Agent skill

sigir-related-work

Use when positioning a paper against the information-retrieval literature for SIGIR — tracing lineage through SIGIR/TOIS/TREC canon, contrasting mechanisms with the nearest recent SIGIR papers, avoiding venue misattribution (DPR is EMNLP, ANCE is ICLR, NCF is WWW), and handling arXiv-era concurrent work in a fast-moving field.

brycew6m4,252★ · +31/wk · 3 repos on radarProfile →
claude-codeMIT
Install
npx skills add brycewang-stanford/Awesome-Journal-Skills --skill sigir-related-work --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 7 KB
Bundled scripts: none
Path: SIGIR-Skills/skills/sigir-related-work/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 984 · +31 this week
Language: Stata
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# SIGIR Related Work At SIGIR, related work is a credibility exam graded by reviewers who may have written the papers you cite. IR is an old field with a living canon: a related-work section that starts retrieval history at BERT signals a visitor from an adjacent community, which primes every other judgment. This skill builds positioning that demonstrates lineage fluency and states the delta mechanically. ## The lineage obligation An IR paper is expected to know which research line it extends and to cite the line's origin plus its current SIGIR-era frontier. The canonical lines and their anchors (all venue-verified — see `../../resources/exemplars/library.md`): | Line | Origin anchor | What your delta sentence must contrast | |---|---|---| | Probabilistic/lexical ranking | Robertson-era BM25 work; Ponte & Croft's language-modeling approach (SIGIR 1998) | Which term-weighting/estimation assumption you change | | LM smoothing & estimation | Zhai & Lafferty (SIGIR 2001) | Estimation method, prior, or evidence source | | Graded evaluation | Järvelin & Kekäläinen (SIGIR 2000; nDCG lineage) | Which validity gap your metric/protocol closes | | Neural re-ranking / late interaction | ColBER

What's inside
Steps it walks through
  1. The lineage obligation
  2. Venue misattribution: the IR-specific trap
  3. The delta sentence, mechanized
  4. Concurrent and arXiv-era work
  5. Positioning failures that cost accepts
  6. The reviewer-eye test
  7. Placement under the 9-page budget
  8. Output format
Commands it runs
Bibliography audit: flag entries whose venue field is suspiciously vague
grep -nE "booktitle.*(arXiv|CoRR|preprint)" refs.bib      # published since?
grep -nE "@misc|howpublished" refs.bib                     # citing repos as papers?
grep -in "sigir" refs.bib | wc -l                          # lineage presence check
More from Awesome-Journal-Skills
All skills →
About this skill
What does the sigir-related-work skill do?

Use when positioning a paper against the information-retrieval literature for SIGIR — tracing lineage through SIGIR/TOIS/TREC canon, contrasting mechanisms with the nearest recent SIGIR papers, avoiding venue misattribution (DPR is EMNLP, ANCE is ICLR, NCF is WWW), and handling arXiv-era concurrent work in a fast-moving field.

How do I install it?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill sigir-related-work --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From brycewang-stanford/Awesome-Journal-Skills, a repository with 984 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going