Agent skill

Research Paper Writing

by HezaoHezao in HezaoHezao/poirot

ML paper pipeline: experiment design to submission. An agent skill from HezaoHezao/poirot.

MITAuto-check passedResearch & Science

Install Research Paper Writing

skills CLI
$ npx skills add HezaoHezao/poirot --skill research-paper-writing -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install HezaoHezao/poirot research-paper-writing --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/HezaoHezao/poirot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/poirot/backend/agents/skill/builtin_skills/research/research-paper-writing .claude/skills/research-paper-writing && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
research-paper-writing
GitHub stars
249
Token cost
~1.4k tokens
SKILL.md length
456 words
Files
1
Skills in repo
23
Repo updated
First seen
Licence
MIT

At a glance

ML paper pipeline: experiment design to submission. An agent skill from HezaoHezao/poirot.

  • Works in 8 steps: Project Setup → Literature Review → Experiment Design → …
  • Tasks that involve Scientific writing
  • SKILL.md covers Overview, When to Use, Pipeline Phases and Statistical Analysis, plus 2 more sections
  • Calls python, python3 and pip

What it does

Research Paper Writing is an agent skill from HezaoHezao/poirot. ML paper pipeline: experiment design to submission.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science, covering Scientific writing and Experimental design. The repository describes itself as: Poirot is a deep research agent kernel built for those who care about how agents are architected. The licence is MIT.

When your agent uses it

  • Tasks that involve Scientific writing
  • Tasks that involve Experimental design

Example prompts

  • “/research-paper-writing”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): bash, write_file, read_file, web_search, browse_page

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Project Setup
  2. Literature Review
  3. Experiment Design
  4. Execution & Monitoring
  5. Analysis
  6. Paper Drafting
  7. Self-Review & Revision
  8. Submission

What it can do on your machine

Read from SKILL.md and the folder at commit 86bf279. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • bash
    • write_file
    • read_file
    • web_search
    • browse_page

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python
    • python3
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Research Paper Writing loads about 1.4k tokens when it runs. Until then it costs about 19 tokens; SKILL.md has 456 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~19
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from HezaoHezao/poirot at commit 86bf279, republished under its MIT licence (© HezaoHezao). 456 words, ~1,367 tokens.

Download SKILL.mdSave it as .claude/skills/research-paper-writing/SKILL.md (or your agent's skills folder).
name
research-paper-writing
description
ML paper pipeline: experiment design to submission.
allowed-tools
bash, write_file, read_file, web_search, browse_page
enabled
true
related-skills
arxiv, academic-paper-review, plan
license
MIT
author
Adapted from hermes-agent (Nous Research, MIT); Orchestra Research

Research Paper Writing Pipeline

Overview

End-to-end pipeline for producing publication-ready ML/AI research papers targeting NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Covers the full research lifecycle: experiment design, execution, analysis, paper writing, review, revision, and submission.

This is not a linear pipeline — it is an iterative loop. Results trigger new experiments. Reviews trigger new analysis.

When to Use

  • User is writing an ML/AI research paper for a top venue
  • User needs help with experiment design, execution, or analysis
  • User wants feedback on a draft
  • User is preparing a submission package

Pipeline Phases

Phase 0: Project Setup → Phase 1: Literature Review
       │                        │
       ▼                        ▼
Phase 2: Experiment      Phase 5: Paper Drafting ◄──┐
       Design                  │                    │
       │                       ▼                    │
       ▼                 Phase 6: Self-Review       │
Phase 3: Execution            & Revision ───────────┘
       & Monitoring              │
       │                         ▼
       ▼                   Phase 7: Submission
Phase 4: Analysis
Phase 0: Project Setup
  • Define research question and hypothesis
  • Identify target venue + deadline
  • Set up project structure:
    project/
    ├── experiments/
    ├── data/
    ├── src/
    ├── paper/
    │   ├── main.tex
    │   ├── figures/
    │   └── references.bib
    └── README.md
  • Initialize git repo, set up environment
Phase 1: Literature Review
  • Use arxiv skill to find related work
  • Use web_search for non-arXiv papers (Semantic Scholar, Google Scholar)
  • Use browse_page to read key papers in full
  • Build a references.bib with all cited works
  • Identify the gap your work fills
Phase 2: Experiment Design
  • Define baselines and comparison methods
  • Choose datasets and evaluation metrics
  • Design ablation studies
  • Plan computational budget
  • Write pre-registration document (optional but recommended)
Phase 3: Execution & Monitoring
bash
# Run experiments
python src/train.py --config configs/exp1.yaml

# Monitor with logging
python src/train.py --config configs/exp1.yaml --log-dir runs/exp1

# Track experiments
python src/eval.py --checkpoint runs/exp1/best.pt --eval-set test
  • Log all hyperparameters, seeds, and environment details
  • Save checkpoints for reproducibility
  • Run each experiment with multiple seeds (3-5)
Phase 4: Analysis
  • Aggregate results across seeds
  • Compute statistical significance (paired t-test, bootstrap CI)
  • Generate comparison tables and plots:
    bash
    python src/plot.py --results runs/ --output paper/figures/
  • Run ablation analysis
  • Identify surprising findings (investigate, don't hide)
Show full SKILL.md (225 more words)Show less
Phase 5: Paper Drafting

Follow venue template structure:

  1. Abstract — problem, method, key result, impact (write last)
  2. Introduction — motivation, contribution summary, roadmap
  3. Related Work — position within literature (from Phase 1)
  4. Method — approach, architecture, training procedure
  5. Experiments — setup, main results, ablations, analysis
  6. Conclusion — summary, limitations, future work

Writing principles:

  • One idea per paragraph
  • Figures tell the story — design figures first, write text around them
  • Tables for comparisons — main results table + ablation table
  • Reproducibility — include all hyperparameters, release code
Phase 6: Self-Review & Revision

Use academic-paper-review skill to self-review:

  • Read the paper cold (fresh eyes)
  • Check methodology soundness, novelty, reproducibility
  • Identify weaknesses and fix them
  • Get feedback from collaborators
Phase 7: Submission
  • Check venue formatting requirements
  • Verify page limits
  • Anonymize for blind review (if applicable)
  • Prepare supplementary material (code, data, extended results)
  • Submit before deadline (not at 23:59)

Statistical Analysis

bash
# Multiple seeds — compute mean ± std
python3 -c "
import numpy as np
results = [0.85, 0.83, 0.86, 0.84, 0.82]  # per-seed results
print(f'Mean: {np.mean(results):.4f} ± {np.std(results):.4f}')
"

# Paired t-test vs baseline
python3 -c "
from scipy import stats
baseline = [0.80, 0.79, 0.81, 0.78, 0.80]
ours = [0.85, 0.83, 0.86, 0.84, 0.82]
t, p = stats.ttest_rel(ours, baseline)
print(f't={t:.3f}, p={p:.4f}')
"

Pitfalls

  • Single seed: results from one seed are not reliable. Use 3-5 minimum.
  • Cherry-picking: report all results, not just the best seed.
  • No ablations: reviewers will ask "does each component matter?" — answer proactively.
  • Missing related work: reviewers know the field. Cite comprehensively.
  • Unclear contributions: list contributions explicitly in the introduction.
  • Overclaiming: "state-of-the-art" needs evidence across datasets, not one.
  • Last-minute submission: servers crash at deadlines. Submit early.

Dependencies

This skill benefits from: numpy, scipy, matplotlib (analysis + plots). Install via pip install numpy scipy matplotlib.

© HezaoHezao, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in poirot/backend/agents/skill/builtin_skills/research/research-paper-writing of HezaoHezao/poirot.

Open the folder on GitHubat commit 86bf279

Compare with similar skills

Research Paper Writing next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Research Paper Writing compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Research Paper Writing this skillHezaoHezao/poirot249—~1.4kAutomated safety check: PassMIT
Benchmark Paper TemplateHKUSTDial/Supervisor-Skills8.8k—~2.8kAutomated safety check: PassCC-BY-4.0
Research Refine PipelinezjYao36/Auto-Research-Refine1285 repos~1.4kAutomated safety check: NotesNone
Scholar Evaluationjimmc414/Kosmos5951 repos~2.5kAutomated safety check: PassNone
Academic Researchvoidful/academic-skills135—~887Automated safety check: PassMIT
Academic Writingwentorai/Research-Claw858—~896Automated safety check: PassCustom licence

Similar skills

  • Benchmark Paper Template

    HKUSTDial/Supervisor-Skills

    Structures benchmark and evaluation papers around five pillars, with a completeness audit, an Introduction logic chain, a section skeleton and a pre-submission checklist.

    8.8k GitHub stars~2.8k tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed
  • Research Refine Pipeline

    zjYao36/Auto-Research-Refine

    Chains research-refine and experiment-plan to turn a vague research direction into a focused proposal and a claim-driven experiment roadmap.

    128 GitHub starsUsed in 5 repos~1.4k tokens
    Research & ScienceAuto-check: notes
  • Scholar Evaluation

    jimmc414/Kosmos

    Systematic framework for evaluating scholarly and research work based on the ScholarEval methodology.

    595 GitHub starsUsed in 1 repo~2.5k tokens
    Research & ScienceAuto-check passed
  • Academic Research

    voidful/academic-skills

    Complete academic research skill suite covering the full pipeline: paper reading (read/explain papers with storytelling), idea generation (brainstorm research directions), experiment design (plan…

    135 GitHub stars~887 tokensUpdated 6 mo ago
    Research & ScienceAuto-check passed
  • Academic Writing

    wentorai/Research-Claw

    Academic writing expert specializing in scholarly papers, literature reviews, research methodology, and thesis writing with strict academic standards.

    858 GitHub stars~896 tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed
  • Research Paper Writing

    RedWoodOG/Hermes-Desktop

    End-to-end pipeline for writing ML/AI research papers — from experiment design through analysis, drafting, revision, and submission.

    177 GitHub starsUsed in 6 repos~16k tokens
    Research & ScienceAuto-check: notes

More from HezaoHezao/poirot

All 23 skills in this repo
  • Requesting Code Review

    HezaoHezao/poirot

    Pre-commit review: security scan, quality gates, auto-fix. An agent skill from HezaoHezao/poirot.

    249 GitHub starsUsed in 5 repos~1.6k tokens
    Auto-check passed
  • Academic Paper Review

    HezaoHezao/poirot

    Structured peer-review of academic papers. An agent skill from HezaoHezao/poirot.

    249 GitHub stars~1.8k tokensUpdated 2 mo ago
    Auto-check passed
  • Blogwatcher

    HezaoHezao/poirot

    Monitor blogs and RSS/Atom feeds via blogwatcher-cli. An agent skill from HezaoHezao/poirot.

    249 GitHub stars~854 tokensUpdated 2 mo ago
    Auto-check passed
  • Bootstrap

    HezaoHezao/poirot

    Onboarding conversation to generate a user profile. An agent skill from HezaoHezao/poirot.

    249 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed
  • Chart Visualization

    HezaoHezao/poirot

    Generate charts: select type, extract data, render image. An agent skill from HezaoHezao/poirot.

    249 GitHub stars~1k tokensUpdated 2 mo ago
    Auto-check passed
  • Code Documentation

    HezaoHezao/poirot

    Generate docs: README, API reference, architecture, guides. An agent skill from HezaoHezao/poirot.

    249 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Research Paper Writing

What does Research Paper Writing do?

ML paper pipeline: experiment design to submission. An agent skill from HezaoHezao/poirot. Research Paper Writing is an agent skill from HezaoHezao/poirot. ML paper pipeline: experiment design to submission.

When should I use Research Paper Writing?

Research Paper Writing fits situations like: tasks that involve Scientific writing; tasks that involve Experimental design.

How do I install Research Paper Writing in Claude Code?

Run `npx skills add HezaoHezao/poirot --skill research-paper-writing -a claude-code`. Or copy the skill folder (poirot/backend/agents/skill/builtin_skills/research/research-paper-writing in HezaoHezao/poirot) into .claude/skills/research-paper-writing in your project. Claude Code loads it when a task matches its description.

How do I install Research Paper Writing in Codex?

Run `npx skills add HezaoHezao/poirot --skill research-paper-writing -a codex`. Or copy the skill folder (poirot/backend/agents/skill/builtin_skills/research/research-paper-writing in HezaoHezao/poirot) into .agents/skills/research-paper-writing in your project. Codex loads it when a task matches its description.

Can I use Research Paper Writing in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HezaoHezao/poirot --skill research-paper-writing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/research-paper-writing, .gemini/skills/research-paper-writing, .github/skills/research-paper-writing and .opencode/skills/research-paper-writing in your project.

What does Research Paper Writing need to run?

Going by SKILL.md and its folder, Research Paper Writing needs the command-line tools its instructions call (python, python3 and pip). Our summary lists: Python 3. Its frontmatter pre-approves these tools: bash, write_file, read_file, web_search, browse_page.

Does Research Paper Writing access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Research Paper Writing safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Research Paper Writing use?

Research Paper Writing is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Research Paper Writing use?

About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Research Paper Writing?

Skills that share tags, products or a category with Research Paper Writing: Benchmark Paper Template (HKUSTDial/Supervisor-Skills, 8.8k stars), Research Refine Pipeline (zjYao36/Auto-Research-Refine, 128 stars), Scholar Evaluation (jimmc414/Kosmos, 595 stars) and Academic Research (voidful/academic-skills, 135 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Research Paper Writing?

HezaoHezao (a GitHub user) maintains it in HezaoHezao/poirot, which has 249 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on July 28, 2026.

Source: HezaoHezao/poirot on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.