[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FE6YC3TMJ5XZS7WN3F4SVG":3,"skill-same:01M7FE6YC3TMJ5XZS7WN3F4SVG":48},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7FE6YC3TMJ5XZS7WN3F4SVG","semantic-scholar",null,"Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements \u002Farxiv (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.","CZX-LBJ\u002Fdeepseek-science","CZX-LBJ","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F204594689?v=4","01M7FC59WQ9PFXT04MKGJDCFFT","czx","01M7FC59XB2GW0BKWN9JTDBQS7",1,"MIT","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fskills-codex\u002Fsemantic-scholar\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: semantic-scholar\ndescription: Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements \u002Farxiv (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.\nargument-hint: \"query-or-paper-id\"\nallowed-tools: Bash(*), Read, Write\n---\n\n# Semantic Scholar Paper Search\n\nSearch topic or paper ID: $ARGUMENTS\n\n## Role & Positioning\n\nThis skill is the **published venue** counterpart to `\u002Farxiv`:\n\n| Skill | Source | Best for |\n|-------|--------|----------|\n| `\u002Farxiv` | arXiv API | Latest preprints, cutting-edge unrefereed work |\n| `\u002Fsemantic-scholar` | Semantic Scholar API | **Published** journal\u002Fconference papers (IEEE, ACM, Springer, etc.) with citation counts, venue info, TLDR |\n\n**Do NOT duplicate arXiv's job.** If results contain an `externalIds.ArXiv` field, the paper is also on arXiv — note this but do not re-fetch from arXiv.\n\n## Constants\n\n- **MAX_RESULTS = 10** — Default number of search results.\n- **S2_FETCHER** — canonical name `semantic_scholar_fetch.py`, resolved per\n  [`shared-references\u002Fintegration-contract.md`](..\u002Fshared-references\u002Fintegration-contract.md) §2\n  (Codex-side chain: `$ARIS_REPO\u002Ftools\u002F` → `tools\u002F` → `~\u002F.codex\u002Fskills\u002Fsemantic-scholar\u002F`).\n  Policy D1 — if unresolved (canonical chain exhausted), fall back to inline Python.\n- **DEFAULT_FILTERS** — For general research queries, apply these by default to reduce noise:\n  - `--fields-of-study \"Computer Science,Engineering\"`\n  - `--publication-types JournalArticle,Conference`\n\n> Overrides (append to arguments):\n> - `\u002Fsemantic-scholar \"topic\" - max: 20` — return up to 20 results\n> - `\u002Fsemantic-scholar \"topic\" - type: journal` — only journal articles\n> - `\u002Fsemantic-scholar \"topic\" - type: conference` — only conference papers\n> - `\u002Fsemantic-scholar \"topic\" - min-citations: 50` — only highly-cited papers\n> - `\u002Fsemantic-scholar \"topic\" - year: 2022-` — papers from 2022 onward\n> - `\u002Fsemantic-scholar \"topic\" - fields: all` — remove default field-of-study filter\n> - `\u002Fsemantic-scholar \"topic\" - sort: citations` — bulk search sorted by citation count\n> - `\u002Fsemantic-scholar \"DOI:10.1109\u002F...\"` — fetch a single paper by DOI\n\n## Workflow\n\n### Step 1: Parse Arguments\n\nParse `$ARGUMENTS` for directives:\n\n- **Query or ID**: main search term, or a paper identifier:\n  - DOI: `10.1109\u002FTWC.2024.1234567`\n  - Semantic Scholar ID: `f9314fd99be5f2b1b3efcfab87197d578160d553`\n  - ArXiv: `ARXIV:2006.10685`\n  - Corpus: `CorpusId:219792180`\n- **`- max: N`**: override MAX_RESULTS\n- **`- type: journal|conference|review|all`**: map to `--publication-types`\n- **`- min-citations: N`**: map to `--min-citations`\n- **`- year: RANGE`**: map to `--year` (e.g. `2022-`, `2020-2024`)\n- **`- fields: FIELDS`**: override `--fields-of-study` (use `all` to remove filter)\n- **`- sort: citations|date`**: use `search-bulk` with `--sort citationCount:desc` or `publicationDate:desc`\n\nIf the argument matches a DOI pattern (`10.XXXX\u002F...`), a Semantic Scholar ID (40-char hex), or a prefixed ID (`ARXIV:...`, `CorpusId:...`), skip search and go directly to Step 3.\n\n### Step 2: Search Papers\n\nResolve `$S2_FETCHER` via the canonical strict-safe Codex chain\n(see [`shared-references\u002Fintegration-contract.md`](..\u002Fshared-references\u002Fintegration-contract.md) §2):\n\n```bash\nif [ -z \"${ARIS_REPO:-}\" ] && [ -f .aris\u002Finstalled-skills-codex.txt ]; then\n    ARIS_REPO=$(awk -F'\\t' '$1==\"repo_root\"{print $2; exit}' .aris\u002Finstalled-skills-codex.txt 2>\u002Fdev\u002Fnull) || true\nfi\nS2_FETCHER=\"\"\n[ -n \"${ARIS_REPO:-}\" ] && [ -f \"$ARIS_REPO\u002Ftools\u002Fsemantic_scholar_fetch.py\" ] && S2_FETCHER=\"$ARIS_REPO\u002Ftools\u002Fsemantic_scholar_fetch.py\"\n[ -z \"$S2_FETCHER\" ] && [ -f tools\u002Fsemantic_scholar_fetch.py ] && S2_FETCHER=\"tools\u002Fsemantic_scholar_fetch.py\"\n[ -z \"$S2_FETCHER\" ] && [ -f ~\u002F.codex\u002Fskills\u002Fsemantic-scholar\u002Fsemantic_scholar_fetch.py ] && S2_FETCHER=\"$HOME\u002F.codex\u002Fskills\u002Fsemantic-scholar\u002Fsemantic_scholar_fetch.py\"\n```\n\n**Standard search** (default — relevance-ranked):\n\n```bash\n[ -n \"$S2_FETCHER\" ] && python3 \"$S2_FETCHER\" search \"QUERY\" --max MAX_RESULTS \\\n  --fields-of-study \"Computer Science,Engineering\" \\\n  --publication-types JournalArticle,Conference\n```\n\n**Bulk search** (when `- sort:` is specified, or MAX_RESULTS > 100):\n\n```bash\n[ -n \"$S2_FETCHER\" ] && python3 \"$S2_FETCHER\" search-bulk \"QUERY\" --max MAX_RESULTS \\\n  --sort citationCount:desc \\\n  --fields-of-study \"Computer Science\" \\\n  --year \"2020-\"\n```\n\nIf `semantic_scholar_fetch.py` is not found, fall back to inline Python using `urllib` against `https:\u002F\u002Fapi.semanticscholar.org\u002Fgraph\u002Fv1\u002Fpaper\u002Fsearch`.\n\n**Recommended filter combos** (from testing):\n\n| Goal | Flags |\n|------|-------|\n| High-quality journal papers | `--publication-types JournalArticle --min-citations 10` |\n| CS\u002FEE papers, recent | `--fields-of-study \"Computer Science,Engineering\" --year \"2022-\"` |\n| Foundational \u002F high-impact | `search-bulk --sort citationCount:desc --fields-of-study \"Computer Science\"` |\n| Conference papers only | `--publication-types Conference` |\n\n> **Note**: `--venue` requires exact venue names (e.g. \"IEEE Transactions on Signal Processing\"), not partial matches like \"IEEE\". Avoid using `--venue` in automated flows — prefer `--publication-types` + `--fields-of-study`.\n\n### Step 3: Fetch Details for a Specific Paper\n\nWhen a single paper ID is requested:\n\n```bash\n[ -n \"$S2_FETCHER\" ] && python3 \"$S2_FETCHER\" paper \"PAPER_ID\"\n```\n\nWhere PAPER_ID can be:\n- DOI: `10.1109\u002FTSP.2021.3071210`\n- ArXiv: `ARXIV:2006.10685`\n- CorpusId: `CorpusId:219792180`\n- S2 ID: `f9314fd99be5f2b1b3efcfab87197d578160d553`\n\n### Step 4: De-duplicate Against arXiv\n\nFor each result, check `externalIds.ArXiv`:\n- If present → paper is also on arXiv. Note this in output but do NOT re-fetch via `\u002Farxiv`.\n- If absent → paper is **venue-only** (e.g. IEEE without preprint). This is the unique value of this skill.\n\n### Step 5: Present Results\n\nPresent results as a table:\n\n```text\n| # | Title | Venue | Year | Citations | Authors | Type |\n|---|-------|-------|------|-----------|---------|------|\n| 1 | Deep Learning Enabled... | IEEE Trans. Signal Process. | 2021 | 1364 | Xie et al. | Journal |\n```\n\nFor each paper, also show:\n- **DOI link**: `https:\u002F\u002Fdoi.org\u002FDOI` (for IEEE\u002FACM papers, this is the canonical link)\n- **Open Access PDF**: if `openAccessPdf.url` is non-empty, show it\n- **TLDR**: if available, show the one-line summary\n- **Also on arXiv**: if `externalIds.ArXiv` exists, note the arXiv ID\n\n### Step 6: Detailed Summary\n\nFor each paper (or top 5 if many results):\n\n```markdown\n## [Title]\n\n- **Venue**: [venue name] ([publicationVenue.type]: journal\u002Fconference)\n- **Year**: [year] | **Citations**: [citationCount]\n- **Authors**: [full author list]\n- **DOI**: [doi link]\n- **Fields**: [fieldsOfStudy]\n- **TLDR**: [tldr.text if available]\n- **Abstract**: [abstract]\n- **Open Access**: [openAccessPdf.url or \"Not available\"]\n- **Also on arXiv**: [ArXiv ID if exists, else \"No\"]\n```\n\n### Step 7: Update Research Wiki (if active)\n\n**Required when `research-wiki\u002F` exists in the project**; skip silently\notherwise. Ingest the papers presented to the user. For results with an\n`externalIds.ArXiv` field, use `--arxiv-id`; for venue-only papers (no\narXiv mirror — common for IEEE\u002FACM), fall back to manual metadata:\n\n```\nif [ -d research-wiki\u002F ]:\n    WIKI_SCRIPT=\"\"\n    [ -n \"$ARIS_REPO\" ] && [ -f \"$ARIS_REPO\u002Ftools\u002Fresearch_wiki.py\" ] && WIKI_SCRIPT=\"$ARIS_REPO\u002Ftools\u002Fresearch_wiki.py\"\n    [ -z \"$WIKI_SCRIPT\" ] && [ -f tools\u002Fresearch_wiki.py ] && WIKI_SCRIPT=\"tools\u002Fresearch_wiki.py\"\n    [ -z \"$WIKI_SCRIPT\" ] && [ -f ~\u002F.codex\u002Fskills\u002Fresearch-wiki\u002Fresearch_wiki.py ] && WIKI_SCRIPT=\"$HOME\u002F.codex\u002Fskills\u002Fresearch-wiki\u002Fresearch_wiki.py\"\n    for each paper in results:\n        if paper.externalIds.ArXiv:\n            [ -n \"$WIKI_SCRIPT\" ] && python3 \"$WIKI_SCRIPT\" ingest_paper research-wiki\u002F \\\n                --arxiv-id \"\u003CArXiv>\"\n        else:\n            [ -n \"$WIKI_SCRIPT\" ] && python3 \"$WIKI_SCRIPT\" ingest_paper research-wiki\u002F \\\n                --title \"\u003Ctitle>\" --authors \"\u003Cauthors joined by , >\" \\\n                --year \u003Cyear> --venue \"\u003Cvenue>\" \\\n                [--external-id-doi \"\u003CexternalIds.DOI>\"]\n```\n\nThe helper handles slug \u002F dedup \u002F page \u002F index \u002F log — **do not\nhandwrite `papers\u002F\u003Cslug>.md`**. See\n[`shared-references\u002Fintegration-contract.md`](..\u002Fshared-references\u002Fintegration-contract.md).\nBackfill with `\u002Fresearch-wiki sync --arxiv-ids \u003Cid1>,\u003Cid2>,...` for\narXiv-available papers.\n\n### Step 8: Final Output\n\nSummarize what was done:\n\n- `Found N published papers for \"query\"`\n- `Filters applied: [publication types, fields, year range, etc.]`\n- `N papers are venue-only (not on arXiv)`\n- `Wiki-ingested N papers` (if `research-wiki\u002F` was present)\n\nSuggest follow-up skills:\n\n```text\n\u002Farxiv \"topic\"           - search arXiv preprints (complements this search)\n\u002Fresearch-lit \"topic\"    - multi-source review: Zotero + local PDFs + arXiv + S2\n\u002Fnovelty-check \"idea\"    - verify novelty against literature\n```\n\n## Key Rules\n\n- **Default to filtered search**: Always apply `--fields-of-study` and `--publication-types` unless user says `- fields: all`. Without filters, S2 returns cross-discipline noise (linguistics, psychology, etc.).\n- **Citation count is gold**: S2's citation data is its main advantage over arXiv. Always show `citationCount` prominently and use it to rank\u002Fprioritize results.\n- **Venue metadata matters**: Show `venue` and `publicationVenue.type` (journal vs conference) — this helps users assess paper quality.\n- **DOI is the canonical ID for published papers**: Always show DOI links for IEEE\u002FACM\u002FSpringer papers.\n- **Rate limiting**: S2 API without key is heavily rate-limited (~1 req\u002Fs, strict cooldown). If HTTP 429 occurs, wait and retry. Recommend users set `SEMANTIC_SCHOLAR_API_KEY` env var for higher limits (free at https:\u002F\u002Fwww.semanticscholar.org\u002Fproduct\u002Fapi#api-key-form).\n- **TLDR may be null**: Some publishers (notably IEEE) elide the TLDR field. Fall back to showing the first sentence of the abstract.\n- **openAccessPdf may be empty**: Many IEEE papers are closed access. Always provide the DOI link as fallback.\n- If the S2 API is unreachable, suggest using `\u002Farxiv` or `\u002Fresearch-lit \"topic\" - sources: web` as fallback.\n","# Semantic Scholar Paper Search\n\nSearch topic or paper ID: $ARGUMENTS\n\n## Role & Positioning\n\nThis skill is the **published venue** counterpart to `\u002Farxiv`:\n\n| Skill | Source | Best for |\n|-------|--------|----------|\n| `\u002Farxiv` | arXiv API | Latest preprints, cutting-edge unrefereed work |\n| `\u002Fsemantic-scholar` | Semantic Scholar API | **Published** journal\u002Fconference papers (IEEE, ACM, Springer, etc.) with citation counts, venue info, TLDR |\n\n**Do NOT duplicate arXiv's job.** If results contain an `externalIds.ArXiv` field, the paper is also on arXiv — note this but do not re-fetch from arXiv.\n\n## Constants\n\n- **MAX_RESULTS = 10** — Default number of search results.\n- **S2_FETCHER** — canonical name `semantic_scholar_fetch.py`, resolved per\n  [`shared-references\u002Fintegration-contract.md`](..\u002Fshared-references\u002Fintegration-contract.md) §2\n  (Codex-side chain: `$ARIS_REPO\u002Ftools\u002F` → `tools\u002F` → `~\u002F.codex\u002Fskills\u002Fsemantic-scholar\u002F`).\n  Policy D1 — if unresolved (canonical chain exhausted), fall back to inline Python.\n- **DEFAULT_FILTERS** — For general research queries, apply these by default to reduce noise:\n  - `--fields-of-study \"Computer Science,Engineering\"`\n  - `--publication-types JournalArticle,Conference`\n\n> Overrides (append to arguments):\n> - `\u002Fsemantic-scholar \"topic\" - max: 20` — return up to 20 results\n> - `\u002Fsemantic-scholar \"topic\" - type: journal` — only journal articles\n> - `\u002Fsemantic-scholar \"topic\" - type: conference` — only conference papers\n> - `\u002Fsemantic-scholar \"topic\" - min-citations: 50` — only highly-cited papers\n> - `\u002Fsemantic-scholar \"topic\" - year: 2022-` — papers from 2022 onward\n> - `\u002Fsemantic-scholar \"topic\" - fields: all` — remove default field-of-study filter\n> - `\u002Fsemantic-scholar \"topic\" - sort: citations` — bulk search sorted by citation count\n> - `\u002Fsemantic-scholar \"DOI:10.1109\u002F...\"` — fetch a single paper by DOI\n\n## Workflow\n\n### Step 1: Parse Arguments\n\nParse `$ARGUMENTS` for directives:\n\n- **Query or ID**: main search term, or a paper identifier:\n  - DOI: `10.1109\u002FTWC.2024.1234567`\n  - Semantic Scholar ID: `f9314fd99be5f2b1b3efcfab87197d578160d553`\n  - ArXiv: `ARXIV:2006.10685`\n  - Corpus: `CorpusId:219792180`\n- **`- max: N`**: override MAX_RESULTS\n- **`- type: journal|conference|review|all`**: map to `--publication-types`\n- **`- min-citations: N`**: map to `--min-citations`\n- **`- year: RANGE`**: map to `--year` (e.g. `2022-`, `2020-2024`)\n- **`- fields: FIELDS`**: override `--fields-of-study` (use `all` to remove filter)\n- **`- sort: citations|date`**: use `search-bulk` with `--sort citationCount:desc` or `publicationDate:desc`\n\nIf the argument matches a DOI pattern (`10.XXXX\u002F...`), a Semantic Scholar ID (40-char hex), or a prefixed ID (`ARXIV:...`, `CorpusId:...`), skip search and go directly to Step 3.\n\n### Step 2: Search Papers\n\nResolve `$S2_FETCHER` via the canonical strict-safe Codex chain\n(see [`shared-references\u002Fintegration-contract.md`](..\u002Fshared-references\u002Fintegration-contract.md) §2):\n\n```bash\nif [ -z \"${ARIS_REPO:-}\" ] && [ -f .aris\u002Finstalled-skills-codex.txt ]; then\n    ARIS_REPO=$(awk -F'\\t' '$1==\"repo_root\"{print $2; exit}' .aris\u002Finstalled-skills-codex.txt 2>\u002Fdev\u002Fnull) || true\nfi\nS2_FETCHER=\"\"\n[ -n \"${ARIS_REPO:-}\" ] && [ -f \"$ARIS_REPO\u002Ftools\u002Fsemantic_scholar_fetch.py\" ] && S2_FETCHER=\"$ARIS_REPO\u002Ftools\u002Fsemantic_scholar_fetch.py\"\n[ -z \"$S2_FETCHER\" ] && [ -f tools\u002Fsemantic_scholar_fetch.py ] && S2_FETCHER=\"tools\u002Fsemantic_scholar_fetch.py\"\n[ -z \"$S2_FETCHER\" ] && [ -f ~\u002F.codex\u002Fskills\u002Fsemantic-scholar\u002Fsemantic_scholar_fetch.py ] && S2_FETCHER=\"$HOME\u002F.codex\u002Fskills\u002Fsemantic-scholar\u002Fsemantic_scholar_fetch.py\"\n```\n\n**Standard search** (default — relevance-ranked):\n\n```bash\n[ -n \"$S2_FETCHER\" ] && python3 \"$S2_FETCHER\" search \"QUERY\" --max MAX_RESULTS \\\n  --fields-of-study \"Computer Science,Engineering\" \\\n  --publication-types JournalArticle,Conference\n```\n\n**Bulk search** (when `- sort:` is specified, or MAX_RESULTS > 100):\n\n```bash\n[ -n \"$S2_FETCHER\" ] && python3 \"$S2_FETCHER\" search-bulk \"QUERY\" --max MAX_RESULTS \\\n  --sort citationCount:desc \\\n  --fields-of-study \"Computer Science\" \\\n  --year \"2020-\"\n```\n\nIf `semantic_scholar_fetch.py` is not found, fall back to inline Python using `urllib` against `https:\u002F\u002Fapi.semanticscholar.org\u002Fgraph\u002Fv1\u002Fpaper\u002Fsearch`.\n\n**Recommended filter combos** (from testing):\n\n| Goal | Flags |\n|------|-------|\n| High-quality journal papers | `--publication-types JournalArticle --min-citations 10` |\n| CS\u002FEE papers, recent | `--fields-of-study \"Computer Science,Engineering\" --year \"2022-\"` |\n| Foundational \u002F high-impact | `search-bulk --sort citationCount:desc --fields-of-study \"Computer Science\"` |\n| Conference papers only | `--publication-types Conference` |\n\n> **Note**: `--venue` requires exact venue names (e.g. \"IEEE Transactions on Signal Processing\"), not partial matches like \"IEEE\". Avoid using `--venue` in automated flows — prefer `--publication-types` + `--fields-of-study`.\n\n### Step 3: Fetch Details for a Specific Paper\n\nWhen a single paper ID is requested:\n\n```bash\n[ -n \"$S2_FETCHER\" ] && python3 \"$S2_FETCHER\" paper \"PAPER_ID\"\n```\n\nWhere PAPER_ID can be:\n- DOI: `10.1109\u002FTSP.2021.3071210`\n- ArXiv: `ARXIV:2006.10685`\n- CorpusId: `CorpusId:219792180`\n- S2 ID: `f9314fd99be5f2b1b3efcfab87197d578160d553`\n\n### Step 4: De-duplicate Against arXiv\n\nFor each result, check `externalIds.ArXiv`:\n- If present → paper is also on arXiv. Note this in output but do NOT re-fetch via `\u002Farxiv`.\n- If absent → paper is **venue-only** (e.g. IEEE without preprint). This is the unique value of this skill.\n\n### Step 5: Present Results\n\nPresent results as a table:\n\n```text\n| # | Title | Venue | Year | Citations | Authors | Type |\n|---|-------|-------|------|-----------|---------|------|\n| 1 | Deep Learning Enabled... | IEEE Trans. Signal Process. | 2021 | 1364 | Xie et al. | Journal |\n```\n\nFor each paper, also show:\n- **DOI link**: `https:\u002F\u002Fdoi.org\u002FDOI` (for IEEE\u002FACM papers, this is the canonical link)\n- **Open Access PDF**: if `openAccessPdf.url` is non-empty, show it\n- **TLDR**: if available, show the one-line summary\n- **Also on arXiv**: if `externalIds.ArXiv` exists, note the arXiv ID\n\n### Step 6: Detailed Summary\n\nFor each paper (or top 5 if many results):\n\n```markdown\n## [Title]\n\n- **Venue**: [venue name] ([publicationVenue.type]: journal\u002Fconference)\n- **Year**: [year] | **Citations**: [citationCount]\n- **Authors**: [full author list]\n- **DOI**: [doi link]\n- **Fields**: [fieldsOfStudy]\n- **TLDR**: [tldr.text if available]\n- **Abstract**: [abstract]\n- **Open Access**: [openAccessPdf.url or \"Not available\"]\n- **Also on arXiv**: [ArXiv ID if exists, else \"No\"]\n```\n\n### Step 7: Update Research Wiki (if active)\n\n**Required when `research-wiki\u002F` exists in the project**; skip silently\notherwise. Ingest the papers presented to the user. For results with an\n`externalIds.ArXiv` field, use `--arxiv-id`; for venue-only papers (no\narXiv mirror — common for IEEE\u002FACM), fall back to manual metadata:\n\n```\nif [ -d research-wiki\u002F ]:\n    WIKI_SCRIPT=\"\"\n    [ -n \"$ARIS_REPO\" ] && [ -f \"$ARIS_REPO\u002Ftools\u002Fresearch_wiki.py\" ] && WIKI_SCRIPT=\"$ARIS_REPO\u002Ftools\u002Fresearch_wiki.py\"\n    [ -z \"$WIKI_SCRIPT\" ] && [ -f tools\u002Fresearch_wiki.py ] && WIKI_SCRIPT=\"tools\u002Fresearch_wiki.py\"\n    [ -z \"$WIKI_SCRIPT\" ] && [ -f ~\u002F.codex\u002Fskills\u002Fresearch-wiki\u002Fresearch_wiki.py ] && WIKI_SCRIPT=\"$HOME\u002F.codex\u002Fskills\u002Fresearch-wiki\u002Fresearch_wiki.py\"\n    for each paper in results:\n        if paper.externalIds.ArXiv:\n            [ -n \"$WIKI_SCRIPT\" ] && python3 \"$WIKI_SCRIPT\" ingest_paper research-wiki\u002F \\\n                --arxiv-id \"\u003CArXiv>\"\n        else:\n            [ -n \"$WIKI_SCRIPT\" ] && python3 \"$WIKI_SCRIPT\" ingest_paper research-wiki\u002F \\\n                --title \"\u003Ctitle>\" --authors \"\u003Cauthors joined by , >\" \\\n                --year \u003Cyear> --venue \"\u003Cvenue>\" \\\n                [--external-id-doi \"\u003CexternalIds.DOI>\"]\n```\n\nThe helper handles slug \u002F dedup \u002F page \u002F index \u002F log — **do not\nhandwrite `papers\u002F\u003Cslug>.md`**. See\n[`shared-references\u002Fintegration-contract.md`](..\u002Fshared-references\u002Fintegration-contract.md).\nBackfill with `\u002Fresearch-wiki sync --arxiv-ids \u003Cid1>,\u003Cid2>,...` for\narXiv-available papers.\n\n### Step 8: Final Output\n\nSummarize what was done:\n\n- `Found N published papers for \"query\"`\n- `Filters applied: [publication types, fields, year range, etc.]`\n- `N papers are venue-only (not on arXiv)`\n- `Wiki-ingested N papers` (if `research-wiki\u002F` was present)\n\nSuggest follow-up skills:\n\n```text\n\u002Farxiv \"topic\"           - search arXiv preprints (complements this search)\n\u002Fresearch-lit \"topic\"    - multi-source review: Zotero + local PDFs + arXiv + S2\n\u002Fnovelty-check \"idea\"    - verify novelty against literature\n```\n\n## Key Rules\n\n- **Default to filtered search**: Always apply `--fields-of-study` and `--publication-types` unless user says `- fields: all`. Without filters, S2 returns cross-discipline noise (linguistics, psychology, etc.).\n- **Citation count is gold**: S2's citation data is its main advantage over arXiv. Always show `citationCount` prominently and use it to rank\u002Fprioritize results.\n- **Venue metadata matters**: Show `venue` and `publicationVenue.type` (journal vs conference) — this helps users assess paper quality.\n- **DOI is the canonical ID for published papers**: Always show DOI links for IEEE\u002FACM\u002FSpringer papers.\n- **Rate limiting**: S2 API without key is heavily rate-limited (~1 req\u002Fs, strict cooldown). If HTTP 429 occurs, wait and retry. Recommend users set `SEMANTIC_SCHOLAR_API_KEY` env var for higher limits (free at https:\u002F\u002Fwww.semanticscholar.org\u002Fproduct\u002Fapi#api-key-form).\n- **TLDR may be null**: Some publishers (notably IEEE) elide the TLDR field. Fall back to showing the first sentence of the abstract.\n- **openAccessPdf may be empty**: Many IEEE papers are closed access. Always provide the DOI link as fallback.\n- If the S2 API is unreachable, suggest using `\u002Farxiv` or `\u002Fresearch-lit \"topic\" - sources: web` as fallback.\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25},"Bash(*), Read, Write","query-or-paper-id","main","18193d71ea3441d7c033dbf195b8a7c75ac96f75","packages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fskills-codex\u002Fsemantic-scholar",0,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science","https:\u002F\u002Fgithub.com\u002FCZX-LBJ","一个没事喜欢随便写点代码的小菜鸡\r\n","2026-10-22 09:48:04",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add CZX-LBJ\u002Fdeepseek-science --skill semantic-scholar",{"tool":40,"command":41},"bunx","bunx skills add CZX-LBJ\u002Fdeepseek-science --skill semantic-scholar",{"tool":43,"command":44},"pnpm","pnpm dlx skills add CZX-LBJ\u002Fdeepseek-science --skill semantic-scholar","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fskills-codex\u002Fsemantic-scholar\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7FEEKSNMRMKW6JEK93PFDFY","bio-free-energy-calculations","Performs alchemical free-energy calculations including relative binding free energy (RBFE \u002F FEP+) and absolute binding free energy (ABFE) via OpenFE, FEP+, GROMACS, AMBER pmemd, and OpenMM with explicit lambda scheduling, soft-core potentials, MBAR\u002FBAR analysis, cycle-closure validation, and protocol-appropriate enhanced sampling. Compares ML alternatives (Boltz-2 affinity, DeepDock). Use when ranking analogs by binding affinity beyond docking accuracy, performing prospective lead optimization, or validating SAR predictions.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Ffree-energy-calculations\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7FEE5CTE5QK55CEMXNNVWY9","bio-conformer-generation","Generates 3D conformer ensembles using RDKit ETKDGv3 with knowledge-enhanced distance geometry, MMFF94\u002FUFF force-field optimization, CREST + GFN2-xTB semi-empirical refinement, and macrocycle-aware torsion preferences. Provides explicit decision rules for single vs ensemble conformer use, RMSD pruning, energy windows, conformer count, and force-field choice. Use when preparing 3D ligands for docking, generating descriptor input for 3D QSAR, or sampling macrocycle\u002Fpeptide conformational ensembles.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Fconformer-generation\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7FEDNGFEMFWD1MSEDR5H7CY","bio-admet-prediction","Predicts ADMET properties using ADMETlab 3.0 (119 platform features, including 77 prediction models with modeled-endpoint uncertainty), ADMET-AI, DeepChem MolNet, and chemprop D-MPNN with explicit handling of OECD QSAR principles, applicability domain assessment, calibration, hERG\u002FCYP\u002FAMES endpoints, and PAINS \u002F Lipinski \u002F Ro5 \u002F Veber \u002F BBB druglikeness filters. Use when filtering compounds for drug-likeness, prioritizing leads by predicted safety, or building an in-house ADMET QSAR model.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Fadmet-prediction\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7FED69GFB54FRF7AV5066DN","writing-systems-papers","Paragraph-level structural blueprint for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides page allocation, paragraph templates, and writing patterns. Use when user says \"写系统论文\", \"systems paper structure\", \"OSDI paper\", \"SOSP paper\", or wants fine-grained structural guidance for a systems conference submission.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fwriting-systems-papers\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7FECVVDWZ0X0VEDTCE4B4DZ","wiki-enrich","Fill in the per-paper TODO sections of research-wiki\u002Fpapers\u002F\u003Cslug>.md pages that literature-ingest skills leave as bare scaffolds. Use when user says 'enrich wiki', 'fill paper TODOs', 'wiki body 補完', '把 paper 摘要寫進 wiki', 'research-wiki 自動填', or after a batch ingest that left papers\u002F as TODO scaffolds.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fwiki-enrich\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7FECD4BCJ2MTSBDDSE3ZAJ5","web-debug-search","Search GitHub, Stack Exchange, Chinese technical communities, official documentation, and general developer web sources for software errors, compatibility problems, API usage questions, and real-world workarounds. Use for debugging and discovery only; results are not paper-citation evidence.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fweb-debug-search\u002FSKILL.md",[],[]]