Loading…
Not enough history yet: 3 of 7 days recorded. Until then this list is ordered by the most recent content change.
77104 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| xy-skill-auditxyaz1313/xyskill【技能安检】扫描本机各 Agent 宿主目录里装的 skill,找出暗中导流、隐藏商业关系、劫持用户指令、偷读敏感数据、可疑外部调用这几类越权信号;默认只出报告,用户点名确认后才把问题 skill 隔离到本地隔离区(可恢复,不删除)。用户说「扫一下我装的 skill」「检查 skill 有没有广告」「这个 skill 安全吗」「清理有问题的 skill」「审查我的 skill」时使用。|小爷出品 | Stars: 134 | Updated | Claude CodeCodex | Verified | Install |
| xy-slow-lanexyaz1313/xyskill【该慢的环节诊断】慢就是快。帮做私域/选品/带团队的人分清:眼前这件事里,哪个环节值得亲自慢做(前 100 个客户、第一轮测品、前 30 天朋友圈、招人前先干一遍岗位),哪个环节该快该外包该用工具。用户说「有没有更慢但更稳的方法」「我是不是走捷径了」「这个能不能外包/用模板/群发」「为什么别人做得快我不行」「我想省事」时使用。|小爷出品 | Stars: 134 | Updated | Claude CodeCodex | Verified | Install |
| xy-syncxyaz1313/xyskill【同步更新】同步 XY 工作台——重建原子导出、把仓库 skills/ 全部重新桥接到各宿主,让改过/新写的 skill 在 Claude Code、Codex、WorkBuddy、Grok 等端立刻可用;仓库接了 GitHub 后再多两步:安全推送(防父目录建仓把内部资料一起推)与拉取更新。用户说「更新 XY」「同步 skill」「把新写的 skill 同步到各端」「推送到 GitHub」「拉最新的」「有没有新版本」时使用。|小爷出品 | Stars: 134 | Updated | Claude CodeCodex | Verified | Install |
| xy-term-crackxyaz1313/xyskill【概念拆解】概念拆解。把私域/短视频/IP 圈里被说烂的词(私域、直营化、微商化、推客、订单粉、引流品/利润品、人效、寂寞期、赢的体验、心智位、精神母体、被动收入、精准流量)拆到能落到动作和数字的程度,并判断哪些是换皮的旧词、哪些问题根本没有文字答案。用户说「私域到底是什么」「这个词什么意思」「帮我拆一下这个概念」「他说的和我理解的一样吗」「这算不算新东西」时使用。|小爷出品 | Stars: 134 | Updated | Claude CodeCodex | Verified | Install |
| xy-trafficxyaz1313/xyskill【导流诊断】诊断"公域流量怎么设计路径导进私域"——按平台风控差异、账号阶段导流强度、手法风险分级、流量质量筛选、后端承接五项检查给判定,排除"抄同行导流话术""流量越多越好""先留联系方式再说"这类想当然式设计。兼管短视频账号起号与冷启动(新号没流量、标签打歪了先来这)。用户说"新号没流量""怎么起号""这个导流方式对不对""引流路径怎么设计""怎么把流量导到微信""这样导流会不会有风险""导流强度该多大""公域转私域怎么做"时触发。|小爷出品 | Stars: 134 | Updated | Claude CodeCodex | Verified | Install |
| xy-vaultxyaz1313/xyskill【知识库】把用户手上的本地文件夹(客户档案、货盘表、朋友圈素材、课程逐字稿、代理政策历史版本、直播复盘…)变成 AI 能稳定查、稳定放、稳定判版本的知识库:没资料先建最小结构,有资料就生成一份只指路的「知识库导航」,之后负责放新资料、找答案、认最新版、体检、瘦身。用户说「搭个知识库」「让 AI 读懂我这堆文件」「把这份放进知识库」「从知识库找一下」「哪个是最新版」「更新知识库」「导航太长了瘦一瘦」时触发。触发词:/xy-vault、/知识库。|小爷出品 | Stars: 134 | Updated | Claude CodeCodex | Verified | Install |
| xy-workbenchxyaz1313/xyskill【多端Agent工作台搭建】把一个项目整理成 Claude Code / Codex / Grok / 通用 Agents(~/.agents/skills)多端一致、能长期维护的 Agent 工作台:审规则文件(CLAUDE.md / AGENTS.md)、认 skill 真源、统一命名、生成桥接、逐项验证。用户说「迁移到 Codex」「迁到 Claude Code」「Grok 也要能用」「统一 AGENTS.md」「我的 Agent 工作台很乱」「skill 散在好几个地方」「帮我把 Claude 和 Codex 和豆包打通」时使用。|小爷出品 | Stars: 134 | Updated | Claude CodeCodex | Verified | Install |
| reasoning-workflowzy839971925-zyy/Agent--deep-research-Workflow-SkillsDefault silent entry for questions, research, artifacts, code, coordination and persistent projects. When available to the host, infer the relevant evidence path from each direct request, including real-world, pre-build engineering, or linked hybrid research; choose proportionate Light-to-Ultra workflow depth and load only relevant guidance. Keep the host-selected default model unless the user or host explicitly changes it. The direct user phrase “调用我的 workflow skills” explicitly selects this workflow. | Stars: 10 | Updated | Claude CodeCodex | Verified | Install |
| audit-verificationzy839971925-zyy/Agent--deep-research-Workflow-SkillsUse when a material result needs contract verification, independent or orthogonal review, evaluator-validity checks, effectiveness review, or defensible closure. | Stars: 10 | Updated | Claude CodeCodex | Verified | Install |
| decision-analysiszy839971925-zyy/Agent--deep-research-Workflow-SkillsUse when the deliverable is a choice, recommendation, prioritization, trade-off, resource allocation, or robustness-sensitive decision. | Stars: 10 | Updated | Claude CodeCodex | Verified | Install |
| deep-researchzy839971925-zyy/Agent--deep-research-Workflow-SkillsUse when a scenario calls for real-world evidence, pre-build engineering/architecture research, or a linked hybrid; infer the route without requiring the user to label it. Keep the host-selected default model; infer proportionate workflow depth, honoring explicit depth requests such as Ultra. | Stars: 10 | Updated | Claude CodeCodex | Verified | Install |
| execution-controlzy839971925-zyy/Agent--deep-research-Workflow-SkillsUse when work creates durable artifacts or external side effects, delegates execution, needs authorization, or must preserve state/checkpoint/recovery semantics. | Stars: 10 | Updated | Claude CodeCodex | Verified | Install |
| reasoning-corezy839971925-zyy/Agent--deep-research-Workflow-SkillsUse when a task needs problem framing, representation choice, decomposition, relationships, causal chains, hypotheses, or careful interpretation. | Stars: 10 | Updated | Claude CodeCodex | Verified | Install |
| workflow-learningzy839971925-zyy/Agent--deep-research-Workflow-SkillsMaintenance-plane only. Use after completed runs or evaluations to derive CAPA/experience candidates, challenge transferability, and gate learning promotion or rollback. | Stars: 10 | Updated | Claude CodeCodex | Verified | Install |
| reasoning-workflowzy839971925-zyy/Agent--deep-research-Workflow-SkillsDefault silent entry for questions, research, artifacts, code, coordination and persistent projects. When available to the host, infer the relevant evidence path from each direct request, including real-world, pre-build engineering, or linked hybrid research; choose proportionate Light-to-Ultra workflow depth and load only relevant guidance. Keep the host-selected default model unless the user or host explicitly changes it. The direct user phrase “调用我的 workflow skills” explicitly selects this workflow. | Stars: 10 | Updated | Claude CodeCodex | Verified | Install |
| ai-visibility-auditvistabylara-dev/vista-claude-skills | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| cloudflare-workers-auditvistabylara-dev/vista-claude-skills | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| google-ads-auditvistabylara-dev/vista-claude-skills | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| jsonld-schema-generatorvistabylara-dev/vista-claude-skills | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| llms-txt-generatorvistabylara-dev/vista-claude-skills | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| meta-ads-auditvistabylara-dev/vista-claude-skills | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| nextjs-seo-auditvistabylara-dev/vista-claude-skills | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| robots-txt-validatorvistabylara-dev/vista-claude-skills | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| shopify-geo-auditvistabylara-dev/vista-claude-skills | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| proposalChuluuMGL/proposal-skillCreate, revise, or audit commercial proposals as editable PowerPoint, interactive HTML, or PDF, with proposal logic, case evidence, scope and pricing, presenter scripts, and format-specific validation. Use for client proposals, pitches, tenders, and proposal revisions, rather than general marketing websites. | Stars: 2 | Updated | Claude CodeCodex | Verified | Install |
| aas-agent-coordination-artifact-integration-approval-evidence-packetManoj-11-Dahal/try-SkillsUse when a parallel artifact integration result is ready for a human owner to approve, reject, or redirect to produce a decision packet for the integration staging plan containing options, evidence, risks, and open questions. Success means the decision owner, requested decision, source evidence, alternatives, uncertainty, and consequence of no action are all visible; each output is reviewed against the same baseline and conflicts remain visible. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Verified | Install |
| aas-agent-coordination-artifact-integration-change-impact-traceManoj-11-Dahal/try-SkillsUse when a version, rule, source, or stakeholder change may affect parallel artifact integration to produce a before/after change record and impact map for the integration staging plan. Success means each material difference is tied to affected dependencies, consumers, owners, and a test or explicitly unknown impact; each output is reviewed against the same baseline and conflicts remain visible. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Verified | Install |
| aas-agent-coordination-artifact-integration-closeout-handoff-ledgerManoj-11-Dahal/try-SkillsUse when a parallel artifact integration work item is nearing completion, pause, or transfer to another owner to produce a closeout ledger for the integration staging plan with status, evidence, owner, and retention state. Success means all deliverables, unresolved items, approvals, and next owners are recorded, and the stop reason is explicit; each output is reviewed against the same baseline and conflicts remain visible. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Verified | Install |
| aas-agent-coordination-artifact-integration-completeness-reconciliationManoj-11-Dahal/try-SkillsUse when the parallel artifact integration workflow receives records that must agree across sources, periods, or statuses to produce a reconciliation worksheet for the integration staging plan with matched, unmatched, and unresolved rows. Success means counts and key fields reconcile or every variance is quantified, sourced, and left unresolved for an owner; each output is reviewed against the same baseline and conflicts remain visible. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Verified | Install |
| aas-agent-coordination-artifact-integration-exception-triage-queueManoj-11-Dahal/try-SkillsUse when the parallel artifact integration workflow has exceptions, missing evidence, or competing priorities to produce a prioritized exception queue for the integration staging plan with evidence, owner, and next action. Success means every exception has a severity rationale, source, owner or explicit unassigned state, and a bounded next step; each output is reviewed against the same baseline and conflicts remain visible. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Verified | Install |