/aris-semantic-scholar

name: aris-semantic-scholar
description: Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /aris-arxiv (preprints) with citation counts, venue metadata, and TLDR. Use when user says "search semantic scholar", "find IEEE papers", "find journal papers", "venue papers", "citation search", or wants published literature beyond arXiv preprints.
argument-hint: query-or-paper-id
allowed-tools: Bash(*), Read, Write
license: MIT
metadata:
  author: wanshuiyin/ARIS
  version: "1.0.0"

Semantic Scholar Paper Search

Search topic or paper ID: $ARGUMENTS

Role & Positioning

This skill is the **published venue** counterpart to `/aris-arxiv`:

| Skill | Source | Best for | |-------|--------|----------| | `/aris-arxiv` | arXiv API | Latest preprints, cutting-edge unrefereed work | | `/aris-semantic-scholar` | Semantic Scholar API | **Published** journal/conference papers (IEEE, ACM, Springer, etc.) with citation counts, venue info, TLDR |

**Do NOT duplicate arXiv's job.** If results contain an `externalIds.ArXiv` field, the paper is also on arXiv — note this but do not re-fetch from arXiv.

Constants

• **MAX_RESULTS = 10** — Default number of search results.
• **FETCH_SCRIPT** — `$ARIS_INFRA/tools/semantic_scholar_fetch.py` (the ARIS helper bundle, located in Step 2). Fall back to inline Python if not found.
• **DEFAULT_FILTERS** — For general research queries, apply these by default to reduce noise:
• `--fields-of-study "Computer Science,Engineering"`
• `--publication-types JournalArticle,Conference`

> Overrides (append to arguments): > - `/aris-semantic-scholar "topic" - max: 20` — return up to 20 results > - `/aris-semantic-scholar "topic" - type: journal` — only journal articles > - `/aris-semantic-scholar "topic" - type: conference` — only conference papers > - `/aris-semantic-scholar "topic" - min-citations: 50` — only highly-cited papers > - `/aris-semantic-scholar "topic" - year: 2022-` — papers from 2022 onward > - `/aris-semantic-scholar "topic" - fields: all` — remove default field-of-study filter > - `/aris-semantic-scholar "topic" - sort: citations` — bulk search sorted by citation count > - `/aris-semantic-scholar "DOI:10.1109/..."` — fetch a single paper by DOI

Workflow

Step 1: Parse Arguments

Parse `$ARGUMENTS` for directives:

• **Query or ID**: main search term, or a paper identifier:
• DOI: `10.1109/TWC.2024.1234567`
• Semantic Scholar ID: `f9314fd99be5f2b1b3efcfab87197d578160d553`
• ArXiv: `ARXIV:2006.10685`
• Corpus: `CorpusId:219792180`
• **`- max: N`**: override MAX_RESULTS
• **`- type: journal|conference|review|all`**: map to `--publication-types`
• **`- min-citations: N`**: map to `--min-citations`
• **`- year: RANGE`**: map to `--year` (e.g. `2022-`, `2020-2024`)
• **`- fields: FIELDS`**: override `--fields-of-study` (use `all` to remove filter)
• **`- sort: citations|date`**: use `search-bulk` with `--sort citationCount:desc` or `publicationDate:desc`

If the argument matches a DOI pattern (`10.XXXX/...`), a Semantic Scholar ID (40-char hex), or a prefixed ID (`ARXIV:...`, `CorpusId:...`), skip search and go directly to Step 3.

Step 2: Search Papers

Locate the fetch script:

# Locate the ARIS helper bundle (skills/aris-infra in Dr. Claw; it sits next to
# this skill's own folder). Non-fatal: the steps below fall back when it is missing.
ARIS_INFRA="${ARIS_INFRA:-}"
if [ ! -f "$ARIS_INFRA/tools/research_wiki.py" ]; then
  ARIS_INFRA=""
  for candidate in \
    "${CLAUDE_SKILL_DIR:-/nonexistent}/../aris-infra" \
    ".claude/skills/aris-infra" \
    ".agents/skills/library/aris-infra" \
    "skills/aris-infra" \
    "${HOME:-/nonexistent}/.claude/skills/aris-infra"; do
    if [ -f "$candidate/tools/research_wiki.py" ]; then ARIS_INFRA="$candidate"; break; fi
  done
fi
if [ -z "$ARIS_INFRA" ]; then
  # Project skill links point into the bundled skills folder, so ../aris-infra
  # resolves through any linked aris-* skill even when aris-infra is not linked.
  for linked in .claude/skills/aris-* .agents/skills/aris-* .agents/skills/library/aris-* .gemini/skills/aris-*; do
    if [ -f "$linked/../aris-infra/tools/research_wiki.py" ]; then ARIS_INFRA="$linked/../aris-infra"; break; fi
  done
fi

If `ARIS_INFRA` is still empty, it is the `aris-infra` folder beside this skill's own folder: set it to that absolute path.

SCRIPT="$ARIS_INFRA/tools/semantic_scholar_fetch.py"
[ -n "$ARIS_INFRA" ] && [ -f "$SCRIPT" ] || SCRIPT=""

**Standard search** (default — relevance-ranked):

python3 "$SCRIPT" search "QUERY" --max MAX_RESULTS \
  --fields-of-study "Computer Science,Engineering" \
  --publication-types JournalArticle,Conference

**Bulk search** (when `- sort:` is specified, or MAX_RESULTS > 100):

python3 "$SCRIPT" search-bulk "QUERY" --max MAX_RESULTS \
  --sort citationCount:desc \
  --fields-of-study "Computer Science" \
  --year "2020-"

If `semantic_scholar_fetch.py` is not found, fall back to inline Python using `urllib` against `https://api.semanticscholar.org/graph/v1/paper/search`.

**Recommended filter combos** (from testing):

| Goal | Flags | |------|-------| | High-quality journal papers | `--publication-types JournalArticle --min-citations 10` | | CS/EE papers, recent | `--fields-of-study "Computer Science,Engineering" --year "2022-"` | | Foundational / high-impact | `search-bulk --sort citationCount:desc --fields-of-study "Computer Science"` | | Conference papers only | `--publication-types Conference` |

> **Note**: `--venue` requires exact venue names (e.g. "IEEE Transactions on Signal Processing"), not partial matches like "IEEE". Avoid using `--venue` in automated flows — prefer `--publication-types` + `--fields-of-study`.

Step 3: Fetch Details for a Specific Paper

When a single paper ID is requested:

python3 "$SCRIPT" paper "PAPER_ID"

Where PAPER_ID can be:

• DOI: `10.1109/TSP.2021.3071210`
• ArXiv: `ARXIV:200