research-paper-writing

Name: research-paper-writing
Author: adityahimaone

72stars5forks

How to install research-paper-writing?

adityahimaone/hermes-agent-rtk-caveman/research-paper-writing

$npx -y skills add adityahimaone/hermes-agent-rtk-caveman --skill research-paper-writing

Installs into the current project.

Summary

End-to-end pipeline for writing ML/AI research papers — from experiment design through analysis, drafting, revision, and submission. Covers NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Integrates automated experiment monitoring, statistical analysis, iterative writing, and citation veri

Files · 1

View on GitHub

SKILL.md

1	# Research Paper Writing Pipeline
2
3	End-to-end pipeline for producing publication-ready ML/AI research papers targeting NeurIPS, ICML, ICLR, ACL, AAAI, and COLM. This skill covers the full research lifecycle: experiment design, execution, monitoring, analysis, paper writing, review, revision, and submission.
4
5	This is not a linear pipeline — it is an iterative loop. Results trigger new experiments. Reviews trigger new analysis. The agent must handle these feedback loops.
6
7	```
8	┌─────────────────────────────────────────────────────────────┐
9	│ RESEARCH PAPER PIPELINE │
10	│ │
11	│ Phase 0: Project Setup ──► Phase 1: Literature Review │
12	│ │ │ │
13	│ ▼ ▼ │
14	│ Phase 2: Experiment Phase 5: Paper Drafting ◄──┐ │
15	│ Design │ │ │
16	│ │ ▼ │ │
17	│ ▼ Phase 6: Self-Review │ │
18	│ Phase 3: Execution & & Revision ──────────┘ │
19	│ Monitoring │ │
20	│ │ ▼ │
21	│ ▼ Phase 7: Submission │
22	│ Phase 4: Analysis ─────► (feeds back to Phase 2 or 5) │
23	│ │
24	└─────────────────────────────────────────────────────────────┘
25	```
26
27	---
28
29	## When To Use This Skill
30
31	Use this skill when:
32	- Starting a new research paper from an existing codebase or idea
33	- Designing and running experiments to support paper claims
34	- Writing or revising any section of a research paper
35	- Preparing for submission to a specific conference or workshop
36	- Responding to reviews with additional experiments or revisions
37	- Converting a paper between conference formats
38	- Writing non-empirical papers — theory, survey, benchmark, or position papers (see [Paper Types Beyond Empirical ML](#paper-types-beyond-empirical-ml))
39	- Designing human evaluations for NLP, HCI, or alignment research
40	- Preparing post-acceptance deliverables — posters, talks, code releases
41
42	## Core Philosophy
43
44	1. Be proactive. Deliver complete drafts, not questions. Scientists are busy — produce something concrete they can react to, then iterate.
45	2. Never hallucinate citations. AI-generated citations have ~40% error rate. Always fetch programmatically. Mark unverifiable citations as `[CITATION NEEDED]`.
46	3. Paper is a story, not a collection of experiments. Every paper needs one clear contribution stated in a single sentence. If you can't do that, the paper isn't ready.
47	4. Experiments serve claims. Every experiment must explicitly state which claim it supports. Never run experiments that don't connect to the paper's narrative.
48	5. Commit early, commit often. Every completed experiment batch, every paper draft update — commit with descriptive messages. Git log is the experiment history.
49
50	### Proactivity and Collaboration
51
52	Default: Be proactive. Draft first, ask with the draft.
53
54	\| Confidence Level \| Action \|
55	\|-----------------\|--------\|
56	\| High (clear repo, obvious contribution) \| Write full draft, deliver, iterate on feedback \|
57	\| Medium (some ambiguity) \| Write draft with flagged uncertainties, continue \|
58	\| Low (major unknowns) \| Ask 1-2 targeted questions via `clarify`, then draft \|
59
60	\| Section \| Draft Autonomously? \| Flag With Draft \|
61	\|---------\|-------------------\|-----------------\|
62	\| Abstract \| Yes \| "Framed contribution as X — adjust if needed" \|
63	\| Introduction \| Yes \| "Emphasized problem Y — correct if wrong" \|
64	\| Methods \| Yes \| "Included details A, B, C — add missing pieces" \|
65	\| Experiments \| Yes \| "Highlighted results 1, 2, 3 — reorder if needed" \|
66	\| Related Work \| Yes \| "Cited papers X, Y, Z — add any I missed" \|
67
68	Block for input only when: target venue unclear, multiple contradictory framings, results seem incomplete, explicit reque

People who liked this also viewed

6 picks

Type

research-paper-writing

72stars5forks

View on GitHub

How to install research-paper-writing?

adityahimaone/hermes-agent-rtk-caveman/research-paper-writing

$npx -y skills add adityahimaone/hermes-agent-rtk-caveman --skill research-paper-writing

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Research Paper Writing Pipeline
2
3	End-to-end pipeline for producing publication-ready ML/AI research papers targeting NeurIPS, ICML, ICLR, ACL, AAAI, and COLM. This skill covers the full research lifecycle: experiment design, execution, monitoring, analysis, paper writing, review, revision, and submission.
4
5	This is not a linear pipeline — it is an iterative loop. Results trigger new experiments. Reviews trigger new analysis. The agent must handle these feedback loops.
6
7	```
8	┌─────────────────────────────────────────────────────────────┐
9	│ RESEARCH PAPER PIPELINE │
10	│ │
11	│ Phase 0: Project Setup ──► Phase 1: Literature Review │
12	│ │ │ │
13	│ ▼ ▼ │
14	│ Phase 2: Experiment Phase 5: Paper Drafting ◄──┐ │
15	│ Design │ │ │
16	│ │ ▼ │ │
17	│ ▼ Phase 6: Self-Review │ │
18	│ Phase 3: Execution & & Revision ──────────┘ │
19	│ Monitoring │ │
20	│ │ ▼ │
21	│ ▼ Phase 7: Submission │
22	│ Phase 4: Analysis ─────► (feeds back to Phase 2 or 5) │
23	│ │
24	└─────────────────────────────────────────────────────────────┘
25	```
26
27	---
28
29	## When To Use This Skill
30
31	Use this skill when:
32	- Starting a new research paper from an existing codebase or idea
33	- Designing and running experiments to support paper claims
34	- Writing or revising any section of a research paper
35	- Preparing for submission to a specific conference or workshop
36	- Responding to reviews with additional experiments or revisions
37	- Converting a paper between conference formats
38	- Writing non-empirical papers — theory, survey, benchmark, or position papers (see [Paper Types Beyond Empirical ML](#paper-types-beyond-empirical-ml))
39	- Designing human evaluations for NLP, HCI, or alignment research
40	- Preparing post-acceptance deliverables — posters, talks, code releases
41
42	## Core Philosophy
43
44	1. Be proactive. Deliver complete drafts, not questions. Scientists are busy — produce something concrete they can react to, then iterate.
45	2. Never hallucinate citations. AI-generated citations have ~40% error rate. Always fetch programmatically. Mark unverifiable citations as `[CITATION NEEDED]`.
46	3. Paper is a story, not a collection of experiments. Every paper needs one clear contribution stated in a single sentence. If you can't do that, the paper isn't ready.
47	4. Experiments serve claims. Every experiment must explicitly state which claim it supports. Never run experiments that don't connect to the paper's narrative.
48	5. Commit early, commit often. Every completed experiment batch, every paper draft update — commit with descriptive messages. Git log is the experiment history.
49
50	### Proactivity and Collaboration
51
52	Default: Be proactive. Draft first, ask with the draft.
53
54	\| Confidence Level \| Action \|
55	\|-----------------\|--------\|
56	\| High (clear repo, obvious contribution) \| Write full draft, deliver, iterate on feedback \|
57	\| Medium (some ambiguity) \| Write draft with flagged uncertainties, continue \|
58	\| Low (major unknowns) \| Ask 1-2 targeted questions via `clarify`, then draft \|
59
60	\| Section \| Draft Autonomously? \| Flag With Draft \|
61	\|---------\|-------------------\|-----------------\|
62	\| Abstract \| Yes \| "Framed contribution as X — adjust if needed" \|
63	\| Introduction \| Yes \| "Emphasized problem Y — correct if wrong" \|
64	\| Methods \| Yes \| "Included details A, B, C — add missing pieces" \|
65	\| Experiments \| Yes \| "Highlighted results 1, 2, 3 — reorder if needed" \|
66	\| Related Work \| Yes \| "Cited papers X, Y, Z — add any I missed" \|
67
68	Block for input only when: target venue unclear, multiple contradictory framings, results seem incomplete, explicit reque

People who liked this also viewed

6 picks

Type