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.
46,100 skills from 2,198 repositories · updated 4 hours ago
9,541 skills
- luo-yonghao-jiaopengyou-perspectiveswaylq/master-skill罗永浩 / 交个朋友视角. 店播头部 + 头部主播 IP 化方法论. 调用此 skill 时, 用交个朋友的认知框架做店播 / 主播 IP 决策.OtherNo warnings★ 174↓ —Also in 1 other repo
- blender-uv-texturingCheshireJCat/blenderUV unwrap, atlas-map, project textures, use alpha decals, bake maps/lightmaps, and prepare texture-driven Blender assets for glTF/GLB export. Use whenever the user provides texture packs, texture atlases, decals, UV layouts, lightmaps, wants a texture to fit a mesh 1:1, or reports stretched/off textures. Pairs with reference-to-3d for template-accurate reconstruction and blender-materials for PBR values.OtherNo warnings★ 63↓ —
- tribunalarbiterForge/codeArbiterRun an opt-in deep codebase audit with persisted findings. Confirm cost before dispatch; filing and telemetry need separate approval.OtherNo warnings★ 149↓ —
- ketchupdsebban/skillsCatch the user up on what changed in this chat since their last message, in plain words and small visuals. List every item waiting on them with what they need to decide it from the reply alone. Use for /skill:ketchup.OtherNo warnings★ 69↓ —
- qiangua-data-driven-perspectiveswaylq/master-skill千瓜数据创始团队视角. 数据驱动派代表方法论 + 工具派. 调用此 skill 时, 用千瓜的认知框架做小红书数据 / 选题 / 投放决策.OtherNo warnings★ 174↓ —Also in 1 other repo
- maintain-verification-skilldsebban/skillsPeriodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /skill:maintain-verification-skill or "audit the verify skill".OtherNo warnings★ 69↓ —
- principle-explain-the-numberdsebban/skillsApply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.OtherNo warnings★ 69↓ —
- gsd-dococo-research/cocoUse when you know what you want but not which /gsd-* command to run. Routes freeform text to the best matching GSD command, confirms the match, then hands off without doing the work itself.OtherNo warnings★ 795↓ —
- zhang-jianzhong-tongren-perspectiveswaylq/master-skill张建中 (首都医科大学附属北京同仁医院足踝外科矫形中心) 视角. 国内足踝外科教父级代表. 拇外翻 + 平足 + 踝关节置换 + 中文圈本土化派. 调用此 skill 时, 用张建中框架做拇外翻 / 国内患者 / 中文圈实操决策.OtherNo warnings★ 174↓ —Also in 1 other repo
- ye-yunyanswaylq/master-skill叶云燕视角. 平安寿险代理人体系销售方法论 living legend, 「事业宗教叙事 + 师徒制扩张」流派代表. 提供「主动筛客 + 极致服务 + 团队复制」式决策视角, 与独立经纪流派 (江立辉 / 明亚) 形成对位张力.OtherNo warnings★ 174↓ —
- ni-haixiaswaylq/master-skill倪海厦视角. 港台五术派代表 (1954-2012), 「命相卜山医一体」流派的 living archive. 提供「跨数术整合 + 命医同源 + 反江湖 + 反学院文献学」式决策视角, 与子平派单术深耕 (沈孝瞻 / 梁湘润) 与盲派师承口诀 (段建业) 形成对位张力. 长讲材料密度华人世界最高.OtherNo warnings★ 174↓ —
- duan-jianyeswaylq/master-skill段建业视角. 大陆当代盲派代表 / 北方盲派核心 / 师承郝金阳口诀派 / 字卜文 / 体系化《段氏理象学》编撰者. 把"看八字"从"取格定用神"的子平静态结构, 换成"取象 + 主宾体用 + 虚实 + 应期"的盲派动态象法. 用途: 当用户问"我这个八字是什么格" / "用神是什么" / "我什么时候能发财" / "婚姻何时动" / "盲派和子平差在哪" 时, 用段建业视角先把命局当成一幅"活的画"来读 — 每个字是事象代号, 不立刻取格, 不轻易下吉凶定论. 当用户提到 "段建业" / "盲派" / "段氏理象学" / "取象" / "主宾体用" / "虚实" / "应期" / "郝金阳" / "北京盲派班" 时使用. 即使用户只是说 "用盲派看一下" / "象法批一下" 也应触发.OtherNo warnings★ 174↓ —
- liu-siyi-qunxiang-perspectiveswaylq/master-skill群响刘思毅视角. 操盘手社群头部 + 私域 + 矩阵派代表. 调用此 skill 时, 用刘思毅的认知框架做小红书操盘手 + 私域 + 矩阵决策.OtherNo warnings★ 174↓ —Also in 1 other repo
- andy-grove-intelswaylq/master-skillAndy Grove 视角. Intel 前 CEO, 《High Output Management》/《Only the Paranoid Survive》作者, Operator-Engineer 流派 (流派 B) 奠基者, OKR 之父 (John Doerr 的源头). 把 CEO 工作当工程系统管: 产出 = 组织产出, 经理杠杆率, OKR, 战略拐点 (SIP), 建设性对抗. 用途: 当用户问 "组织效率 / 中层管理 / OKR 怎么定 / 会议怎么开 / 什么时候该全力转向 (战略拐点判断) / 数据驱动经营" 类问题时, 用 Grove 的 经营科学镜片先把 "杠杆率在哪 + 拐点信号是噪音还是信号" 盘清楚再给判断. 当用户提到 "Andy Grove" "Grove" "High Output Management" "OKR 源头" "战略拐点" "strategic inflection point" "Only the Paranoid Survive" "经理杠杆率" 时使用. 即使用户只是说 "用 Grove 思路看一下" 也应触发.OtherNo warnings★ 174↓ —
- benchmark-checklistdsebban/skillsVet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or regression you measured.OtherNo warnings★ 69↓ —
- gumai-jiahe-content-perspectiveswaylq/master-skill古麦嘉禾创始团队视角. 内容驱动派代表方法论, 强调内容 IP 化 + 真实分享. 调用此 skill 时, 用古麦嘉禾的认知框架做小红书内容运营决策.OtherNo warnings★ 174↓ —Also in 1 other repo
- liang-xiangrunswaylq/master-skill梁湘润 (1930-2014) 视角. 港台子平派学科化代言人, 「子平母法」主张者, 三阶段教学法奠基人. 行卯出版社系列著作主笔, 对民国整理派 (徐乐吾) 有学科史层级反驳 — 「沈氏精蕴, 为徐之注释所掩, 多以己习误解沈意」. 把禄命学从「师徒相授」推向「学科化教学体系」, 是子平派内部少有的「学院气 + 实务命理人」复合身份. 用途: 当用户面临「评注派 vs 原文派 / 命学如何系统化学习 / 子平方法论梳理 / 整理派内部古意分歧」类问题时, 切换到这副镜片.OtherNo warnings★ 174↓ —
- john-gottman-perspectiveswaylq/master-skillJohn Gottman (Gottman Institute) 视角. 循证婚姻研究派代表. Four Horsemen + 5:1 Magic Ratio + Cascade Model. 调用此 skill 时, 用 Gottman 框架做关系健康度判断.OtherNo warnings★ 174↓ —Also in 1 other repo
- yang-meng-anker-perspectiveswaylq/master-skill阳萌 (Anker 创始人 / CEO) 视角. 中国品牌出海方法论 — 长期主义 / 浅海战略 / 国际品牌三段论. 调用此 skill 时, 用阳萌的认知框架做品牌出海决策.OtherNo warnings★ 174↓ —Also in 1 other repo
- in-your-own-wordsdsebban/skillsRestate in your own words what you think the user's goals are and what problem they're trying to solve. Use for /skill:in-your-own-words.OtherNo warnings★ 69↓ —
- jiang-lihuiswaylq/master-skill江立辉视角. 明亚体系经纪人「专业顾问转型」流派代言人, 「保单体检 4 维度 + 客户最佳利益第一」方法论的奠基人. 把「卖产品」语境换成「家庭风险审计 + 现金流规划 + 财富传承」的独立派思维操作系统. 用途: 当客户问「我已有保单要不要再加保 / 这个新产品好不好 / 经纪人和代理人到底差在哪」时, 用江立辉的视角先审计存量再推荐增量, 而不是直接推单. 当用户提到「江立辉」「保单体检」「经纪人专业顾问」「明亚体系」「客户最佳利益」「独立经纪人」时使用. 即使用户只是说「用江立辉视角」「明亚经纪人怎么看」也应触发.OtherNo warnings★ 174↓ —
- amadeusAnil-matcha/awesome-muse-connectorsSearch travel with Amadeus: flight offers and prices, airport autocomplete, hotel offers, cheapest dates. Trigger phrases: amadeus, flight search, flight prices, hotel search.OtherNo warnings★ 1.4K↓ —
- automate-medsebban/skillsUse for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via the authoring-a-skill playbook + unslop, optionally pulling fresh evidence from recent session history.OtherNo warnings★ 69↓ —
- no-commentsdsebban/skillsSpawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.OtherNo warnings★ 69↓ —
simpo-training
KalarisLabs/research-agent-skills
OtherUpdated 4 days ago
From the author
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.
Install
npx skills add KalarisLabs/research-agent-skills --skill simpo-training -a claude-code
Installs to .claude/skills/simpo-training/ · 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
Instructions onlyUses the networkLicence: MIT
Safety checks on SKILL.md
No warnings.
Why 82
Security100
Provenance62
Maintenance100
Licence100
Adoption32
Files (4)
- SKILL.md
- references/datasets.md
- references/hyperparameters.md
- references/loss-functions.md