Evidence-Bound Section Drafting
Use only after triage, outline, and evidence boundaries exist (see
../workflow/SKILL.md and
../SKILL.md).
Drafting Rules
- Write
draft/paper.md as the content source of truth.
- Keep each core claim within
claim_evidence_map.md.
- Use
missing evidence to ask for material, downgrade, or remove claims.
- Do not invent data, citations, mechanisms, reviewer changes, or availability
statements.
- For major rewrites, shape from raw material to candidate openings to
paragraph-by-paragraph structure before polishing.
Section Roles (quick reference)
| Section |
Role |
Quality gate |
| Title |
searchable, precise, not inflated |
no vague clever title |
| Abstract |
problem, gap, method, key result, meaning |
no result-free impact claim |
| Introduction |
known → gap → insufficiency → approach → contribution |
gap and contribution align |
| Related work |
themed positioning |
not chronological paper dump |
| Methods |
reproducible protocol |
data/software/parameters/statistics clear |
| Results |
question → method → observation → quantitative result → interpretation |
each result points to figure/table/data |
| Discussion |
finding, relation to literature, mechanism, limits, future |
no new data |
| Limitations |
honest boundary and risk |
no hidden fatal flaw |
| Conclusion |
contribution and boundary |
not abstract repetition |
Section-Specific Skills
Read the corresponding skill file before drafting each section.
| Section |
File |
Focus |
| Abstract |
abstract.md |
Three proven templates (Challenge→Contribution, Challenge→Insight→Contribution, Multiple Contributions); 150–250 words; no citations |
| Introduction |
introduction.md |
Logic Map: Task → Challenge → Solution → Advantage; backward writing |
| Methods |
method.md |
Reproducibility checklist: software versions, parameters, hardware, data/code statements |
| Results |
results.md |
Each subsection ≥1 figure/table reference; claim → evidence; present tense |
| Discussion |
discussion.md |
Four-part structure: Interpretation → Comparison → Limitations → Future |
| Response Letter |
response_letter.md |
Reviewer-comment-to-response unit format |
Quality Protocols
| Skill |
File |
Purpose |
| Claim-Evidence Check |
claim_evidence_check.md |
Verify every major claim has supporting evidence; target ≥80% |
| Reviewer Rubric (NeurIPS-style) |
reviewer_rubric.md |
6-dimension peer-review simulation with worked example |
Usage
- Before writing a section, read the corresponding section skill file.
- Apply the templates and structural guidelines.
- After the full draft is complete, run claim_evidence_check.md.
- If alignment < 80%, revise claims (add evidence, downgrade, or remove) and
re-run.
- For submissions, grants, or revision responses, optionally simulate peer
review using reviewer_rubric.md.
Quality Standards
- Clarity: clear, concise, unambiguous language
- Evidence: every claim backed by citation, data, or figure
- Structure: logical flow and organization
- Reproducibility: sufficient detail for replication
- Impact: clear contribution and boundary
Sources: Research-Paper-Writing-Skills (Master-cai, MIT), AI-Scientist
(SakanaAI, MIT), ResearAI writer.md, K-Dense scientific-writing/SKILL.md,
mattpocock writing-shape/SKILL.md.
1---2name: evidence-bound-section-drafting3description: Section-level writing skill for evidence-bound academic prose: IMRaD papers, grants, reports, talks, and response letters. Indexes section-specific templates (abstract, introduction, method, results, discussion) and pre-submission quality protocols (claim-evidence, reviewer rubric, response letter).4---5
6# Evidence-Bound Section Drafting
7
8Use only after triage, outline, and evidence boundaries exist (see
9[../workflow/SKILL.md](../workflow/SKILL.md) and
10[../SKILL.md](../SKILL.md)).
11
12## Drafting Rules
13
14- Write `draft/paper.md` as the content source of truth.
15- Keep each core claim within `claim_evidence_map.md`.
16- Use `missing` evidence to ask for material, downgrade, or remove claims.
17- Do not invent data, citations, mechanisms, reviewer changes, or availability
18 statements.
19- For major rewrites, shape from raw material to candidate openings to
20 paragraph-by-paragraph structure before polishing.
21
22## Section Roles (quick reference)
23
24| Section | Role | Quality gate |
25|---|---|---|
26| Title | searchable, precise, not inflated | no vague clever title |
27| Abstract | problem, gap, method, key result, meaning | no result-free impact claim |
28| Introduction | known → gap → insufficiency → approach → contribution | gap and contribution align |
29| Related work | themed positioning | not chronological paper dump |
30| Methods | reproducible protocol | data/software/parameters/statistics clear |
31| Results | question → method → observation → quantitative result → interpretation | each result points to figure/table/data |
32| Discussion | finding, relation to literature, mechanism, limits, future | no new data |
33| Limitations | honest boundary and risk | no hidden fatal flaw |
34| Conclusion | contribution and boundary | not abstract repetition |
35
36## Section-Specific Skills
37
38Read the corresponding skill file before drafting each section.
39
40| Section | File | Focus |
41|---|---|---|
42| Abstract | [abstract.md](./abstract.md) | Three proven templates (Challenge→Contribution, Challenge→Insight→Contribution, Multiple Contributions); 150–250 words; no citations |
43| Introduction | [introduction.md](./introduction.md) | Logic Map: Task → Challenge → Solution → Advantage; backward writing |
44| Methods | [method.md](./method.md) | Reproducibility checklist: software versions, parameters, hardware, data/code statements |
45| Results | [results.md](./results.md) | Each subsection ≥1 figure/table reference; claim → evidence; present tense |
46| Discussion | [discussion.md](./discussion.md) | Four-part structure: Interpretation → Comparison → Limitations → Future |
47| Response Letter | [response_letter.md](./response_letter.md) | Reviewer-comment-to-response unit format |
48
49## Quality Protocols
50
51| Skill | File | Purpose |
52|---|---|---|
53| Claim-Evidence Check | [claim_evidence_check.md](./claim_evidence_check.md) | Verify every major claim has supporting evidence; target ≥80% |
54| Reviewer Rubric (NeurIPS-style) | [reviewer_rubric.md](./reviewer_rubric.md) | 6-dimension peer-review simulation with worked example |
55
56## Usage
57
581. Before writing a section, read the corresponding section skill file.
592. Apply the templates and structural guidelines.
603. After the full draft is complete, run [claim_evidence_check.md](./claim_evidence_check.md).
614. If alignment < 80%, revise claims (add evidence, downgrade, or remove) and
62 re-run.
635. For submissions, grants, or revision responses, optionally simulate peer
64 review using [reviewer_rubric.md](./reviewer_rubric.md).
65
66## Quality Standards
67
68- **Clarity**: clear, concise, unambiguous language
69- **Evidence**: every claim backed by citation, data, or figure
70- **Structure**: logical flow and organization
71- **Reproducibility**: sufficient detail for replication
72- **Impact**: clear contribution and boundary
73
74Sources: Research-Paper-Writing-Skills (Master-cai, MIT), AI-Scientist
75(SakanaAI, MIT), ResearAI writer.md, K-Dense scientific-writing/SKILL.md,
76mattpocock writing-shape/SKILL.md.
gabrielmoreira