academic-paper

Name: academic-paper
Author: thtskaran

16stars2forks

How to install academic-paper?

thtskaran/claude-skills/academic-paper

$npx -y skills add thtskaran/claude-skills --skill academic-paper

Installs into the current project.

Summary

Write, format, and export professional academic research papers as publication-ready PDFs using reportlab. Use this skill whenever the user wants to write a research paper, preprint, white paper, literature review, position paper, or technical report — whether from scratch, from

Files · 1

View on GitHub

SKILL.md

1	# Academic Paper Skill
2
3	Generate publication-ready academic research papers as professionally formatted PDFs.
4	This skill covers the full pipeline: gathering inputs → writing/rewriting → figure creation
5	→ PDF formatting with reportlab → submission preparation for SSRN/arXiv.
6
7	---
8
9	## Workflow Decision Tree
10
11	When the user triggers this skill, figure out where they are:
12
13	```
14	User has... → Start at...
15	─────────────────────────────────────────────
16	A topic/idea only → Stage 1 (Gather) → full pipeline
17	Bullet points/notes → Stage 2 (Structure) → write → format
18	A markdown/text draft → Stage 3 (Write/Rewrite) → format
19	A finished draft → Stage 5 (Format as PDF)
20	A PDF, needs submission → Stage 6 (Submission Prep)
21	```
22
23	Always ask what they have and what they need. Don't assume full pipeline.
24
25	---
26
27	## Stage 1: Gather Inputs
28
29	Collect these before ANY writing:
30
31	Required:
32	- Author full name, email, affiliation (company name or "Independent Researcher" — both valid)
33	- Paper type: preprint, position paper, empirical study, literature synthesis, technical report
34	- Existing content: draft file, notes, or topic description
35	- Target venue: SSRN, arXiv, specific journal, or general
36
37	Ask about:
38	- Do they have citations/references already, or do we need to find them?
39	- Do they have figures/diagrams, or should we create them?
40	- Any page limits or formatting constraints from the venue?
41	- Any specific sections they want or don't want?
42
43	If user provides a markdown/text draft:
44	1. Read the entire draft before doing anything
45	2. Count all citations — you'll need to verify none get lost during rewriting
46	3. Map the section structure
47	4. Identify: What's the thesis? What evidence supports it? What's missing?
48
49	---
50
51	## Stage 2: Structure
52
53	### Standard Paper Architecture
54
55	```
56	Title + Abstract (≤300 words) + Keywords (8-12)
57	1. Introduction → Hook → Gap → Thesis → Contribution list
58	2. Background/Related → Only what the reader needs; argue, don't survey
59	3-5. Core sections → The actual contribution (varies by paper type)
60	6. Discussion → Implications, limitations, future work
61	7. Conclusion → Mirror intro, restate contributions concretely
62	References → Hanging indent, consistent format
63	Appendices (optional) → Supporting tables, proofs, supplementary data
64	```
65
66	### Before Writing, Map the Argument
67
68	Do this explicitly — it prevents structural drift:
69
70	- Thesis: One sentence. The paper's central claim.
71	- Evidence chain: What supports it? Arrange in logical order.
72	- Counterarguments: What would a skeptic say? Plan where to address.
73	- Novel contribution: What is genuinely NEW here?
74	- Reader: Who is reading this, and what do they already know?
75
76	---
77
78	## Stage 3: Write or Rewrite
79
80	### Writing Principles
81
82	1. Enter the reader's world first.
83	Open with what the audience already knows and cares about — a concrete scenario, a surprising
84	finding, a known problem. Then introduce your contribution. Never lead with your own framework.
85
86	2. Every section ARGUES, not just DESCRIBES.
87	Bad section heading: "Related Work." Good: "Three Independently Studied Phenomena That Interact
88	as a System." Each section should advance a claim, not just organize information.
89
90	3. Concrete before abstract.
91	Give a specific example or scenario, then generalize. The reader should visualize before you name.
92
93	4. Every data point gets a "so what" sentence.
94	Never drop a statistic bare. After every cited finding, one sentence interpreting what it means
95	for YOUR argument. Example: "Retrieval drops to 29.8% at 32K tokens (Modarressi et al., 2025).
96	A user asking 'remember what I said about feeling worthless?' is making exactly this kind of
97	semantic retrieval request — and the model is likely to fail."
98
99	5. Transitions advance the argument.
100	Kill "Additionally", "Furthermore", "Moreover" as paragraph openers. Each transition should
101	show logical progression: "This creates a problem that..." / "That finding has a direct
102	corollary..." / "The mechanism just des

People who liked this also viewed

6 picks

Type

academic-paper

16stars2forks

View on GitHub

How to install academic-paper?

thtskaran/claude-skills/academic-paper

$npx -y skills add thtskaran/claude-skills --skill academic-paper

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Academic Paper Skill
2
3	Generate publication-ready academic research papers as professionally formatted PDFs.
4	This skill covers the full pipeline: gathering inputs → writing/rewriting → figure creation
5	→ PDF formatting with reportlab → submission preparation for SSRN/arXiv.
6
7	---
8
9	## Workflow Decision Tree
10
11	When the user triggers this skill, figure out where they are:
12
13	```
14	User has... → Start at...
15	─────────────────────────────────────────────
16	A topic/idea only → Stage 1 (Gather) → full pipeline
17	Bullet points/notes → Stage 2 (Structure) → write → format
18	A markdown/text draft → Stage 3 (Write/Rewrite) → format
19	A finished draft → Stage 5 (Format as PDF)
20	A PDF, needs submission → Stage 6 (Submission Prep)
21	```
22
23	Always ask what they have and what they need. Don't assume full pipeline.
24
25	---
26
27	## Stage 1: Gather Inputs
28
29	Collect these before ANY writing:
30
31	Required:
32	- Author full name, email, affiliation (company name or "Independent Researcher" — both valid)
33	- Paper type: preprint, position paper, empirical study, literature synthesis, technical report
34	- Existing content: draft file, notes, or topic description
35	- Target venue: SSRN, arXiv, specific journal, or general
36
37	Ask about:
38	- Do they have citations/references already, or do we need to find them?
39	- Do they have figures/diagrams, or should we create them?
40	- Any page limits or formatting constraints from the venue?
41	- Any specific sections they want or don't want?
42
43	If user provides a markdown/text draft:
44	1. Read the entire draft before doing anything
45	2. Count all citations — you'll need to verify none get lost during rewriting
46	3. Map the section structure
47	4. Identify: What's the thesis? What evidence supports it? What's missing?
48
49	---
50
51	## Stage 2: Structure
52
53	### Standard Paper Architecture
54
55	```
56	Title + Abstract (≤300 words) + Keywords (8-12)
57	1. Introduction → Hook → Gap → Thesis → Contribution list
58	2. Background/Related → Only what the reader needs; argue, don't survey
59	3-5. Core sections → The actual contribution (varies by paper type)
60	6. Discussion → Implications, limitations, future work
61	7. Conclusion → Mirror intro, restate contributions concretely
62	References → Hanging indent, consistent format
63	Appendices (optional) → Supporting tables, proofs, supplementary data
64	```
65
66	### Before Writing, Map the Argument
67
68	Do this explicitly — it prevents structural drift:
69
70	- Thesis: One sentence. The paper's central claim.
71	- Evidence chain: What supports it? Arrange in logical order.
72	- Counterarguments: What would a skeptic say? Plan where to address.
73	- Novel contribution: What is genuinely NEW here?
74	- Reader: Who is reading this, and what do they already know?
75
76	---
77
78	## Stage 3: Write or Rewrite
79
80	### Writing Principles
81
82	1. Enter the reader's world first.
83	Open with what the audience already knows and cares about — a concrete scenario, a surprising
84	finding, a known problem. Then introduce your contribution. Never lead with your own framework.
85
86	2. Every section ARGUES, not just DESCRIBES.
87	Bad section heading: "Related Work." Good: "Three Independently Studied Phenomena That Interact
88	as a System." Each section should advance a claim, not just organize information.
89
90	3. Concrete before abstract.
91	Give a specific example or scenario, then generalize. The reader should visualize before you name.
92
93	4. Every data point gets a "so what" sentence.
94	Never drop a statistic bare. After every cited finding, one sentence interpreting what it means
95	for YOUR argument. Example: "Retrieval drops to 29.8% at 32K tokens (Modarressi et al., 2025).
96	A user asking 'remember what I said about feeling worthless?' is making exactly this kind of
97	semantic retrieval request — and the model is likely to fail."
98
99	5. Transitions advance the argument.
100	Kill "Additionally", "Furthermore", "Moreover" as paragraph openers. Each transition should
101	show logical progression: "This creates a problem that..." / "That finding has a direct
102	corollary..." / "The mechanism just des

People who liked this also viewed

6 picks

Type