries one idea.
52
53	## Rule 2 — Don't trade the dash for a colon tic
54
55	Colons are the natural replacement, but the same overuse applies: at most one
56	colon per sentence, and if every sentence in a paragraph ends `...: <expansion>`
57	you've just moved the tic. Vary the repair — some become periods, some commas.
58
59	## Rule 3 — Hedge once, not thrice
60
61	Scientific prose stacks hedges (`may possibly suggest that ... could in principle
62	...`). State the claim with one qualifier and the confidence level, then stop.
63	`These results suggest X` — not `These results may tentatively be taken to
64	suggest that X could hold`.
65
66	## Rule 4 — Vary sentence length; one idea per sentence
67
68	A paragraph of uniformly long, clause-heavy sentences is as fatiguing as the
69	dash tic. Follow a long sentence with a short one. If a sentence has three
70	clauses joined by dashes, semicolons, and "and," it is three sentences.
71
72	## Rule 5 — Openers and connectives
73
74	- Don't open consecutive paragraphs with the same word (`We ... We ... We ...`).
75	- Prefer plain connectives (`but`, `so`, `because`, `here`) over heavy ones
76	(`moreover`, `furthermore`, `additionally`) unless enumerating.
77
78	## Self-check before you hand prose back
79
80	Run this on any abstract/intro/section you write:
81
82	1. Count em-dashes. More than one per paragraph, or any in the abstract →
83	rewrite the excess with the substitution table.
84	2. Count paragraph-opening words. Repeated opener → vary it.
85	3. Read the longest sentence aloud. If you run out of breath, split it.
86	4. En-dashes in numeric ranges (`5–

People who liked this also viewed

6 picks

Type