A skill your agent uses when positioning a paper against prior literature for WSDM - locating the work inside WSDM's own research lineages (click models, unbiased LTR, sequential recommendation…

MITAuto-check passedResearch & Science

Install Wsdm Related Work

skills CLI
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill wsdm-related-work -a claude-code

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

GitHub CLI
$ gh skill install brycewang-stanford/Awesome-Journal-Skills wsdm-related-work --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/WSDM-Skills/skills/wsdm-related-work .claude/skills/wsdm-related-work && 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
wsdm-related-work
GitHub stars
1.2k
Token cost
~1.6k tokens
SKILL.md length
606 words
Files
1
Skills in repo
2,387
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when positioning a paper against prior literature for WSDM - locating the work inside WSDM's own research lineages (click models, unbiased LTR, sequential recommendation…

  • Works in 3 steps: Two or three lineage paragraphs (one per… → One paragraph for adjacent-venue and… → Zero survey paragraphs. History lessons…
  • Positioning a paper against prior literature for WSDM - locating the work inside WSDMs own research lineages (click models
  • SKILL.md covers Join a lineage, don't float free, The contrast sentence, Sibling-venue positioning and Misattribution traps, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Wsdm Related Work is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when positioning a paper against prior literature for WSDM - locating the work inside WSDM's own research lineages (click models, unbiased LTR, sequential recommendation, community detection), contrasting against SIGIR/KDD/WWW/CIKM/RecSys neighbors, venue-misattribution traps, and compressing the section for the tight page budget.

Its SKILL.md is about 1.6k 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 Literature review and Positioning and messaging. 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

  • Positioning a paper against prior literature for WSDM - locating the work inside WSDMs own research lineages (click models
  • Sequential recommendation
  • Community detection)
  • Contrasting against SIGIR/KDD/WWW/CIKM/RecSys neighbors

Example prompts

  • “/wsdm-related-work”

Workflow steps

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

  1. Two or three lineage paragraphs (one per relevant lineage), each ending in
  2. One paragraph for adjacent-venue and concurrent work.
  3. Zero survey paragraphs. History lessons ("early work in information

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

Wsdm Related Work loads about 1.6k tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 606 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~89
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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). 606 words, ~1,562 tokens.

Download SKILL.mdSave it as .claude/skills/wsdm-related-work/SKILL.md (or your agent's skills folder).
name
wsdm-related-work
description
Use when positioning a paper against prior literature for WSDM - locating the work inside WSDM's own research lineages (click models, unbiased LTR, sequential recommendation, community detection), contrasting against SIGIR/KDD/WWW/CIKM/RecSys neighbors, venue-misattribution traps, and compressing the section for the tight page budget.

Position a submission against the literature the WSDM PC actually knows. At a small single-track venue, related-work errors are unusually visible: the person who wrote the paper you mis-cited may be your SPC. The section's job in a 9-page-inclusive budget is positioning - establishing which conversation the paper joins and what precisely it adds - not coverage.

Join a lineage, don't float free

WSDM has multi-edition research lineages, and reviewers instinctively slot new work into them. Naming your lineage does the slotting for them (all rows verified against ACM DL/dblp; see ../../resources/exemplars/library.md):

LineageAnchor papers at WSDMIf your paper is here, position against
Click models / position biasCraswell et al. 2008 (cascade model)Subsequent click-model and propensity work
Unbiased learning-to-rankJoachims et al. 2017The ULTR line it started, incl. recent WSDM/SIGIR follow-ups
Sequential recommendationTang & Wang 2018 (Caser)The CNN/attention sequential-rec succession
RL / bandits for recommendationChen et al. 2019 (Top-K off-policy, YouTube)Off-policy and bandit rec work since
Community detection / graph miningYang & Leskovec 2013 (BigCLAM)Scalable overlapping-community successors

If no WSDM lineage fits, that is routing information, not a citation problem - run wsdm-topic-selection before writing further.

The contrast sentence

For each of the three to five closest works, write one sentence with this anatomy: their mechanism, their setting, the delta, why the delta matters here. Citation-listing ("[3,7,12] studied recommendation") communicates nothing and spends budget.

text
Template:
  <Closest work> <does X by mechanism M> <in setting S>; we differ by <Δ>,
  which matters because <consequence in our data regime>.

Instance (fictional):
  CDR-Net transfers cross-domain preferences via shared user embeddings,
  assuming overlapping user sets; we require no user overlap, which is the
  common case for the partner-site logs we target.

Reviewers at this venue read contrast sentences as competence signals: they show you know the mechanism, not just the title.

Sibling-venue positioning

WSDM's neighborhood is dense - SIGIR, KDD, TheWebConf (WWW), CIKM, RecSys, and ICWSM publish adjacent work continuously. Rules:

  • Cite by contribution, not by venue prestige. Missing the directly relevant RecSys paper because you only searched WSDM+SIGIR is a standard negative-review trigger.
  • Recency bar: at minimum, sweep the last two editions of WSDM, SIGIR, KDD, WWW, and CIKM for your exact topic before claiming novelty; the overlap between these communities makes "we are the first" claims fragile.
  • Concurrent work: if a recent preprint does something similar, cite and contrast it calmly; at a no-rebuttal venue you cannot later explain that you "were unaware" - the paper must already handle it.
Show full SKILL.md (248 more words)Show less

Misattribution traps

Famous papers cluster in this neighborhood, and attributing them to the wrong venue damages credibility with reviewers who know exactly where they appeared. Verified placements to guard against common mix-ups:

  • DeepWalk, node2vec, XGBoost - KDD papers, not WSDM.
  • BERT4Rec - CIKM 2019, not WSDM/SIGIR.
  • Neural Graph Collaborative Filtering (NGCF) - SIGIR 2019.
  • "WTF: The Who to Follow Service at Twitter" - WWW 2013.
  • SASRec - ICDM 2018.
  • Conversely, the five lineage anchors in the table above are WSDM papers - citing Craswell et al.'s cascade model or Caser to another venue is the same error mirrored.

When in doubt, resolve the venue on dblp before the citation enters the draft; never trust memory or a secondhand BibTeX file for venue fields.

Worked positioning paragraph (fictional)

A dwell-time debiasing paper joining the unbiased-LTR lineage might position itself in four sentences - lineage entry, two contrasts, one boundary:

text
Learning from logged interactions without inheriting their biases is a
long-standing WSDM concern, from cascade-style click models [Craswell et
al., 2008] to counterfactual learning-to-rank [Joachims et al., 2017].
Propensity-based ULTR corrects exposure bias but treats post-click signals
as unbiased; we show dwell time carries its own salience confound and
extend the counterfactual framework to post-click behavior. Session-aware
rerankers <fictional cites> model dwell directly but require editorial
labels for calibration; our estimator calibrates from abandonment
behavior alone. Unlike both lines, we assume no access to the production
propensity model, matching the partner-platform setting of Section 5.

Note what the paragraph never does: survey the field, praise prior work emptily, or cite anything it does not contrast. Each sentence moves the paper's coordinates.

Compression for the budget

Target half a page to three-quarters. Structure that survives compression:

  1. Two or three lineage paragraphs (one per relevant lineage), each ending in a contrast sentence for the closest works.
  2. One paragraph for adjacent-venue and concurrent work.
  3. Zero survey paragraphs. History lessons ("early work in information retrieval...") belong in theses.

Where the intro already contrasts the closest work (it should - see wsdm-writing-style), the related-work section elaborates rather than repeats: same contrast, mechanism-level detail.

Output format

text
[Lineage] WSDM lineage(s) joined: <named or "none - route check">
[Contrast sentences] closest 3-5 works each have mechanism-level contrast: yes / gaps
[Neighbor sweep] WSDM/SIGIR/KDD/WWW/CIKM last-2-editions checked: date + hits
[Misattribution scan] venue fields dblp-verified: yes / fixes made
[Budget] section length vs target: pass / compress list

© 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 WSDM-Skills/skills/wsdm-related-work of brycewang-stanford/Awesome-Journal-Skills.

Open the folder on GitHubat commit 932eb23

Compare with similar skills

Wsdm Related Work 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.

Wsdm Related Work compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Wsdm Related Work this skillbrycewang-stanford/Awesome-Journal-Skills1.2k—~1.6kAutomated safety check: PassMIT
Gec Literature Positioningfranklee16/academic-research-skills2231 repos~855Automated safety check: PassNone
Jpsp Literature Positioningfranklee16/academic-research-skills2231 repos~850Automated safety check: PassNone
Rje Literature Positioningfranklee16/academic-research-skills2231 repos~720Automated safety check: PassNone
Icml Related Workfranklee16/academic-research-skills2231 repos~402Automated safety check: PassNone
Ieee Paper ReaderCloudWave818/ieee-skills359—~591Automated safety check: PassMIT

Similar skills

  • Gec Literature Positioning

    franklee16/academic-research-skills

    A skill your agent uses when positioning a Global Environmental Change (GEC) manuscript against the relevant literatures.

    223 GitHub starsUsed in 1 repo~855 tokens
    Research & ScienceAuto-check passed
  • Jpsp Literature Positioning

    franklee16/academic-research-skills

    A skill your agent uses when positioning a Journal of Personality and Social Psychology (JPSP) manuscript against the literatures its section's readers expect, building the long-format introduction…

    223 GitHub starsUsed in 1 repo~850 tokens
    Research & ScienceAuto-check passed
  • Rje Literature Positioning

    franklee16/academic-research-skills

    A skill your agent uses to position a manuscript against the industrial-organization frontier for The RAND Journal of Economics (RJE) — staking the contribution against prior IO work without a…

    223 GitHub starsUsed in 1 repo~720 tokens
    Research & ScienceAuto-check passed
  • Icml Related Work

    franklee16/academic-research-skills

    A skill your agent uses when positioning an ICML submission against close ML literature, concurrent ICML submissions, recent public papers, workshop papers, ICLR/AISTATS/NeurIPS neighbors, and prior…

    223 GitHub starsUsed in 1 repo~402 tokens
    Research & ScienceAuto-check passed
  • Ieee Paper Reader

    CloudWave818/ieee-skills

    Read, decompose, and analyze IEEE-style papers using routed technical-reading workflows.

    359 GitHub stars~591 tokensUpdated 2 mo ago
    Research & ScienceAuto-check passed
  • Novelty Matrix

    WILLOSCAR/research-units-pipeline-skills

    A skill your agent uses when paper-review needs overlap/delta positioning against provided related work.

    513 GitHub stars~364 tokensUpdated 6 days ago
    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 Wsdm Related Work

What does Wsdm Related Work do?

A skill your agent uses when positioning a paper against prior literature for WSDM - locating the work inside WSDM's own research lineages (click models, unbiased LTR, sequential recommendation…. Wsdm Related Work is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when positioning a paper against prior literature for WSDM - locating the work inside WSDM's own research lineages (click models, unbiased LTR, sequential recommendation, community detection), contrasting against SIGIR/KDD/WWW/CIKM/RecSys neighbors, venue-misattribution traps, and compressing the section for the tight page budget.

When should I use Wsdm Related Work?

Wsdm Related Work fits situations like: positioning a paper against prior literature for WSDM - locating the work inside WSDMs own research lineages (click models; sequential recommendation; community detection); contrasting against SIGIR/KDD/WWW/CIKM/RecSys neighbors.

How do I install Wsdm Related Work in Claude Code?

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

How do I install Wsdm Related Work in Codex?

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

Can I use Wsdm Related Work 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 wsdm-related-work -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/wsdm-related-work, .gemini/skills/wsdm-related-work, .github/skills/wsdm-related-work and .opencode/skills/wsdm-related-work in your project.

What does Wsdm Related Work need to run?

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

Does Wsdm Related Work 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 Wsdm Related Work 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 Wsdm Related Work use?

Wsdm Related Work 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 Wsdm Related Work use?

About 1.6k tokens (SKILL.md is roughly 6.2k 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 Wsdm Related Work?

Skills that share tags, products or a category with Wsdm Related Work: Gec Literature Positioning (franklee16/academic-research-skills, 223 stars), Jpsp Literature Positioning (franklee16/academic-research-skills, 223 stars), Rje Literature Positioning (franklee16/academic-research-skills, 223 stars) and Icml Related Work (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 Wsdm Related Work?

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.