Research industry standards and best practices, identify viable approaches for a given technical or architectural problem, and produce a structured factual comparison against project-specific constraints. Reports options — does not decide.
Save and organize links for later reading. Use when: user wants to save a URL, manage bookmarks, find a saved link. Don't use when: user just wants to read/fetch a URL (use web_fetch) or research a topic (use research skill).
大学生毕业论文 Word 排版技能。用于先收集学校 Word 模板、学院规范、任务书或示例论文，再对本科或硕士毕业论文进行 Word 版式整理、目录与编号校正、参考文献与图表题注检查，并输出可直接复核的排版执行清单。适用于用户说“给毕业论文排版”“按学校要求整理 Word”“检查论文格式”“论文目录标题编号不对”“把这篇论文整理成提交版”等场景。
This skill should be used when optimizing AMD GPU kernels on MI300 using the aiter project, including running op tests, benchmarking, iterating on kernel changes, and recording results in the kernel experiment database.
Performs GPU kernel correctness and performance evaluation and LLM inference benchmarking with Magpie. Analyzes single or multiple kernels (HIP/CUDA/PyTorch), compares kernel implementations, runs vLLM/SGLang benchmarks with profiling and TraceLens, and runs gap analysis on torch traces. Creates kernel config YAMLs, discovers kernels in a project, and queries GPU specs. Use when the user mentions Magpie, kernel analyze or compare, HIP/CUDA kernel evaluation, vLLM/SGLang benchmark, gap analysis, TraceLens, creating kernel configs, or discovering GPU kernels.
Structured B2B software vendor evaluation for buyers. Researches your company, asks domain-expert questions, engages vendor AI agents via the Salespeak Frontdoor API, scores vendors across 7 dimensions, and produces a comparative recommendation with evidence transparency. Use when asked to evaluate, compare, or research B2B software vendors.
论文全能处理工具。每当用户上传论文 PDF、粘贴论文文本/摘要，或提到"论文"、"paper"、"文献"、"arxiv"时必须使用此 skill。功能包括：深度分析报告、思维导图、审稿意见、宣传推广脚本、播客音频生成。即使用户只说"帮我看这篇论文"或直接上传 PDF 也必须触发。
当 Supervisor 说"调研""survey""了解研究现状"，或需要系统了解某主题的文献全貌时，搜索外部文献、批量 digest、综合生成调研报告
Guide for writing the abstract of an academic economics paper. Use this skill whenever the user asks for help writing, drafting, revising, or structuring an abstract for an economics paper - whether empirical micro, development economics, applied economics, or related fields. Also trigger when the user mentions "abstract," "paper summary," or asks how to compress their findings into a short description. This skill synthesizes best practices from David Evans (CGDev), Marc Bellemare, and patterns observed in top economics journals (AER, QJE, AEJ: Applied, etc.). --- # How to Write the Abstract of an Economics Paper A lot of people will read no further than the abstract of your paper to decide whether it is worth reading, sharing, or citing. Some will not even get past the title. The abstract is your most compressed sales pitch: it must tell the reader what you did and what you found, clearly and fast. This skill is based primarily on David Evans' analysis of abstracts in top economics journals, supplemented by Marc Bellemare's writing advice, empirical research on abstract readability, and common patterns from AER, QJE, and AEJ: Applied papers. ## The Evidence on What Works Before getting to structure, two empirical facts worth knowing: **Readability predicts citations.** Dowling and others examined abstracts in Economics Letters and found that abstracts with simpler words and shorter sentences were associated with more citations. As Bellemare puts it: do not confuse lack of intelligibility with intellectual rigor. **Accessibility expands your audience.** Bellemare's rule of thumb: if your title is not repellent and your abstract is intelligible to people outside your narrow subfield, you have expanded the scope of your citations tenfold - because many people cite papers they have only read the abstract of. --- ## The Core Structure Abstracts in top economics journals follow a compressed version of the introduction formula. Evans identifies five ingredients of a good
Autonomous experiment loop for optimization research. Use when the user wants to: - Optimize a metric through systematic experimentation (ML training loss, test speed, bundle size, build time, etc.) - Run an automated research loop: try an idea, measure it, keep improvements, revert regressions, repeat - Set up autoresearch for any codebase with a measurable optimization target Implements the autoresearch pattern with MAD-based confidence scoring, git branch isolation, and structured experiment logging. --- # Autoresearch
Use when preparing to engage a target account, researching a company before outreach, or building pre-call intelligence. Triggers: 'research this company', 'account brief for [company]', 'company research', 'what do I need to know about [company]', 'pre-outreach research'.
Fetch, classify, and summarize papers from multiple sources (arXiv, etc.) with AI-powered multi-language summaries and email delivery.
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
├─ ⭐ 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
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.
Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.
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.
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.
Use these three together:
Note: file size for all methods should be within 10MB.
Typical paths (may vary by local setup):
One SKILL.md can usually be reused 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.
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
Most common reasons:
We try to avoid that. Use ranking + comments to surface better skills:
