New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Kdd Supplementary

by brycewang-stanford in brycewang-stanford/Awesome-Journal-Skills

A skill your agent uses when splitting a KDD paper across its 8 content pages, the optional appendix after the references, and the cited repository, under the camera-ready rule capping references…

MITAuto-check passed

Install Kdd Supplementary

skills CLI
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill kdd-supplementary -a claude-code

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

GitHub CLI
$ gh skill install brycewang-stanford/Awesome-Journal-Skills kdd-supplementary --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/KDD-Skills/skills/kdd-supplementary .claude/skills/kdd-supplementary && 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
kdd-supplementary
GitHub stars
1.2k
Token cost
~1.7k tokens
SKILL.md length
799 words
Files
1
Skills in repo
2,387
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when splitting a KDD paper across its 8 content pages, the optional appendix after the references, and the cited repository, under the camera-ready rule capping references…

  • Works in 4 steps: List every appendix section with the… → For each, ask: if a reviewer never opens… → Mark each section's camera-ready fate… → …
  • Splitting a KDD paper across its 8 content pages
  • SKILL.md covers The container model, What belongs where, Resubmission special page and Appendix triage pass…, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Kdd Supplementary is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when splitting a KDD paper across its 8 content pages, the optional appendix after the references, and the cited repository, under the camera-ready rule capping references plus appendix at 3 of 12 pages. Covers appendix triage, reviewer-discretion reality, and the one-page cross-cycle resubmission change summary.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

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

  • Splitting a KDD paper across its 8 content pages
  • The optional appendix after the references
  • The cited repository
  • Under the camera-ready rule capping references plus appendix at 3 of 12 pages

Example prompts

  • “/kdd-supplementary”

Workflow steps

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

  1. List every appendix section with the body reference(s) that point to it; delete
  2. For each, ask: if a reviewer never opens this, does any scored dimension drop? If
  3. Mark each section's camera-ready fate now: migrate-to-body, compress,
  4. Anonymity-sweep the appendix with the same rigor as the body; grant numbers and

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

Kdd Supplementary loads about 1.7k tokens when it runs. Until then it costs about 84 tokens; SKILL.md has 799 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~84
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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). 799 words, ~1,736 tokens.

Download SKILL.mdSave it as .claude/skills/kdd-supplementary/SKILL.md (or your agent's skills folder).
name
kdd-supplementary
description
Use when splitting a KDD paper across its 8 content pages, the optional appendix after the references, and the cited repository, under the camera-ready rule capping references plus appendix at 3 of 12 pages. Covers appendix triage, reviewer-discretion reality, and the one-page cross-cycle resubmission change summary.

KDD Supplementary

Use this when distributing material across the three containers a KDD submission actually has: the 8 content pages, the optional appendix after the references, and the repository cited in the PDF. KDD has no separate supplement upload deadline in the 2026 pattern — the appendix travels inside the submission PDF — which makes the split decision a writing-time decision, not a deadline-week one.

The container model

ContainerSize disciplineReviewer obligationSurvives to proceedings?
8 content pagesHard budgetMust be reviewable standaloneYes, grows to 9
Appendix (after refs)Unbounded at submission (verify current CFP)Discretionary readingOnly within the 3-page refs+appendix cap
Cited repositoryPractically unboundedRarely opened; never linkable again after submissionYes, as the public artifact

The asymmetry between submission and camera-ready is the planning trap: an appendix that balloons to 15 pages at submission must shrink to fit references + appendix within 3 pages of the 12-page proceedings version. Anything you are not prepared to delete or migrate to the repository later should not be load-bearing in review.

What belongs where

Content pages — everything a reviewer needs to score the paper: the mechanism, the main comparison table, the mechanism-isolating ablation, complexity statements, the deployment metrics (ADS). The KDD failure pattern is a body that reads like an extended abstract with "see Appendix" doing the arguing; reviewers score what they can see in eight pages.

Appendix — proofs of stated propositions, full hyperparameter grids, per-dataset result breakdowns, extra case studies, prompt/feature inventories, dataset documentation. Order it by reference-frequency from the body, restate each claim before its proof, and reference every appendix table from the body at least once — orphaned appendix material is invisible under reviewer discretion.

Repository — anything executable, anything larger than a page of tables, extended logs, and full configs. Remember the one-way door: the repo must be cited in the PDF at submission because rebuttals cannot introduce links (see kdd-artifact-evaluation).

Resubmission special page

A paper returning after a Resubmit decision prepends a one-page summary of changes as the first page of the PDF, alongside the previous OpenReview forum id in the form. Treat that page as the highest-value real estate in the resubmission:

text
Summary of Changes (Resubmission of forum <id>)

R1-W1 "no ablation isolating the decay mechanism"
  -> New Table 5 (Sec 5.3): decay ablation across all datasets.
R2-W1 "temporal leakage suspected in splits"
  -> Splits rebuilt time-ordered (Sec 4.2); all tables regenerated;
     headline delta changed from +4.1 to +3.3, conclusions unchanged.
R3-W2 "claims exceed tested scale"
  -> Claim scoped to <=2.1B events (Abstract, Sec 1); added 2.1B-event run.
Unaddressed: R2-W3 (user study) - out of scope, argued in Sec 6.

Point-by-point, mapped to sections, honest about what changed numerically and what was declined — this is the page the new area chair reads first.

Appendix triage pass (pre-deadline)

  1. List every appendix section with the body reference(s) that point to it; delete sections with zero inbound references or add the reference.
  2. For each, ask: if a reviewer never opens this, does any scored dimension drop? If yes, promote its key row/claim into the body.
  3. Mark each section's camera-ready fate now: migrate-to-body, compress, move-to-repo, or cut — the 3-page cap arrives with acceptance.
  4. Anonymity-sweep the appendix with the same rigor as the body; grant numbers and internal system names hide in appendix footnotes.
Show full SKILL.md (329 more words)Show less

Vignette: splitting a graph-systems paper

A submission proposes a partitioning scheme for distributed GNN training with a cost-model analysis, twelve datasets, and a parameter study. The split that survives both review and the eventual 3-page cap:

  • Body: the partitioning mechanism with its one algorithm block, the cost-model proposition (statement plus intuition), the main table on the five most informative datasets, the mechanism ablation, and the scaling figure.
  • Appendix: the cost-model proof, the remaining seven datasets' rows, the full parameter sweep, and cluster configuration details — each referenced from the body ("full results in Appendix A.2").
  • Repository: the partitioner implementation, per-dataset configs, the raw sweep logs, and the plotting scripts.
  • Camera-ready fates decided at submission time: proof → compress to one column; seven-dataset table → move to repo with a pointer; parameter sweep → cut, summary sentence stays.

Nothing in the appendix is load-bearing for the score; everything in it answers a question a reviewer might ask. That is the target state.

Appendix anti-patterns seen at this venue

  • The overflow appendix: paragraphs that clearly belong to Section 4 but were pushed out at the page limit, complete with dangling "as discussed above" references. Reviewers read it as a 9th content page smuggled past the budget.
  • The dataset dump: twenty per-dataset tables with no summary statistic in the body; the body should carry the aggregate, the appendix the breakdown.
  • The unreviewed method: a "practical extension" appearing only in the appendix and then claimed in the conclusion — claims live where reviewers score them.
  • The stale appendix: numbers regenerated in the body but not in the appendix after a late pipeline fix; run the consistency diff before upload.

Cycle-volatile mechanics to reconfirm

  • Whether the current cycle caps appendix length at submission or allows separate supplementary uploads in the OpenReview form (待核实 per cycle).
  • Whether reviewers are instructed that appendix reading is optional — assume yes and write the body accordingly.
  • The exact camera-ready arithmetic: the 9-content/3-refs+appendix/12-total split is the 2026 rule; later cycles may rebalance it.

Output format

text
[Container split] body: <sections> / appendix: <sections> / repo: <items>
[Standalone test] body scoreable without appendix: yes / no -> <promotions needed>
[Orphan check] appendix sections w/o body references: <list or none>
[Camera-ready fates] <section -> migrate/compress/move-to-repo/cut>
[Resubmission page] present + point-by-point / N-A
[Anonymity] appendix + repo sweep: clean / findings

© 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 KDD-Skills/skills/kdd-supplementary of brycewang-stanford/Awesome-Journal-Skills.

Open the folder on GitHubat commit 932eb23

Compare with similar skills

Kdd Supplementary 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.

Kdd Supplementary compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Kdd Supplementary this skillbrycewang-stanford/Awesome-Journal-Skills1.2k—~1.7kAutomated safety check: PassMIT
Code Splittingthedaviddias/Front-End-Checklist74k—~492Automated safety check: PassMIT
Splitting Oversized ModulesPostHog/posthog40k—~2.2kAutomated safety check: PassCustom licence
SplitsBankrBot/skills1.2k—~3.9kAutomated safety check: PassNone
Mcore Split PRNVIDIA/Megatron-LM18k—~1.4kAutomated safety check: PassApache-2.0
Stack Split Commitmozilla-firefox/firefox13k—~1.3kAutomated safety check: PassCustom licence

Similar skills

  • Code Splitting

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing large SPA bundles, new dependency additions, or routes that feel slow to hydrate.

    74k GitHub stars~492 tokensUpdated 4 days ago
    Auto-check passed

  • Splitting Oversized Modules

    PostHog/posthog

    Official

    Split an oversized Python module (a thousand-plus-line logic.py, models.py, api.py, or its test file) into a package of one module per concern, mechanically and provably without changing behavior.

    40k GitHub stars~2.2k tokensUpdated today
    Frontend & DesignAuto-check passed

  • Splits

    BankrBot/skills

    Use Splits with Bankr for onchain treasury operations: secure assets, process revenue, manage operating subaccounts, pay expenses, govern contracts, and maintain clean accounting books.

    1.2k GitHub stars~3.9k tokensUpdated today
    Business, Finance & HRAuto-check passed

  • Mcore Split PR

    NVIDIA/Megatron-LM

    Official

    Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

    18k GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Stack Split Commit

    mozilla-firefox/firefox

    Split one large or hard-to-review commit into several commits that each stand on their own for review, in a git or a Jujutsu (jj) checkout.

    13k GitHub stars~1.3k tokensUpdated today
    DevelopmentAuto-check passed

  • Splitting Datasets

    foryourhealth111-pixel/Vibe-Skills

    Split datasets into training, validation, and test partitions with the right stratification and temporal rules.

    3.6k GitHub stars~346 tokensUpdated 1 mo ago
    Data & AnalyticsAuto-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 13 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 13 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 13 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 13 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 13 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 13 days ago
    Auto-check passed

Questions about Kdd Supplementary

What does Kdd Supplementary do?

A skill your agent uses when splitting a KDD paper across its 8 content pages, the optional appendix after the references, and the cited repository, under the camera-ready rule capping references…. Kdd Supplementary is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when splitting a KDD paper across its 8 content pages, the optional appendix after the references, and the cited repository, under the camera-ready rule capping references plus appendix at 3 of 12 pages.

When should I use Kdd Supplementary?

Kdd Supplementary fits situations like: splitting a KDD paper across its 8 content pages; the optional appendix after the references; the cited repository; under the camera-ready rule capping references plus appendix at 3 of 12 pages.

How do I install Kdd Supplementary in Claude Code?

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

How do I install Kdd Supplementary in Codex?

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

Can I use Kdd Supplementary 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 kdd-supplementary -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kdd-supplementary, .gemini/skills/kdd-supplementary, .github/skills/kdd-supplementary and .opencode/skills/kdd-supplementary in your project.

What does Kdd Supplementary need to run?

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

Does Kdd Supplementary 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 Kdd Supplementary 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 Kdd Supplementary use?

Kdd Supplementary 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 Kdd Supplementary use?

About 1.7k tokens (SKILL.md is roughly 6.9k 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 Kdd Supplementary?

Skills that share tags, products or a category with Kdd Supplementary: Code Splitting (thedaviddias/Front-End-Checklist, 74k stars), Splitting Oversized Modules (PostHog/posthog, 40k stars), Splits (BankrBot/skills, 1.2k stars) and Mcore Split PR (NVIDIA/Megatron-LM, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Kdd Supplementary?

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.