A skill your agent uses when writing or revising an ICSE research-track paper, covering empirical-SE paper anatomy, research questions as the load-bearing structure, the threats-to-validity section…

MITAuto-check passedResearch & Science

Install Icse Writing Style

skills CLI
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill icse-writing-style -a claude-code

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

GitHub CLI
$ gh skill install brycewang-stanford/Awesome-Journal-Skills icse-writing-style --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/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ICSE-Skills/skills/icse-writing-style .claude/skills/icse-writing-style && 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
icse-writing-style
GitHub stars
1.2k
Token cost
~1.5k tokens
SKILL.md length
710 words
Files
1
Skills in repo
2,387
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when writing or revising an ICSE research-track paper, covering empirical-SE paper anatomy, research questions as the load-bearing structure, the threats-to-validity section…

  • Works in 3 steps: Name your actual weakest point, the one… → Pair every threat with what you did… → Ban imported boilerplate. "Our results…
  • Revising an ICSE research-track paper
  • SKILL.md covers The load-bearing skeleton, Research questions as contract, The threats-to-validity craft and Motivation that survives the…, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Icse Writing Style is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when writing or revising an ICSE research-track paper, covering empirical-SE paper anatomy, research questions as the load-bearing structure, the threats-to-validity section the community expects, practitioner-grounded motivation, calibrated claims, and fitting a complete study into ten IEEE pages.

Its SKILL.md is about 1.5k 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 Brand voice and tone and Hypothesis generation. The repository describes itself as: Journal-specific Claude Code/Codex skill packs covering mainstream journals — AER, QJE, Nature, Cell, 管理世界, 经济研究 & 200+ more — your fast track to getting published. | 覆盖主流期刊的… The licence is MIT.

When your agent uses it

  • Revising an ICSE research-track paper
  • Covering empirical-SE paper anatomy
  • Research questions as the load-bearing structure
  • The threats-to-validity section the community expects

Example prompts

  • “/icse-writing-style”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Name your actual weakest point, the one a hostile reviewer would find
  2. Pair every threat with what you did about it (mitigation) or why it is
  3. Ban imported boilerplate. "Our results may not generalize to other

What it can do on your machine

Read from SKILL.md and the folder at commit 932eb23. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are latex).

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

  • Network

    No URLs in SKILL.md.

    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

Icse Writing Style loads about 1.5k tokens when it runs. Until then it costs about 81 tokens; SKILL.md has 710 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~81
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

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 brycewang-stanford/Awesome-Journal-Skills at commit 932eb23, republished under its MIT licence (© brycewang-stanford). 710 words, ~1,506 tokens.

Download SKILL.mdSave it as .claude/skills/icse-writing-style/SKILL.md (or your agent's skills folder).
name
icse-writing-style
description
Use when writing or revising an ICSE research-track paper, covering empirical-SE paper anatomy, research questions as the load-bearing structure, the threats-to-validity section the community expects, practitioner-grounded motivation, calibrated claims, and fitting a complete study into ten IEEE pages.

ICSE Writing Style

ICSE prose is judged by empiricists. The reviewer pool's shared training — controlled experiments, mining studies, qualitative methods — produces a house reading style: they locate the research questions, check that the design answers them, and read the threats-to-validity section as a candor test. Write for that reading order, not for a general CS audience.

The load-bearing skeleton

A canonical ICSE technique-plus-evaluation paper spends its ten pages (2027 format: 10 pages main text including all figures/tables/appendices, +2 pages references only) roughly like this:

SectionPagesWhat reviewers extract from it
Introduction1.5The SE problem, who suffers it, the claim, the contributions list
Background / motivating example1One concrete failing case the technique later fixes
Approach2–2.5How it works, precisely enough to reimplement (verifiability)
Study design1.5RQs, subjects, baselines, metrics, protocol — before any results
Results, organized by RQ2.5One answer per RQ, stated then evidenced
Discussion + implications0.5–1What researchers and practitioners should do differently
Threats to validity0.5Honest limits with mitigations
Related work + conclusion1Delta over neighbors (see icse-related-work)

Empirical studies swap Approach for extended methodology; the RQ-driven spine stays. If a section cannot say which RQ it serves, it is a cut candidate.

Research questions as contract

State 2–4 RQs in the introduction or design section, then answer them in order with boxed findings:

latex
\subsection{RQ1: How often do generated patches overfit the test suite?}
...evidence...
\begin{tcolorbox}
\textbf{RQ1 finding.} 47\% of patches passing the full suite fail held-out
tests; overfitting concentrates in multi-hunk patches.
\end{tcolorbox}

Reviewers navigate by these boxes. An RQ that is asked but never answered, or a finding with no RQ, both read as design drift — a rigor flag.

The threats-to-validity craft

The section is expected, but its quality is what gets scored. Community convention organizes threats as construct validity (are you measuring the right thing?), internal validity (could something else explain the result?), external validity (to what does it generalize?), and — for statistical work — conclusion validity. Three rules separate a real threats section from ritual:

  1. Name your actual weakest point, the one a hostile reviewer would find anyway. Preempting it converts an attack into a footnote.
  2. Pair every threat with what you did about it (mitigation) or why it is tolerable (bounded impact). A threat with neither is a confession.
  3. Ban imported boilerplate. "Our results may not generalize to other projects" appears in thousands of papers; "our 17 subjects are all Java build systems, and the technique reads JVM bytecode, so C# generalization is untested" is yours alone.
Show full SKILL.md (318 more words)Show less

Motivation that survives the relevance criterion

ICSE scores relevance to software engineering explicitly. Ground the opening in an engineering pain that is evidenced, not asserted: a quantified cost from a cited study, a documented incident, an observed practice from your own formative data. The weakest ICSE openings assert that a problem "is important and has attracted increasing attention" — citation-mulch that spends the most valuable half page on nothing.

Calibrated claims

The verifiability criterion punishes claim/evidence gaps, so calibrate:

  • Quantify or delete: "substantially outperforms" → "improves F1 by 0.09–0.14 across all three benchmarks (Table 3)".
  • Scope every generalization: "for the Java projects studied", "in our interview population".
  • Distinguish observation from causation everywhere except where the design licenses causal language (a controlled experiment does; a mining correlation does not).
  • Make the contributions list checkable — each bullet should name the section and, where relevant, the artifact directory that substantiates it.

The abstract, sentence by sentence

An ICSE abstract that reviewers bid on accurately runs six moves: (1) the engineering problem with its cost; (2) the gap in how existing work handles it; (3) the approach in one mechanism-revealing sentence; (4) the study design in one sentence — subjects, baselines, method; (5) headline results with numbers, scoped; (6) the availability sentence. Move 4 is the one authors from other communities omit and SE reviewers miss immediately: at ICSE the study is a first-class part of the contribution, and an abstract that hides it reads as having something to hide.

Ten-page compression without desk-reject risk

The IEEE template's formatting rules are desk-reject-enforceable, so recover space editorially: merge motivating example into the introduction; convert prose protocol descriptions into a design table; move non-decision-critical material to the replication package and cite it in the availability statement (the package, unlike the paper, has no page cap); tighten figures — SE papers lose half-pages to screenshots that could be 4-line listings. Never touch \vspace, margins, or font sizes.

Output format

text
[Structure audit] skeleton section -> present/missing/oversized (page budget)
[RQ contract] each RQ -> design element -> boxed answer (complete? ordered?)
[Threats quality] real weakest point named? mitigations paired? boilerplate found?
[Claim calibration] list of unquantified/over-scoped claims with rewrites
[Space plan] cuts and relocations to reach 10 pages template-clean

© brycewang-stanford, 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 ICSE-Skills/skills/icse-writing-style of brycewang-stanford/Awesome-Journal-Skills.

Open the folder on GitHubat commit 932eb23

Compare with similar skills

Icse Writing Style 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.

Icse Writing Style compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Icse Writing Style this skillbrycewang-stanford/Awesome-Journal-Skills1.2k—~1.5kAutomated safety check: PassMIT
Academic Venue Researchjoshua-zyy/academic-paper-writer115—~626Automated safety check: PassMIT
Ccf Idea Optimizermikubaka88/CCFA-Skills3k—~1.9kAutomated safety check: PassMIT
Agsy Writing Stylefranklee16/academic-research-skills2231 repos~1kAutomated safety check: PassNone
Artbull Writing Style And Citationfranklee16/academic-research-skills2231 repos~848Automated safety check: PassNone
Car Writing Stylefranklee16/academic-research-skills2231 repos~960Automated safety check: PassNone

Similar skills

  • Academic Venue Research

    joshua-zyy/academic-paper-writer

    Research target venue requirements and writing style for CS/AI/ML papers.

    115 GitHub stars~626 tokensUpdated 6 days ago
    Research & ScienceAuto-check passed
  • Ccf Idea Optimizer

    mikubaka88/CCFA-Skills

    Develop and optimize rough CCF research ideas into problems, insights, mechanisms, and evidence plans.

    3k GitHub stars~1.9k tokensUpdated 25 days ago
    Research & ScienceAuto-check passed
  • Agsy Writing Style

    franklee16/academic-research-skills

    A skill your agent uses when drafting or polishing an Agricultural Systems (AgSy) manuscript so it reads clearly for a systems-science audience, follows the journal's format, and meets front-matter…

    223 GitHub starsUsed in 1 repo~1k tokens
    Research & ScienceAuto-check passed
  • Artbull Writing Style And Citation

    franklee16/academic-research-skills

    A skill your agent uses when polishing prose and formatting citations for an Art Bulletin article to The Chicago Manual of Style — endnotes (not author-date), full credit-line captions, and…

    223 GitHub starsUsed in 1 repo~848 tokens
    Research & ScienceAuto-check passed
  • Car Writing Style

    franklee16/academic-research-skills

    A skill your agent uses when polishing the prose of a Contemporary Accounting Research (CAR) manuscript — a front-loaded research question, disciplined accounting terminology, the ≤300-word abstract…

    223 GitHub starsUsed in 1 repo~960 tokens
    Business, Finance & HRAuto-check passed
  • Ectheory Writing Style

    franklee16/academic-research-skills

    A skill your agent uses to polish the prose, notation, and proof exposition of an Econometric Theory (ET) manuscript — theorem-proof clarity, consistent notation, APA author-date references, and ET…

    223 GitHub starsUsed in 1 repo~874 tokens
    Research & ScienceAuto-check passed

More from brycewang-stanford/Awesome-Journal-Skills

All 2,387 skills in this repo
  • Aaag Data Analysis

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when running and reporting the analysis for an Annals of the American Association of Geographers manuscript — spatial statistics and modeling, remote-sensing accuracy, or…

    1.2k GitHub stars~1.3k tokensUpdated 14 days ago
    Auto-check passed
  • Aaag Literature Positioning

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when positioning an Annals of the American Association of Geographers manuscript in the literature — engaging geographic scholarship across the relevant area and the…

    1.2k GitHub stars~1.3k tokensUpdated 14 days ago
    Auto-check passed
  • Aaag Rebuttal

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when responding to an Annals of the American Association of Geographers decision letter (major/minor revision) — building a point-by-point response to the subject editor and…

    1.2k GitHub stars~1.4k tokensUpdated 14 days ago
    Auto-check passed
  • Aaag Research Design

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when defending the research design of an Annals of the American Association of Geographers manuscript — spatial/quantitative analysis and GIScience, remote-sensing and…

    1.2k GitHub stars~1.4k tokensUpdated 14 days ago
    Auto-check passed
  • Aaag Review Process

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when you need to understand how the Annals of the American Association of Geographers evaluates a manuscript — double-anonymous review routed through a subject editor by…

    1.2k GitHub stars~1.3k tokensUpdated 14 days ago
    Auto-check passed
  • Aaag Submission

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when running the final pre-submission preflight for the Annals of the American Association of Geographers via ScholarOne Manuscripts — area/article-type selection…

    1.2k GitHub stars~1.6k tokensUpdated 14 days ago
    Auto-check passed

Questions about Icse Writing Style

What does Icse Writing Style do?

A skill your agent uses when writing or revising an ICSE research-track paper, covering empirical-SE paper anatomy, research questions as the load-bearing structure, the threats-to-validity section…. Icse Writing Style is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when writing or revising an ICSE research-track paper, covering empirical-SE paper anatomy, research questions as the load-bearing structure, the threats-to-validity section the community expects, practitioner-grounded motivation, calibrated claims, and fitting a complete study into ten IEEE pages.

When should I use Icse Writing Style?

Icse Writing Style fits situations like: revising an ICSE research-track paper; covering empirical-SE paper anatomy; research questions as the load-bearing structure; the threats-to-validity section the community expects.

How do I install Icse Writing Style in Claude Code?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill icse-writing-style -a claude-code`. Or copy the skill folder (ICSE-Skills/skills/icse-writing-style in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/icse-writing-style in your project. Claude Code loads it when a task matches its description.

How do I install Icse Writing Style in Codex?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill icse-writing-style -a codex`. Or copy the skill folder (ICSE-Skills/skills/icse-writing-style in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/icse-writing-style in your project. Codex loads it when a task matches its description.

Can I use Icse Writing Style 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 brycewang-stanford/Awesome-Journal-Skills --skill icse-writing-style -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/icse-writing-style, .gemini/skills/icse-writing-style, .github/skills/icse-writing-style and .opencode/skills/icse-writing-style in your project.

What does Icse Writing Style need to run?

SKILL.md names no scripts, command-line tools or credentials: Icse Writing Style is instructions for the agent only.

Does Icse Writing Style access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Icse Writing Style 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 Icse Writing Style use?

Icse Writing Style is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Icse Writing Style use?

About 1.5k tokens (SKILL.md is roughly 6k 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 Icse Writing Style?

Skills that share tags, products or a category with Icse Writing Style: Academic Venue Research (joshua-zyy/academic-paper-writer, 115 stars), Ccf Idea Optimizer (mikubaka88/CCFA-Skills, 3k stars), Agsy Writing Style (franklee16/academic-research-skills, 223 stars) and Artbull Writing Style And Citation (franklee16/academic-research-skills, 223 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Icse Writing Style?

brycewang-stanford (a GitHub user) maintains it in brycewang-stanford/Awesome-Journal-Skills, which has 1,231 GitHub stars. The repository holds 2,387 skills in this directory. The repository was last updated on September 27, 2026.

Source: brycewang-stanford/Awesome-Journal-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.