sigir-topic-selection
Use when deciding whether a project belongs at SIGIR and in which of its tracks — testing whether retrieval is the contribution or the plumbing, forking across full/short/resources/reproducibility/perspectives/industry, and routing misfits to ECIR, CIKM, WSDM, CHIIR, ICTIR, RecSys, TheWebConf, or NLP/ML venues.
Profile →npx skills add brycewang-stanford/Awesome-Journal-Skills --skill sigir-topic-selection --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# SIGIR Topic Selection Two decisions, in order: (1) is this an information-retrieval contribution at all, and (2) which SIGIR track owns it. Both are cheaper to get right in October than to learn from reviews in March. SIGIR 2026's verified lineup — Full, Short, Perspectives, Resources, Reproducibility, Low Resource Environments, and Industry tracks — makes the second decision genuinely multi-way. ## Test 1: is retrieval the contribution or the plumbing? The LLM era floods SIGIR with papers where retrieval is present but incidental. The discriminating question: **if you swapped the retrieval component for an oracle (or a black box), would the contribution survive?** - Survives → the contribution is the downstream system (agent, QA, generation quality); route to an NLP/ML venue and cite IR work properly. - Dies → the contribution is retrieval: ranking quality, efficiency, evaluation validity, user search behavior, or the retrieval-specific part of RAG (candidate quality, index design, retrieval evaluation). SIGIR-shaped. Corollary signals of SIGIR fit: the natural headline table has metric@cutoff columns on named collections; the natural reviewers are IR-evaluation people; the natu
- Test 1: is retrieval the contribution or the plumbing?
- Test 2: the track fork
- Neighbor routing when SIGIR isn't the answer
- Borderline cases, adjudicated
- Timing and prestige honesty
- Scope vocabulary check
- Output format
What does the sigir-topic-selection skill do?
Use when deciding whether a project belongs at SIGIR and in which of its tracks — testing whether retrieval is the contribution or the plumbing, forking across full/short/resources/reproducibility/perspectives/industry, and routing misfits to ECIR, CIKM, WSDM, CHIIR, ICTIR, RecSys, TheWebConf, or NLP/ML venues.
How do I install it?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill sigir-topic-selection --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.