Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
49,534 skills from 2,407 repositories · updated 44 minutes ago
10,681 skills
- linter-fix-guideproflead/codex-skills-libraryExplain lint errors and propose fixes. Use when a junior developer needs help resolving common lint or format warnings.OtherNo warnings★ 167↓ —
- org-standardizationproflead/codex-skills-libraryDefine engineering standards across teams. Use when a senior developer needs to align practices.OtherNo warnings★ 167↓ —
- deepchemBioTender-max/awesome-bio-agent-skillsMolecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first PyTorch workflows use torchdrug; for benchmark datasets use pytdc.OtherNo warnings★ 215↓ —
- alicealicewe1/alice_skillAlice 六类技能总路由。用户输入 Alice 或要求查看 Alice 技能菜单时，严格输出固定菜单；输入攻/防模式、六类入口或直接描述任务时，按类别→领域→模块渐进路由。OtherNo warnings★ 62↓ —
- quality-risk-analysisnaodeng/awesome-qa-skillsUse this skill when you need to identify and prioritize quality risks from product, change, and evidence inputs; triggers include 质量风险分析 and quality risk analysis.OtherNo warnings★ 297↓ —
- pymc-bayesian-modelingBioTender-max/awesome-bio-agent-skillsBayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.OtherNo warnings★ 215↓ —
- quality-debt-analysisnaodeng/awesome-qa-skillsUse this skill when you need evidence-bounded quality-debt items, origins, impact, age, priority, ownership, and paydown tradeoffs; triggers include 质量债务 and quality debt.OtherNo warnings★ 297↓ —
- view-your-harnessSpaceZephyr/build-your-harness把一个本地目录变成可浏览的可视化工作台，一屏看清「我有哪些文件」和「我有哪些 Skill 可用」。起一个本地只读服务，浏览器里出目录卡片墙、文件清单、Skill 装备台（带真实调用次数和僵尸标记），支持全局搜索、按类型/时间/体量筛选、点开预览、用系统程序打开或在访达中定位。当用户说「打开工作台」「可视化看一下这个目录」「我有哪些 Skill」「我有哪些文件」「这个文件夹里都有什么」「看板」「dashboard」「浏览我的 harness」时触发，也适用于用户直接甩来一个本地路径要求「看看里面有什么」的场景。OtherNo warnings★ 58↓ —
- scvi-toolsBioTender-max/awesome-bio-agent-skillsDeep generative models for single-cell omics. Use when you need probabilistic batch correction (scVI), transfer learning, differential expression with uncertainty, or multi-modal integration (TOTALVI, MultiVI). Best for advanced modeling, batch effects, multimodal data. For standard analysis pipelines use scanpy.OtherNo warnings★ 215↓ —
- multi-agent-coordinatorhuangwb8/skills用于规划包含独立任务的实施计划、定义 Agent 角色和依赖，并通过 `parallel-vibe` 统一执行与审查；本角色不直接创建或调度子代理。OtherReview first★ 50↓ —
- mirror-optimizerhuangwb8/skills当用户明确要求优化镜像源、配置国内镜像、加速部署或切换依赖源时使用。分析项目技术栈并生成适配的镜像配置。⚠️ 不适用：用户只是询问镜像源概念、无需部署加速，或明确要求使用官方源。OtherReview first★ 50↓ —
- interactive-learninggeekjourneyx/interactive-learning接收任意文本、链接、文档或问题，把“解释一下”升级成真正的学习闭环：先判断值不值得学、该学多深，再用最小验证逼出真实理解，并在必要时动态生成 checkpoint HTML。只要用户明显想“学懂”“吃透”“带我学”“帮我验证我是不是真懂了”，而不是只要摘要、改写或普通解释，就应主动使用本技能。也适用于用户想导出学习卡片、checkpoint 页面、复盘页、学习状态页的场景。OtherNo warnings★ 51↓ —
- harness:certifyraphaelchristi/harness-evolverUse when the user wants to verify that the evolved agent's score is stable and reliable. Runs evaluation multiple times and reports mean ± std.OtherNo warnings★ 57↓ —
- filteringBioTender-max/awesome-bio-agent-skillsUse this model doc whenever the user wants to perform neuroimaging signal denoising with classical temporal filtering methods. This is a non-deep-learning preprocessing route focused on temporal cleaning, frequency selection, and preparation of cleaner time series for downstream analysis.OtherNo warnings★ 215↓ —
- katalin-kariko-perspectiveBioTender-max/awesome-bio-agent-skills诺贝尔奖得主Katalin Karikó的认知框架——40年逆共识坚持、从边缘到改变世界的思维操作系统。 核心镜片：内在信念驱动、问题导向超越领域、实验验证高于同行评价。 触发词：「卡里科」「Karikó」「mRNA思维」「逆共识坚持」「长期主义科学家」「被低估的天才」。OtherNo warnings★ 215↓ —
- jack-w-szostak-perspectiveBioTender-max/awesome-bio-agent-skillsJack W. Szostak（2009年诺贝尔生理学或医学奖得主）思维框架。 端粒与端粒酶的共同发现者，RNA世界假说/生命起源领域的领军人物。 核心镜片：化学还原论+跨学科碰撞+问题选择艺术。 适用场景：科研方向选择、跨学科创新、从化学第一性原理思考生命问题、科研诚信决策。OtherNo warnings★ 215↓ —
- dependency-install-helperproflead/codex-skills-libraryGuide installation of project dependencies and toolchains. Use when a junior developer is stuck setting up the environment.OtherNo warnings★ 167↓ —
- automation-roi-analysisnaodeng/awesome-qa-skillsUse this skill when you need evidence-bounded automation candidates, build/run/maintenance costs, benefit assumptions, time horizon, and sensitivity; triggers include 自动化投资回报 and automation ROI.OtherNo warnings★ 297↓ —
- faqseldonframe/seldonframeFrequently-asked-questions section addressing the actual concerns that block visitors from booking — pricing, scheduling, what to expect, scope, refunds.OtherNo warnings★ 66↓ —
- re-ebpffreyrswift/UaStationeBPF 程序逆向与对抗分析：BPF-64 指令集、progs/maps 关联、bpftool 反汇编、跟踪取证/恶意样本/EDR 对抗三用途。 触发词：eBPF、BPF、bpftool、bcc、libbpf、xlated、BPF 指令、bpf hook、EDR 对抗、tracepoint、kprobe。OtherNo warnings★ 58↓ —
- ca-releasearbiterForge/codeArbiterPrepare a declared release target, or preview it with --dry-run. Derive its version and require authorization before publication.OtherReview first★ 151↓ —
- seecutYeJe-cpu/SeeCut网感口播精剪（v3.4）：口播视频加动效，自动剪成"网感口播精剪风格"竖版/横版样片，交付渲染成片+分层工程包（装了剪映引擎则再出剪映分层草稿，音效放草稿；没装则音效混进成片）。当用户给了口播粗剪(+B-roll/截图/录屏)并想要"口播动效/加卡片弹字/剪成短视频/做动效样片/网感口播精剪"时用。自循环:预检→素材理解→找真证据→编排→HyperFrames构建→硬门+两两对比自迭代(≤3版)→配音效→交付→用户终审。不做:纯字幕/纯配音/纯生图/BGM。OtherNo warnings★ 431↓ —
- re-crash-triagefreyrswift/UaStation崩溃/漏洞样本分析：确定性复现、ASAN/UBSAN 报告解读、输入最小化 (afl-tmin/cmin)、gdb 回溯定位、rr 录制重放、PoC 产出。 触发词：崩溃、crash、ASAN、UBSAN、未定义行为、UAF、堆溢出、越界、段错误、segfault、 core dump、PoC、漏洞分析、崩溃分析。OtherNo warnings★ 58↓ —
- bio-atac-seq-atac-qcBioTender-max/awesome-bio-agent-skillsATAC-seq library quality control -- TSS enrichment, FRiP, fragment-size periodicity, library complexity (NRF/PBC1/PBC2), mitochondrial fraction, and ENCODE 4 thresholds. Use when assessing whether an ATAC-seq library passes ENCODE acceptance criteria, diagnosing transposition artefacts, comparing Omni-ATAC vs standard prep quality, or selecting which replicates to drop before peak calling.OtherNo warnings★ 215↓ —
status
apache/magpie
OtherUpdated 5 hours ago
From the author
Show how Magpie is adopted in this repo — install method and pin, drift, wired agent targets, installed skill families, symlink health — and change that wiring from the same view. The change itself runs through the setup skill.
Install
npx skills add apache/magpie --skill status -a claude-code
Installs to .claude/skills/status/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Runs bundled scriptsNo network use seenLicence: APACHE-2.0
Safety checks on SKILL.md
- Contains hidden text (invisible characters, long comments or encoded blobs)Medium
- Ships scripts we have not reviewedLow
Why 74
Security75
Provenance66
Maintenance100
Licence100
Adoption37
Files (6)
- SKILL.md
- adjust.md
- collect.md
- render.md
- scripts/collect_status.py
- tests/test_collect_status.py