manuscript-reframe

Name: manuscript-reframe
Author: yha9806

24stars3forks

How to install manuscript-reframe?

yha9806/academic-writing-toolkit/manuscript-reframe

$npx -y skills add yha9806/academic-writing-toolkit --skill manuscript-reframe

Installs into the current project.

Summary

Reframe academic manuscript drafts that read like engineering reports, module inventories, internal validation packets, or system notes into paper-form scientific arguments with clear gap, contribution chain, results narrative, figure/table roles, AI-assisted component boundaries

Files · 1

View on GitHub

SKILL.md

1	# /manuscript-reframe - Scientific Manuscript Reframing
2
3	## Purpose
4
5	Turn a technically valid but report-like manuscript into a scientific paper argument. Use this when a draft contains many modules, raw tables, internal artifact language, scattered figures, or exploratory AI/report-generation material but the scientific gap and contribution are not yet crisp.
6
7	## Trigger Words
8
9	This skill activates on: `manuscript reframe`, `paper form`, `too much like a report`, `gap and contribution`, `scientific framing`, `journal framing`, `submission clean`, `methods paper`, `/manuscript-reframe`.
10
11	## Core Rule
12
13	Write around the scientific problem, not the implementation inventory.
14
15	Before editing, force the draft into one sentence:
16
17	```text
18	This paper solves [specific reliability / evidence / workflow gap] between [upstream technical output] and [downstream scientific or operator-facing use].
19	```
20
21	If the sentence cannot be written, do not rewrite sections yet. First produce a gap-and-contribution diagnosis.
22
23	## Workflow
24
25	### 1. Locate The Current Draft And Evidence Anchors
26
27	Inspect manuscript sources, figures, tables, supplementary files, result summaries, reference files, and revision reports. Identify which artifacts are canonical and which are exploratory.
28
29	Create a short working note with:
30
31	- manuscript source path
32	- intended venue or article type
33	- canonical result artifacts
34	- exploratory-only artifacts
35	- forbidden or overclaim risks
36	- unresolved submission metadata
37
38	### 2. Diagnose The Paper Spine
39
40	Check whether the Introduction answers:
41
42	1. What do existing approaches output?
43	2. Why is that output insufficient for downstream use?
44	3. What gap does this paper evaluate or close?
45	4. What is the proposed interface, workflow, or method?
46	5. What evidence shows the gap and the method effect?
47
48	Prefer gap forms such as:
49
50	- Perception outputs are not automatically evidence objects.
51	- Segmentation metrics do not guarantee downstream task reliability.
52	- Uncertain perception should be routed rather than silently converted into support.
53	- Reports and interfaces need explicit claim boundaries.
54	- Machine-readable records must not imply execution permission unless validated for that role.
55
56	### 3. Rebuild Contributions As A Chain
57
58	Avoid module lists. Use a small contribution chain:
59
60	1. Problem formulation: define the reliability, evidence, or workflow gap.
61	2. Interface definition: convert raw outputs into structured evidence objects.
62	3. Bottleneck measurement: quantify where upstream metrics and downstream claims diverge.
63	4. Conservative routing: expose reliability-coverage trade-offs and review capture.
64	5. Bounded output: produce traceable reports or records without unsupported claims.
65
66	Every contribution should answer: what gap does this close, and what evidence supports it?
67
68	### 4. Rewrite Results As A Narrative Transition
69
70	Do not present Results as raw artifact counts. Use paragraphs that explain the transition:
71
72	- perception metric: what the frozen model or upstream system achieved
73	- direct conversion: what fails when outputs are treated as downstream evidence
74	- gate/routing effect: how selective support changes agreement and coverage
75	- failure taxonomy: which bottleneck dominates
76	- bounded output audit: whether reports or records stayed within evidence boundaries
77
78	Keep exact values in tables. In prose, translate audit-zero metrics into natural language when clearer:
79
80	```text
81	The audit detected no unsupported statements, contradictions, or prohibited action claims.
82	```
83
84	Do not write prose that sounds like a metric dump:
85
86	```text
87	unsupported rate 0.000, contradiction rate 0.000, prohibited rate 0.000
88	```
89
90	### 5. Explain Low Values Honestly
91
92	Low support, low coverage, or small denominators are not automatically failures. Identify what they mean:
93
94	- model evidence was missing
95	- geometry conversion failed
96	- the gate correctly withheld weak evidence
97	- the task is intentionally conservative
98	- the dataset has few evaluable cases
99
100	Use language such as:
101
102	```text
103	Low supported coverage indicates conservative evidence routing under the frozen gate, not a direct measure of segmentation accuracy.
104	```
105
106	### 6. Keep Generative Components In Their Proper Role
107
108	Do not let language-model or multimodal generative experiments steal the manuscript thesis unless they are the locked primary experiment.
109
110	Safe hierarchy:
111
112	- Primary result: deterministic, evidence-grounded, rule-based, or schema-validated workflow.
113	- Supplementary extension: frozen text-only or image-conditioned formatting tests.
114	- Future work: live domain reporting, open-ende

People who liked this also viewed

6 picks

Type

manuscript-reframe

24stars3forks

View on GitHub

How to install manuscript-reframe?

yha9806/academic-writing-toolkit/manuscript-reframe

$npx -y skills add yha9806/academic-writing-toolkit --skill manuscript-reframe

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# /manuscript-reframe - Scientific Manuscript Reframing
2
3	## Purpose
4
5	Turn a technically valid but report-like manuscript into a scientific paper argument. Use this when a draft contains many modules, raw tables, internal artifact language, scattered figures, or exploratory AI/report-generation material but the scientific gap and contribution are not yet crisp.
6
7	## Trigger Words
8
9	This skill activates on: `manuscript reframe`, `paper form`, `too much like a report`, `gap and contribution`, `scientific framing`, `journal framing`, `submission clean`, `methods paper`, `/manuscript-reframe`.
10
11	## Core Rule
12
13	Write around the scientific problem, not the implementation inventory.
14
15	Before editing, force the draft into one sentence:
16
17	```text
18	This paper solves [specific reliability / evidence / workflow gap] between [upstream technical output] and [downstream scientific or operator-facing use].
19	```
20
21	If the sentence cannot be written, do not rewrite sections yet. First produce a gap-and-contribution diagnosis.
22
23	## Workflow
24
25	### 1. Locate The Current Draft And Evidence Anchors
26
27	Inspect manuscript sources, figures, tables, supplementary files, result summaries, reference files, and revision reports. Identify which artifacts are canonical and which are exploratory.
28
29	Create a short working note with:
30
31	- manuscript source path
32	- intended venue or article type
33	- canonical result artifacts
34	- exploratory-only artifacts
35	- forbidden or overclaim risks
36	- unresolved submission metadata
37
38	### 2. Diagnose The Paper Spine
39
40	Check whether the Introduction answers:
41
42	1. What do existing approaches output?
43	2. Why is that output insufficient for downstream use?
44	3. What gap does this paper evaluate or close?
45	4. What is the proposed interface, workflow, or method?
46	5. What evidence shows the gap and the method effect?
47
48	Prefer gap forms such as:
49
50	- Perception outputs are not automatically evidence objects.
51	- Segmentation metrics do not guarantee downstream task reliability.
52	- Uncertain perception should be routed rather than silently converted into support.
53	- Reports and interfaces need explicit claim boundaries.
54	- Machine-readable records must not imply execution permission unless validated for that role.
55
56	### 3. Rebuild Contributions As A Chain
57
58	Avoid module lists. Use a small contribution chain:
59
60	1. Problem formulation: define the reliability, evidence, or workflow gap.
61	2. Interface definition: convert raw outputs into structured evidence objects.
62	3. Bottleneck measurement: quantify where upstream metrics and downstream claims diverge.
63	4. Conservative routing: expose reliability-coverage trade-offs and review capture.
64	5. Bounded output: produce traceable reports or records without unsupported claims.
65
66	Every contribution should answer: what gap does this close, and what evidence supports it?
67
68	### 4. Rewrite Results As A Narrative Transition
69
70	Do not present Results as raw artifact counts. Use paragraphs that explain the transition:
71
72	- perception metric: what the frozen model or upstream system achieved
73	- direct conversion: what fails when outputs are treated as downstream evidence
74	- gate/routing effect: how selective support changes agreement and coverage
75	- failure taxonomy: which bottleneck dominates
76	- bounded output audit: whether reports or records stayed within evidence boundaries
77
78	Keep exact values in tables. In prose, translate audit-zero metrics into natural language when clearer:
79
80	```text
81	The audit detected no unsupported statements, contradictions, or prohibited action claims.
82	```
83
84	Do not write prose that sounds like a metric dump:
85
86	```text
87	unsupported rate 0.000, contradiction rate 0.000, prohibited rate 0.000
88	```
89
90	### 5. Explain Low Values Honestly
91
92	Low support, low coverage, or small denominators are not automatically failures. Identify what they mean:
93
94	- model evidence was missing
95	- geometry conversion failed
96	- the gate correctly withheld weak evidence
97	- the task is intentionally conservative
98	- the dataset has few evaluable cases
99
100	Use language such as:
101
102	```text
103	Low supported coverage indicates conservative evidence routing under the frozen gate, not a direct measure of segmentation accuracy.
104	```
105
106	### 6. Keep Generative Components In Their Proper Role
107
108	Do not let language-model or multimodal generative experiments steal the manuscript thesis unless they are the locked primary experiment.
109
110	Safe hierarchy:
111
112	- Primary result: deterministic, evidence-grounded, rule-based, or schema-validated workflow.
113	- Supplementary extension: frozen text-only or image-conditioned formatting tests.
114	- Future work: live domain reporting, open-ende

People who liked this also viewed

6 picks

Type