- 📄 example_input.json
- 📄 example_output.json
- 📄 schema.json
citation-gap
引文缺口识别技能。用于在当前 draft 中找到最需要补的一条 citation 缺口，并产出 query。
10 days ago · Uploaded
Detail →
Daily Featured Skills Count
04/06
04/07
04/08
04/09
04/10
04/11
04/12
♾️ Free & Open Source 🛡️ Secure & Worry-Free
Import Skills
- 📁 agents/
- 📁 assets/
- 📁 docs/
- 📄 .gitignore
- 📄 LICENSE
- 📄 Makefile
academic-search
学术论文搜索、引用分析与元数据提取专用 Skill。 【自动触发条件——出现以下任一信号时立即加载本 Skill，无需用户显式说明】 意图信号（中文）： - 搜论文 / 找论文 / 查论文 / 调研论文 / 检索文献 / 文献综述 / 综述 - 顶会 / 顶刊 / CCF / NeurIPS / ICML / ICLR / ACL / EMNLP / CVPR / KDD / SIGIR / WWW - 引用数 / 被引 / 引用关系 / 引用量 - BibTeX / 参考文献格式 / 导出引用 - 作者发表列表 / 某人的论文 / 某人在哪发了什么 - arXiv / Semantic Scholar / Google Scholar / PubMed / ACM DL / IEEE - 知网 / CNKI / 中国知网 / 学位论文 / 硕士论文 / 博士论文 / 中文文献 / 中文期刊 - PDF 链接 / 论文 PDF / 开放获取 - 摘要 abstract / 元数据 意图信号（英文）： - search paper / find paper / look up paper / literature review / survey - citation count / citation graph / citing / cited by - BibTeX / reference export - top conference / top journal / venue ranking - author publication list / papers by X URL 信号（出现以下域名的链接时自动触发）： - arxiv.org / ar5iv.org - semanticscholar.org - scholar.google.com - dl.acm.org - ieeexplore.ieee.org - pubmed.ncbi.nlm.nih.gov - paperswithcode.com - cnki.net / kns.cnki.net 覆盖平台：arXiv、Semantic Scholar、Google Scholar、ACM DL、IEEE Xplore、PubMed、Papers with Code、CNKI（中国知网）
5 days ago · Uploaded
Detail →
- 📄 SKILL.md
research
Deep research with citation tracking
10 days ago · Uploaded
Detail →
- 📁 evals/
- 📁 scripts/
- 📄 .gitignore
- 📄 citation-guide.md
- 📄 SKILL.md
make-bib
Generate accurate BibTeX entries from authoritative sources (DBLP, ACL Anthology, PMLR, CrossRef, arXiv). Use this skill whenever the user needs a citation, BibTeX entry, bibliography fix, or wants to look up where/whether a paper was published — even if they don't explicitly say "BibTeX." Triggers on: paper titles, arXiv IDs, DOIs, DBLP keys, "cite this paper", "add to references", reference list verification, or any academic citation task. --- # make-bib `$ARGUMENTS` — accepts `arxiv:ID`, `doi:ID`, `dblp:KEY`, `openreview:ID`, a title in quotes, or an abbreviation. For background on how bibliographic sources work and their reliability characteristics, see `${CLAUDE_SKILL_DIR}/citation-guide.md`. ## Principles Each principle exists because a specific class of citation error is common and hard to catch after the fact. **Ask when uncertain.** Citations involve judgment calls — which of two similar titles is the right paper, whether something is workshop or main track, what venue a paper belongs to. Guessing wrong means the user silently gets a wrong citation in their manuscript. Use `AskUserQuestion` for any ambiguous case: multiple candidates, unclear venue, conflicting metadata across sources. **One source per entry.** Every field in a BibTeX entry (title, authors, year, venue) should come from the same source. Mixing metadata across sources — even "just the author order" from a different database — creates entries where no single source can verify the whole record. If sources disagree on a field, use the chosen source as-is or ask the user. **Discovery tools are not citation sources.** Semantic Scholar and Google Scholar optimize for finding papers, not for metadata accuracy. Their venue names, dates, and author formatting frequently contain errors. Use them to locate papers and collect external IDs, then get the actual BibTeX from authoritative sources downstream. **Honest representation.** Citing a preprint as a published paper (or vice versa) is academic misrep
5 days ago · Uploaded
Detail →
‹
1
›
Skill File Structure Sample (Reference)
skill-sample/ ├─ SKILL.md ⭐ Required: skill entry doc (purpose / usage / examples / deps) ├─ manifest.sample.json ⭐ Recommended: machine-readable metadata (index / validation / autofill) ├─ LICENSE.sample ⭐ Recommended: license & scope (open source / restriction / commercial) ├─ scripts/ │ └─ example-run.py ✅ Runnable example script for quick verification ├─ assets/ │ ├─ example-formatting-guide.md 🧩 Output conventions: layout / structure / style │ └─ example-template.tex 🧩 Templates: quickly generate standardized output └─ references/ 🧩 Knowledge base: methods / guides / best practices ├─ example-ref-structure.md 🧩 Structure reference ├─ example-ref-analysis.md 🧩 Analysis reference └─ example-ref-visuals.md 🧩 Visual reference
More Agent Skills specs Anthropic docs: https://agentskills.io/home
SKILL.md Requirements
├─ ⭐ Required: YAML Frontmatter (must be at top) │ ├─ ⭐ name : unique skill name, follow naming convention │ └─ ⭐ description : include trigger keywords for matching │ ├─ ✅ Optional: Frontmatter extension fields │ ├─ ✅ license : license identifier │ ├─ ✅ compatibility : runtime constraints when needed │ ├─ ✅ metadata : key-value fields (author/version/source_url...) │ └─ 🧩 allowed-tools : tool whitelist (experimental) │ └─ ✅ Recommended: Markdown body (progressive disclosure) ├─ ✅ Overview / Purpose ├─ ✅ When to use ├─ ✅ Step-by-step ├─ ✅ Inputs / Outputs ├─ ✅ Examples ├─ 🧩 Files & References ├─ 🧩 Edge cases ├─ 🧩 Troubleshooting └─ 🧩 Safety notes
Why SkillWink?
Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.
We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.
Quick Start:
Import/download skills (.zip/.skill), then place locally:
~/.claude/skills/ (Claude Code)
~/.codex/skills/ (Codex CLI)
One SKILL.md can be reused across tools.
FAQ
Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.
1. What are Agent Skills?
A skill is a reusable capability package, usually including SKILL.md (purpose/IO/how-to) and optional scripts/templates/examples.
Think of it as a plugin playbook + resource bundle for AI assistants/toolchains.
2. How do Skills work?
Skills use progressive disclosure: load brief metadata first, load full docs only when needed, then execute by guidance.
This keeps agents lightweight while preserving enough context for complex tasks.
3. How can I quickly find the right skill?
Use these three together:
- Semantic search: describe your goal in natural language.
- Multi-filtering: category/tag/author/language/license.
- Sort by downloads/likes/comments/updated to find higher-quality skills.
4. Which import methods are supported?
- Upload archive: .zip / .skill (recommended)
- Upload skills folder
- Import from GitHub repository
Note: file size for all methods should be within 10MB.
5. How to use in Claude / Codex?
Typical paths (may vary by local setup):
- Claude Code：~/.claude/skills/
- Codex CLI：~/.codex/skills/
One SKILL.md can usually be reused across tools.
6. Can one skill be shared across tools?
Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.
Example: retrieval + writing + automation scripts as one workflow.
7. Are these skills safe to use?
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
8. Why does it not work after import?
Most common reasons:
- Wrong folder path or nested one level too deep
- Invalid/incomplete SKILL.md fields or format
- Dependencies missing (Python/Node/CLI)
- Tool has not reloaded skills yet
9. Does SkillWink include duplicates/low-quality skills?
We try to avoid that. Use ranking + comments to surface better skills:
- Duplicate skills: compare differences (speed/stability/focus)
- Low quality skills: regularly cleaned up