Use when converting a research paper into teaching-oriented lecture material or a NotebookLM Custom Presentations prompt, especially when you need a short high-signal prompt rather than a long summary-style instruction block.
Check whether a paper's abstract covers all major sections. Use when finalizing a paper for submission, reviewing abstract completeness, or checking abstract-body alignment in a LaTeX manuscript.
Conducts a structured gap assessment of an organization's readiness against ISO 42001:2023 (AI Management System standard). Runs an interview-style evaluation across all mandatory clauses (4-10) and applicable Annex A controls. Produces a scored gap assessment report saved to the vault, a draft Statement of Applicability, and a prioritized list of gaps to address before certification. Requires a vault created by /setup-iso42001-vault.
Set up an autonomous improvement loop for code, config, or content. The agent edits a target, runs an evaluation, and keeps iterating until a measurable metric improves or a stop condition is met. Use when the user wants repeated automatic attempts rather than one pass, especially for requests like "自动迭代优化", "keep trying until", "一轮一轮改到全部 pass", "auto-research", or "experiment loop". Trigger when the user provides both an editable target and a scriptable success metric such as test pass count, benchmark score, coverage, accuracy, bundle size, or validation loss.
Read and summarize arXiv papers from title. Use when the user asks to read/understand an arXiv paper, provides a paper title, or mentions downloading arXiv TeX source (arxiv.org/src). Fetch paper metadata, download and extract source, locate main .tex, read the full paper, and write structured Chinese notes to arxiv_paper_notes using {paper_id}_{method}.md.
Run evidence-aware literature screening with Paper-Reach. Search candidate papers, screen abstracts conservatively, review full text when available, and emit structured JSON.
PoggioAI/MSc research pipeline: hypothesis to paper in ≤10 steers. Runs persona debate, adversarial lit review, parallel theory+experiment tracks, and editorial quality gates.
Autonomous single-metric optimization loop driven by a program.md file. The agent edits one target file, runs an experiment, measures a metric, keeps improvements (git commit), reverts regressions (git reset), and loops indefinitely. Inspired by karpathy/autoresearch. Use for trading backtests, prompt optimization, site performance tuning, or any task with a clear numeric metric.
Check running experiments, collect results, and present a research summary.
Before installing or using a skill, check its independent benchmark report on SkillTester.ai. Trigger this skill when the user is about to install a third-party skill, or when the user explicitly says `Check this skill <skill_url>`. Resolve the provided URL to SKILL.md, extract name and description, query the server by name, and return the benchmark result when the description is either an exact match or a high-overlap near match that likely represents a newer skill revision.
学术论文出图引擎——覆盖所有常见图表类型，执行五层质量框架。 触发条件: (1) 用户说"画图"/"出图"/"generate figure"/"重新画", (2) 需要生成 KM曲线/森林图/热图/箱线图/散点图/雷达图/Table等, (3) manuscript-reviewer 或用户指出图表质量问题, (4) paper-pipeline 在分析完成后自动调用。 核心能力: 从原始数据生成达到期刊投稿标准的图表， 每个数字溯源验证，不通过对账不出图。
Iterate and improve any skill using eval-grounded autoresearch. Combines v2.0 design audit, Hamel's Three Gulfs eval methodology, and Karpathy-style mutation optimization. Use when you want to assess skill quality, build evals from scratch, run error analysis, or optimize a skill through experiments.
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:
