/deepxiv

name: deepxiv
description: Search and progressively read open-access academic papers through DeepXiv. Use when the user wants layered paper access, section-level reading, trending papers, or DeepXiv-backed literature retrieval.
argument-hint: "[query-or-paper-id]"
allowed-tools: Bash(*), Read, Write

DeepXiv Paper Search & Progressive Reading

Search topic or paper ID: $ARGUMENTS

Role & Positioning

DeepXiv is the **progressive-reading** literature source:

| Skill | Source | Best for | |-------|--------|----------| | `/arxiv` | arXiv API | Batch search, PDF download, metadata | | **`/deepxiv`** | **DeepXiv SDK** | **Progressive section-level reading** | | `/semantic-scholar` | S2 API | Published venue metadata, citation counts | | `/alphaxiv` | www.alphaxiv.org | Instant LLM-optimized summary of one paper, with LaTeX source fallback |

Use DeepXiv when you want to avoid loading full papers too early.

Constants

• **DEEPXIV_FETCHER** — canonical name `deepxiv_fetch.py`, resolved per

[`shared-references/integration-contract.md`](../shared-references/integration-contract.md) §2 (Policy D1 — primary + fallback cascade). If unresolved (canonical chain exhausted), fall back to the raw `deepxiv` CLI (documented per command below).

• **MAX_RESULTS = 10** — Default number of results to return.

> Overrides (append to arguments): > - `/deepxiv "agent memory" - max: 5` — top 5 results > - `/deepxiv "2409.05591" - brief` — quick paper summary > - `/deepxiv "2409.05591" - head` — metadata + section overview > - `/deepxiv "2409.05591" - section: Introduction` — read one section only > - `/deepxiv "trending" - days: 14 - max: 10` — trending papers > - `/deepxiv "karpathy" - web` — DeepXiv web search > - `/deepxiv "258001" - sc` — Semantic Scholar metadata by ID

Setup

DeepXiv is optional. If the CLI is not installed, tell the user:

pip install deepxiv-sdk

Authentication is handled by the third-party `deepxiv-sdk` CLI using `DEEPXIV_TOKEN`. In [SDK 1.2.2](https://pypi.org/project/deepxiv-sdk/1.2.2/), a command that needs a token auto-registers one if none is configured and saves it to `~/.env`. With `python-dotenv` installed, the CLI also loads `~/.env` and the current project's `.env` on startup. Providing `DEEPXIV_TOKEN` in the CLI's environment skips automatic registration and token saving, but does not disable that file loading. This skill does not need to read those files or display tokens; leave authentication to the CLI.

Workflow

Step 1: Parse Arguments

Parse `$ARGUMENTS` for:

• **Query or ID**: a paper topic, arXiv ID, or Semantic Scholar ID
• **`- max: N`**: override `MAX_RESULTS`
• **`- brief`**: fetch paper brief
• **`- head`**: fetch metadata and section map
• **`- section: NAME`**: fetch one named section
• **`- trending`** or query `trending`: fetch trending papers
• **`- days: 7|14|30`**: trending time window
• **`- web`**: run DeepXiv web search
• **`- sc`**: fetch Semantic Scholar metadata by ID

If the main argument looks like an arXiv ID and no explicit mode is given, default to `- brief`.

Step 2: Locate the Adapter

Resolve `$DEEPXIV_FETCHER` via the canonical strict-safe chain (see [`shared-references/integration-contract.md`](../shared-references/integration-contract.md) §2). Policy D1 cascade: the resolved adapter is preferred; if unresolved (canonical chain exhausted), fall back to raw `deepxiv` CLI commands documented in Step 3.

cd "$(git rev-parse --show-toplevel 2>/dev/null || pwd)" || exit 1
if [ -z "${ARIS_REPO:-}" ] && [ -f .aris/installed-skills.txt ]; then
    ARIS_REPO=$(awk -F'\t' '$1=="repo_root"{print $2; exit}' .aris/installed-skills.txt 2>/dev/null) || true
fi
if [ -z "${ARIS_REPO:-}" ] && [ -f "$HOME/.aris/repo" ]; then
    ARIS_REPO=$(cat "$HOME/.aris/repo" 2>/dev/null) || true
fi
DEEPXIV_FETCHER=".aris/tools/deepxiv_fetch.py"
[ -f "$DEEPXIV_FETCHER" ] || DEEPXIV_FETCHER="tools/deepxiv_fetch.py"
[ -f "$DEEPXIV_FETCHER" ] || { [ -n "${ARIS_REPO:-}" ] && DEEPXIV_FETCHER="$ARIS_REPO/tools/deepxiv_fetch.py"; }
[ -f "$DEEPXIV_FETCHER" ] || DEEPXIV_FETCHER=""

# Smoke test (optional — adapter resolution shown to user). The cascade
# in Step 3 below branches purely on `[ -n "$DEEPXIV_FETCHER" ]`; a
# resolved-but-non-functional adapter is not currently auto-demoted.
if [ -n "$DEEPXIV_FETCHER" ]; then
  echo "DeepXiv adapter resolved at: $DEEPXIV_FETCHER" >&2
else
  echo "DeepXiv adapter unresolved (canonical chain exhausted); raw deepxiv CLI fallback will be used." >&2
fi

Step 3: Execute the Minimal Command

**Search papers**

python3 "$DEEPXIV_FETCHER" search "QUERY" --max MAX_RESULTS

Fallback:

deepxiv search "QUERY" --limit MAX_RESULTS --format json

**Brief summary**

python3 "$DEEPXIV_FETCHER" paper-brief ARXIV_ID

Fallback:

deepxiv paper ARXIV_ID --brief --format json

**Section map**

python3 "$DEEPXIV_FETCHER" paper-head ARXIV_ID

Fallback:

deepxiv paper ARXIV_ID --head --format json

**Specific section**

python3 "$DEEPXIV_FETCHER" paper-section ARXIV_ID "SECTION_NAME"

Fallback:

deepxiv paper ARXIV_ID --section "SECTION_NAME" --format json

**Trending**

python3 "$DEEPXIV_FETCHER" trending --days 7 --max MAX_RESULTS

Fallback:

deepxiv trending --days 7 --limit MAX_RESULTS --output json

**Web search**

python3 "$DEEPXIV_FETCHER" wsearch "QUERY"

Fallback:

deepxiv wsearch "QUERY" --output json

**Semantic Scholar metadata**

python3 "$DEEPXIV_FETCHER" sc "SEMANTIC_SCHOLAR_ID"

Fallback:

deepxiv sc "SEMANTIC_SCHOLAR_ID" --output json

Step 4: Present Results

When searching, present a compact table:

| # | ID | Title | Year | Citations | Notes |
|---|----|-------|------|-----------|-------|

When reading a paper, show:

• title
• arXiv ID
• authors
• venue/date if available
• TLDR or abstract summa