A skill your agent uses when shaping the prose of an ICDT (International Conference on Database Theory) paper — the theorem-proof structure, stating the data model and computation model precisely…

MITAuto-check passedWriting & Content

Install Icdt Writing Style

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

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

GitHub CLI
$ gh skill install brycewang-stanford/Awesome-Journal-Skills icdt-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/ICDT-Skills/skills/icdt-writing-style .claude/skills/icdt-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
icdt-writing-style
GitHub stars
1.2k
Token cost
~1.3k tokens
SKILL.md length
630 words
Files
1
Skills in repo
2,387
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when shaping the prose of an ICDT (International Conference on Database Theory) paper — the theorem-proof structure, stating the data model and computation model precisely…

  • Works in 5 steps: The data-management problem, stated… → Why the current state is unsatisfactory… → The contribution as formal statements —… → …
  • Shaping the prose of an ICDT (International Conference on Database Theory) paper — the theorem-proof structure
  • SKILL.md covers The ICDT first-page arc, State the models before the…, Theorem-proof discipline… and Precision conventions a…, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Icdt Writing Style is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when shaping the prose of an ICDT (International Conference on Database Theory) paper — the theorem-proof structure, stating the data model and computation model precisely, leading with the result and its data-management consequence, proof-sketch-then-appendix discipline within the lipics-v2021 15-page budget, and the notation conventions a database-theory referee expects.

Its SKILL.md is about 1.3k 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 Writing & Content, covering Brand voice and tone. 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

  • Shaping the prose of an ICDT (International Conference on Database Theory) paper — the theorem-proof structure
  • Stating the data model and computation model precisely
  • Leading with the result and its data-management consequence
  • Proof-sketch-then-appendix discipline within the lipics-v2021 15-page budget

Example prompts

  • “/icdt-writing-style”

Workflow steps

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

  1. The data-management problem, stated precisely — what query language / constraint class /
  2. Why the current state is unsatisfactory — the exact gap: an open bound, a case the prior
  3. The contribution as formal statements — "We prove that evaluation for [class] is
  4. The technique in one breath — the proof idea a theorist can recognize (a reduction, a
  5. The consequence — what changes for querying, integration, or reasoning over data.

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.

    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

Icdt Writing Style loads about 1.3k tokens when it runs. Until then it costs about 100 tokens; SKILL.md has 630 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~100
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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). 630 words, ~1,281 tokens.

Download SKILL.mdSave it as .claude/skills/icdt-writing-style/SKILL.md (or your agent's skills folder).
name
icdt-writing-style
description
Use when shaping the prose of an ICDT (International Conference on Database Theory) paper — the theorem-proof structure, stating the data model and computation model precisely, leading with the result and its data-management consequence, proof-sketch-then-appendix discipline within the lipics-v2021 15-page budget, and the notation conventions a database-theory referee expects.

ICDT Writing Style

Write for a referee who will read the proof. An ICDT paper is judged on whether a precise theorem is correctly established and matters for data management, so the house style is the theorem-proof style of mathematical writing, disciplined into the lipics-v2021 15-page budget (excluding references) with the full details in a marked appendix. Exposition that hides the exact statement, the model, or the assumptions reads as imprecision at this venue.

The ICDT first-page arc

Lead with the result, not a survey. A strong ICDT introduction moves:

  1. The data-management problem, stated precisely — what query language / constraint class / data model, and what question about it (expressiveness? evaluation complexity? decidability?).
  2. Why the current state is unsatisfactory — the exact gap: an open bound, a case the prior dichotomy missed, a model whose complexity was unknown.
  3. The contribution as formal statements — "We prove that evaluation for [class] is [complexity], and that this is tight," ideally with the main theorem paraphrased in the intro.
  4. The technique in one breath — the proof idea a theorist can recognize (a reduction, a game argument, a normal form, a semiring homomorphism).
  5. The consequence — what changes for querying, integration, or reasoning over data.

Put the formal theorem statements early and label them; a referee should find "Theorem 1" and know your result before page three.

State the models before the theorems

The commonest avoidable ICDT weakness is an under-specified setting. Before the first theorem, pin:

  • The data model — relational, graph/RDF, semistructured, probabilistic, inconsistent, incomplete — and whether structures are finite (they usually are; finite model theory is the default over databases).
  • The query/constraint language — CQs, UCQs, Datalog, FO, MSO, regular path queries, TGDs/EGDs — with its exact syntax and semantics, not a hand-wave.
  • The computation and complexity measure — combined vs data vs query complexity, the machine model, and the complexity classes in play. "Data complexity" vs "combined complexity" is a distinction ICDT referees will hold you to.

Theorem-proof discipline within 15 pages

  • Body: definitions, theorem statements, and the ideas of the proofs — enough that a referee can judge correctness and see the structure. Full proofs may be sketched here.
  • Appendix (marked): the complete proofs, read at the PC's discretion. Write the body so a referee who never opens the appendix still believes the result is provable; write the appendix so one who does can certify it.
  • Do not pad the body with restated related work to fill space, and do not shrink the font or margins to reclaim it — lipics-v2021 is fixed; compress by editing.
Show full SKILL.md (209 more words)Show less

Precision conventions a referee expects

  • Every symbol is introduced before use; overloaded notation across sections is a correctness hazard, not a style nit.
  • Quantify claims exactly — "for every schema," "there exists a database," "in the worst case." A theory referee reads quantifier order literally.
  • Match bounds explicitly — if you claim tightness, state and prove both the upper and the lower bound, and say which is which.
  • Distinguish conjecture from theorem — "we conjecture" and "it is easy to see" are read literally; only write "it is easy to see" when it truly is, and give the argument if a referee might not.
  • Use standard names — call it a UCQ, a guarded TGD, a semiring provenance annotation, using the community's established terminology so the referee maps you to known results.

Common failure modes

  • Model-last writing — theorems before the data model is fixed, so the referee cannot tell what was proved.
  • One-sided bounds sold as tight — an upper bound with no matching lower bound presented as a complete answer.
  • Proof-by-citation — "the argument is similar to [12]" where the difference is exactly the hard part.
  • Survey-as-introduction — three pages of background before the first formal statement, burning the 15-page budget.
  • Undefined asymptotics — big-O over an unspecified parameter (data size? query size? both?).

Output format

text
[First-page arc] problem -> gap -> formal contribution -> technique -> data consequence: present?
[Models fixed] data model / query language / complexity measure stated before Theorem 1? yes/no
[Budget] body <=15 pages excl. refs; full proofs in the marked appendix? yes/no
[Precision] quantifiers exact / bounds matched / notation introduced: pass/fix
[Fix queue] <ordered edits>

© 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 ICDT-Skills/skills/icdt-writing-style of brycewang-stanford/Awesome-Journal-Skills.

Open the folder on GitHubat commit 932eb23

Compare with similar skills

Icdt 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.

Icdt Writing Style compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Icdt Writing Style this skillbrycewang-stanford/Awesome-Journal-Skills1.2k—~1.3kAutomated safety check: PassMIT
Crim Writing Stylefranklee16/academic-research-skills2231 repos~975Automated safety check: PassNone
Est Writing Stylefranklee16/academic-research-skills2231 repos~798Automated safety check: PassNone
Jaar Writing Stylefranklee16/academic-research-skills2231 repos~760Automated safety check: PassNone
Jcf Writing Stylefranklee16/academic-research-skills2231 repos~669Automated safety check: PassNone
Joc Writing Stylefranklee16/academic-research-skills2231 repos~873Automated safety check: PassNone

Similar skills

  • Crim Writing Style

    franklee16/academic-research-skills

    A skill your agent uses when drafting or polishing a Criminology (ASC / Wiley) manuscript so it reads for an interdisciplinary criminology audience, follows the journal's APA-based style, and uses…

    223 GitHub starsUsed in 1 repo~975 tokens
    Writing & ContentAuto-check passed
  • Est Writing Style

    franklee16/academic-research-skills

    A skill your agent uses when drafting or polishing the prose of an Environmental Science & Technology (ES&T) manuscript so it reads for a multidisciplinary audience in ACS style and fits the…

    223 GitHub starsUsed in 1 repo~798 tokens
    Writing & ContentAuto-check passed
  • Jaar Writing Style

    franklee16/academic-research-skills

    A skill your agent uses when drafting or polishing the prose of a Journal of the American Academy of Religion (JAAR) article so it is clear, analytic, gender-neutral, and readable across the study…

    223 GitHub starsUsed in 1 repo~760 tokens
    Writing & ContentAuto-check passed
  • Jcf Writing Style

    franklee16/academic-research-skills

    A skill your agent uses when drafting or polishing prose for a Journal of Corporate Finance (JCF) manuscript — the ≤250-word abstract, 1–7 keywords, author-date (Harvard) in-text citations, and the…

    223 GitHub starsUsed in 1 repo~669 tokens
    Writing & ContentAuto-check passed
  • Joc Writing Style

    franklee16/academic-research-skills

    A skill your agent uses when drafting or polishing a Journal of Communication (JoC) manuscript so it reads for the whole field, follows APA 7th edition, and fits the limits (main document <= 35…

    223 GitHub starsUsed in 1 repo~873 tokens
    Writing & ContentAuto-check passed
  • Jpe Writing Style

    franklee16/academic-research-skills

    A skill your agent uses when polishing the prose of a Journal of Political Economy (JPE) manuscript into its spare, analytical, economics-first register.

    223 GitHub starsUsed in 1 repo~1.1k tokens
    Writing & ContentAuto-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 Icdt Writing Style

What does Icdt Writing Style do?

A skill your agent uses when shaping the prose of an ICDT (International Conference on Database Theory) paper — the theorem-proof structure, stating the data model and computation model precisely…. Icdt Writing Style is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when shaping the prose of an ICDT (International Conference on Database Theory) paper — the theorem-proof structure, stating the data model and computation model precisely, leading with the result and its data-management consequence, proof-sketch-then-appendix discipline within the lipics-v2021 15-page budget, and the notation conventions a database-theory referee expects.

When should I use Icdt Writing Style?

Icdt Writing Style fits situations like: shaping the prose of an ICDT (International Conference on Database Theory) paper — the theorem-proof structure; stating the data model and computation model precisely; leading with the result and its data-management consequence; proof-sketch-then-appendix discipline within the lipics-v2021 15-page budget.

How do I install Icdt Writing Style in Claude Code?

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

How do I install Icdt Writing Style in Codex?

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

Can I use Icdt 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 icdt-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/icdt-writing-style, .gemini/skills/icdt-writing-style, .github/skills/icdt-writing-style and .opencode/skills/icdt-writing-style in your project.

What does Icdt Writing Style need to run?

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

Does Icdt 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 Icdt 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 Icdt Writing Style use?

Icdt 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 Icdt Writing Style use?

About 1.3k tokens (SKILL.md is roughly 5.1k 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 Icdt Writing Style?

Skills that share tags, products or a category with Icdt Writing Style: Crim Writing Style (franklee16/academic-research-skills, 223 stars), Est Writing Style (franklee16/academic-research-skills, 223 stars), Jaar Writing Style (franklee16/academic-research-skills, 223 stars) and Jcf Writing Style (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 Icdt 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.