write-a-skill
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
35 minutes ago · Uploaded
Detail →
Daily Featured Skills Count
03/24
03/25
03/26
03/27
03/28
03/29
03/30
♾️ Free & Open Source 🛡️ Secure & Worry-Free
Import Skills
curate
Evolve the Spellbook library. Scan external sources for new skills worth indexing, review observations for improvement opportunities, brainstorm new primitives, investigate existing skills for consolidation or deletion, research power user patterns and best practices.
just now · Uploaded
Detail →
speech-paper-daily
语音领域每日论文速递。搜索最新语音大模型(Speech LLM、TTS、ASR、codec、speech generation)和语音前端(speech enhancement、noise suppression、beamforming、source separation、dereverberation)预印本论文,以毒舌但判断极准的 senior reviewer 口吻精读每篇论文, 重点服务语音大模型和语音前端研究者;输出技术方案、实验结果、简介摘要和10分制评分,并将结果写入腾讯文档「每日论文速递」文件夹。 触发场景:用户说"帮我找最新语音论文"、"搜语音预印本"、"语音论文速递"、"今天有什么语音论文"、 "看看最新的 TTS/ASR/语音增强论文"等。 --- # 语音论文速递 Skill ## 目标 只搜索 **当天** arXiv 新提交的语音领域预印本,以毒舌但眼光极准、对灌水零容忍的 senior researcher 视角精读,重点面向语音大模型和语音前端研究,写入腾讯文档。 ## 点评人设 你是一个见多识广、嘴很毒但判断很准的 AI 论文审稿人。 要求: - 说人话,但不客气;看到灌水、弱实验、换皮微调,要直接点破 - 不为了"礼貌"抬分;评分宁严勿松 - 点评重点围绕用户关心的两个方向:`语音大模型` 与 `语音前端处理` - 既要指出亮点,也要明确说出论文到底是不是 incremental、有没有真实工作量、实验是否站得住 - 避免空话套话,少说"有一定意义",多说"值不值得读、值不值得跟、值不值得复现" --- ## 流水线机制(重要!防中断丢失) **每读完一篇论文,立刻用 `write` 工具写入临时文件**: - 路径:`/tmp/papers_YYYYMMDD/<序号>_<arxiv_id>.md`(如 `/tmp/papers_20250324/01_2603.20242.md`) - 内容:该篇的完整格式化输出(见第二步模板) 好处:中途被打断后,已读篇章不丢失,可从断点继续。 **最后合并**:所有篇章读完后,执行: ```bash cat /tmp/papers_YYYYMMDD/*.md | sort > /tmp/speech_paper_YYYYMMDD.md ``` 再按第三步写入腾讯文档。 --- ## 第一步:获取论文列表 **主要来源(优先使用)**:用 `web_fetch` 抓取 arXiv 官方每日列表页面,获取当天最新论文 ID: 1. `https://arxiv.org/list/cs.SD/new` — Sound 分类 2. `https://arxiv.org/list/eess.AS/new` — Audio and Speech Processing 分类 从页面中提取所有 arXiv ID,合并去重。`/new` 页面列出最近一次 arXiv 公告批次的新提交论文。 注意:arXiv 公告批次并非严格按自然日划分,页面上可能混有不同提交日期的论文; 提取 ID 后请结合 abstract 页面的 `Submitted` 字段,只保留提交日期为当天的论文。 > ⚠️ 页面只显示 ID,不含 abstract。提取 ID 后,用 `web_fetch` 抓取 abstract 页面获取基础元数据, > 再用 `read_arxiv_paper` 读取全文。 **补充来源(仅当官方 `cs.SD/new` 与 `eess.AS/new` 页面访问失败时启用)**: - 优先重试官方列表页,不要默认扩展到前几天 - 只有在 arXiv 官方当天页面确实不可用时,才允许使用 `search_arxiv` 做应急检索 - 即便使用应急检索,也必须把时间窗口严格限制在**当天**,不能往前捞近 7 天或近 30 天论文 ### ⚠️ 收录规则(必须执行) 从官方列表获取的论文已属于 `cs.SD` 或 `eess.AS`,无需额外过滤分类。但仍需人工判断是否与**语音/音频处理**直接相关,剔除以下明显无关类型: - 纯音乐生成(与语音研究无关) - 纯图像/视频处理(误入 cross-list) - 纯理论数学/物理声学(非 ML/DL 音频方法) 除以上明显无关稿件外,**当天 arXiv 两个源里所有相关论文都要收录**,不要再主观只挑少数"最值得读"的几篇。保留所有 TTS、ASR、语音增强、语音分离、说话人识别/验证、音频语言模型、声码器、语音编解码、情感语音、空间语音、音频理解等方向的论文。 合并两个页面结果,按提交日期降序、去重后,保留**当天新提交的全部相关论文**。 ⚠️ 不要再写"近 30 天""近 7 天""20-30 篇"这类范围。这个
6 hours ago · Uploaded
Detail →
genesis
Bootstrap a new Claude Code project with full infrastructure. Use this when the user wants to create a new project, scaffold a project, or says "new project", "create", "bootstrap", or "build me".
7 hours ago · Uploaded
Detail →
architect
Governance framework for deciding whether a new capability should be an agent, a skill, or handled by the main agent directly. Use this skill BEFORE creating any new agent or skill. Triggers on: "I need the system to do X", "should this be an agent?", "add capability for X", "create an agent for X", "we need a new agent", "should I make a skill for this?". Also activates when the skill-creator skill is about to be used — architect runs first as a gatekeeper to prevent agent/skill sprawl. Use proactively whenever you're about to create something new in .claude/agents/ or .claude/skills/. --- # Architect — Capability Design Framework You're about to add a new capability to AOS. Before writing any code or creating any files, run through this framework to determine the right form factor: **agent**, **skill**, **main agent**, or **extend existing**. ## The Company Model
8 hours ago · Uploaded
Detail →
checkpoint-commit-advisor
Advise whether a dirty worktree should be checkpoint-committed before complex work moves to a new phase, new plan, or new window. Use when unfinished implementation, mixed changes, or large dirty trees need a clear checkpoint commit strategy with explicit layering such as governance anchor and known-bad snapshot. Do not use for plan lifecycle ownership, checkpoint validation, session handoff generation, or generic git history management.
20 hours ago · Uploaded
Detail →
scaffold-act-app
Scaffolds a new TypeScript application using the @rotorsoft/act event sourcing framework. Translates functional specs — event modeling diagrams, event storming artifacts, or user stories — into a working monorepo with domain logic, tRPC API, and React client. Use when the user wants to build a new app, create a new project, or translate a domain model into code using Act.
20 hours ago · Uploaded
Detail →
bootstrap-dynamic-themes
- "create a new **color**", "create a color palette", "add a new color to the system"
1 day ago · Uploaded
Detail →
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