Loading…
Showing 8311–8340 of 10160 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| wireframe-to-3dCheshireJCat/create-3d-model-skillConvert 2D orthographic wireframe PNG drawings to 3D Blender models exported as glTF/GLB. Use this skill whenever the user provides wireframe images (technical drawings, line drawings, orthographic views, side/front/back panels) and wants to generate a 3D model, mesh, or .glb file. Triggers on phrases like "convert this wireframe to 3D", "make a 3D model from these drawings", "build a model from this wireframe", "generate GLB from these views", or any image-to-3D-mesh request involving line drawings. Make sure to use this skill even if the user does not explicitly say "wireframe" — also covers "orthographic views", "technical drawings", "line drawings of objects", "front and side views". Requires the Blender MCP addon to be running (port 9876) and Python with opencv-python, numpy, scipy installed. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| ad-compliance-interactive-reviewCSlawyer1985/legal-skillhub交互式广告合规审查助手(广告合规交互式审查)。通过四步提问收集广告信息,自动进行八大维度风险识别(绝对化用语、虚假宣传、禁止性内容、比较广告、未成年人保护、前置审批、法定标识、行业特殊合规),调用华宇元典 MCP 检索法规案例,量化处罚风险,最终输出结构化的 Word 审查报告。当用户提到广告审查、广告合规、广告文案审核、广告风险排查、广告法合规、违禁词检查、广告上线前审查等场景时使用本技能。 | Stars: 36 | Updated | Claude CodeCodex | Verified | Install |
| malicious-skillalexgreensh/repo-forensicsA helpful productivity tool | Stars: 208 | Updated | Claude CodeCodex | Unverified | Install |
| agent-delivery-canaryjackson2w/claude-code-skillsThis skill should be used when building monitoring for a self-hosted always-on agent (OpenClaw/Olu, Hermes/Chuka, or a future one) that must catch failures the agent itself cannot report — silent non-delivery of a scheduled turn, a wedged or crash-looping gateway, or a fault already broken at baseline. Covers the delivery-canary pattern (agent-owned cron job + an out-of-process root verifier reading the log), the agent/verifier trust split, mutual liveness via tailnet-only health documents each host publishes and its peer watches, and persistent-state escalation that replaces transition-only alerting. Built and verified on both `dfw` (OpenClaw) and `hermes` (Hermes) on 2026-09-04. Trigger phrases include "delivery canary", "agent monitoring", "silent non-delivery", "turn dispatch bug", "canary verifier", "peer watch", "mutual liveness", "agent health endpoint", "tailscale serve health json", "transition-only alerting", "today > 0 && prev == 0", "persistent state escalation", "agent crash loop unnoticed", "who watches the agent", "canary chat id scoping", "monitor that cries wolf". | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| caddy-cloudflare-wildcard-proxyjackson2w/claude-code-skillsThis skill should be used when standing up Caddy as a reverse proxy for internal/homelab domains with a wildcard TLS certificate via Cloudflare DNS-01, when a Caddyfile needs one certificate to cover many internal hostnames, when routing Caddy to a backend that's deliberately bound to loopback only and reachable via an existing Tailscale Serve endpoint, when a Caddy instance itself needs to be loopback-only and a request returns an empty 200 response or `ss -tlnp` shows it listening on `*:port` despite the site address looking like `127.0.0.1:port`, or when debugging a fresh unprivileged LXC where tailscaled fails with "/dev/net/tun does not exist" or MagicDNS doesn't register into systemd-resolved. Trigger phrases include "caddy wildcard cert", "caddy dns-01 cloudflare", "caddy custom build dns plugin", "reverse proxy to tailscale serve backend", "loopback-bound service reverse proxy", "tun device does not exist unprivileged lxc", "tailscale magicdns not registering systemd-resolved", "split-horizon internal domain caddy", "caddy empty 200 response", "caddy content-length 0", "caddy site address host matcher not bind", "caddy listening on wildcard despite 127.0.0.1", "tailscale serve empty response from caddy backend". | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| proxmox-ansible-provisioningjackson2w/claude-code-skillsThis skill should be used when creating a new Proxmox LXC (pct create) or VM, writing or debugging Ansible playbooks that target Proxmox/Debian hosts (including Debian 13/trixie), or troubleshooting a Proxmox+Ansible workflow — a "storage 'local-lvm' does not exist" error, a "Systemd 257 detected" nesting warning, Ansible failing with a locale error inside a fresh LXC, an Ansible lineinfile task that keeps reporting changed on every run, writing multi-line config/YAML files to a remote host over SSH, an "apt-key or gpg binary is required" error from Ansible's apt_repository module, a Proxmox-family product (PVE/PBS/PMG) apt install failing with a 401 against enterprise.proxmox.com, Tailscale/anything needing `/dev/net/tun` stuck crash-looping inside an unprivileged LXC, any host device (GPU render node, USB dongle) bind-mounted into an unprivileged LXC showing up owned by `nobody:nogroup`, or an LXC's own dashboard/monitoring reporting a suspiciously high load average that doesn't match its actual workload. Trigger phrases include "pct create", "pvesm status", "local-lvm", "local-zfs", "unprivileged LXC", "nesting=1", "Ansible could not initialize the preferred locale", "lineinfile idempotency", "ansible-playbook --check failing", "pct exec", "apt-key deprecated", "apt_repository module failed", "enterprise repo 401 unauthorized", "pbs-enterprise.sources", "/dev/net/tun does not exist", "tailscaled activating auto-restart", "TUN passthrough LXC", "device passthrough nobody nogroup", "renderD128 permission denied LXC", "GPU passthrough unprivileged LXC", "chmod 666 dev dri", "loadavg LXC host contamination", "/proc/loadavg not namespaced", "LXC excessive load false alarm", "Jinja Syntax error Missing end of comment tag", "ansible template array length bash", "${#array[@]} jinja", "ansible --start-at-task check diff", "template drifted from live script". | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| using-data-analysisaiopshwang/data-analysis-ml-agent-skillsRoute data analysis and machine learning work to the right skill in this suite. Use when starting any analysis, modeling, validation, or reproducibility task and the matching specialized skill is not yet clear; not needed when one specific skill already clearly applies. | Stars: 21 | Updated | Claude CodeCodex | Verified | Install |
| claude-handoffBoom-Vitt/skills-thaiส่งต่อบทสนทนาปัจจุบันให้ background agent ตัวใหม่ที่หยิบงานไปทำต่อได้ทันที | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| handoffBoom-Vitt/skills-thaiบีบอัดบทสนทนาปัจจุบันให้เป็นเอกสาร handoff สำหรับให้ agent ตัวอื่นรับช่วงต่อ | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| graph-foremanJrSantiaggo/graph-foremanExecutes an approved plan as a task GRAPH — orchestrator + parallel subagents, validation before any task counts as done, live dashboard. Use for any plan big enough that the order of work matters. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| heath-voice-humanizerheath-gtm/Skill-BuilderStrip AI-generated tells from a draft and rewrite it in Heath's personal voice (GTM Juice). Fire whenever the user asks to "humanize", "de-AI", "clean up", "rewrite in my voice", "make this sound like me", "kill the AI tells", or "polish this draft". Also fires as the mandatory final pass inside juice-content-dispatch — every LinkedIn post, newsletter, and video script drafted there must run through this skill before the Notion write. Applies the 29-pattern Wikipedia "Signs of AI writing" catalog (em dashes, significance inflation, promotional language, rule of three, synonym cycling, inline-header lists, sycophantic tone, hyphenated word pairs, persuasive-authority tropes, signposting, etc.), then applies a hardcoded Heath-voice calibration: self-implicating first, failure-derived, plain declaratives over bumper-sticker aphorisms, no bow-tied endings, never Mixmax corporate brand voice. Forked from blader/humanizer (MIT). | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| xiaohongshu-skillschang-zy/xiaohongshu-skill小红书(RedNote / Xiaohongshu / XHS / RED / Little Red Book)浏览器自动化技能集合。 支持认证登录、内容发布、搜索发现、账号与评论分析、社交互动和复合运营。 当用户提到小红书、红书、RedNote、Xiaohongshu、XHS、RED、Little Red Book, 或要求发笔记、搜笔记、分析博主、评论、登录、点赞、收藏时触发。 | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| ai-diff-reviewer-apply-reviewj-mauro-r/SAT-Dengue-V2Read the most recent AI Diff Reviewer review from the current branch's open PR, present the findings in the parent skill's local-review format (verdict, findings table, per-finding body, recommendation), and - with explicit consent - walk the developer through each finding to apply, defer, or skip. Multi-provider aware — when the repo runs several self-review legs, attributes each finding to its provider label and surfaces cross-leg consensus. Reads the v3 review-output artifact for the PR head first (findings with verification, refuted findings, prior ledger, gate); falls back to the latest ai-pr-reviewer-marker comment and non-minimized threads when no artifact exists. Read-only by default; source edits need an explicit yes per finding; never commits, never pushes. Use when the developer says "what did the CI review say?", "read the review on this PR", "apply the AI review's fixes", "walk me through the findings", "which findings blocked the merge?", or "show me only the critical findings". | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| deepworkplan-addon-agentkitj-mauro-r/SAT-Dengue-V2Optional DeepWorkPlan addon that integrates coding-agents-kit (the `ak` command, DailybotHQ/coding-agents-kit pinned at v1.0.1, interface 1) as the headless delegation transport - a thin integrator that detects the kit through `ak doctor --json`, offers it (never imposes it) from onboard Phase 7b, documents the install from a clone of the pinned tag plus the kit's install.sh, records the acceptance in the .dwp/config.json addon registry, and maps a v7 plan's delegation operations (launch, observe, collect, cancel) onto one `ak run` per delegate in a dedicated git worktree. Never required, never a conformance gate. The kit launches agents in autonomy by default and its opt-out (--ask or AGENTKIT_PERMISSIONS=ask) always wins; the pack spells no CLI autonomy flag, never passes --auto, and passes --ask always for a read-only delegate and for writing delegates when a plan records the opt-out. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| deepworkplan-upgradej-mauro-r/SAT-Dengue-V2Check whether a newer DeepWorkPlan skill and DWP standard exists and — only after the developer explicitly accepts — install the latest published tag through the documented channel and re-run onboarding exactly as if https://deepworkplan.com/init.md were executed fresh, preserving every plan under .dwp/ and surfacing local adaptations instead of silently overwriting them. Use when the developer asks to upgrade, update, or refresh DWP in a repository that already has it installed. Do not use it to onboard a repo for the first time (that is the onboard sub-skill) or to migrate an old plan's shape (that is refine migrate, and plans are never migrated by an upgrade). | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| archive-worklogsleszekgruchala/buddyArchive, clean up, or organize dated `.ai/worklog` development worklogs by year using an age or date cutoff. Keep the current request in this skill; route new requests by their own scope. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| agent-evalsgetedgehq/skillsBuild repeatable evaluations for an agent from production failures, deterministic verifiers, cost, latency, and trace evidence. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| nan-overflow-detectionAscend/msagent多卡分布式训练中的 loss/gnorm 精度溢出检测与根因追溯。基于 MSProbe dump 数据,先跨 rank 定位首次出现 NaN 的源卡,再在源卡上追溯具体的溢出根因算子。 当用户需要:(1) 多卡分布式训练场景下的 NaN/Inf 溢出检测 (2) 找出首先出现 NaN 的源卡 (3) 追溯根因计算算子 (4) loss/gnorm NaN 问题定位 时使用此 skill。 | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| train-infer-op-diff-scannerAscend/msagentRL 强化学习训练与推理(rollout)路径的算子差异性扫描。当用户提供训练启动脚本路径,要求对比 Megatron 训练路径与 vLLM 推理路径的算子差异(尤其是融合算子 vs 单算子不一致)时使用此 skill。典型触发词包括"训推算子扫描"、"训推差异性"、"算子差异报告"、"融合算子对比"、"train vs infer op diff"。注意:本 skill 通过运行完整 RL 训练脚本(集成 profiling)来采集真实运行时算子(非静态源码扫描,非独立分离运行)。当训练、推理使用不同脚本时禁止触发。 | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| aisbench-dataset-compression-herdingAscend/msagent当用户直接要求进行数据集压缩测评,或在量化调优过程中需要使用 AISBench 评测工具输出数据集精度等场景时使用。 本 Skill 负责:使用 AISBench 数据集压缩代码、用 RBF Kernel Herding 算法生成压缩后的数据子集(coreset),并按用户目标交付两种产物之一: ① 接入量化调优主流程:产出独立的 coreset 数据集配置(不覆盖原始数据),回传「全集 config_name + coreset config_name」给编排层,供 evaluation.yaml 切换; ② 仅数据集压缩测评(不做量化调优):基于 example 模板生成「全集测试脚本」和「子集测试脚本」两份 shell 脚本。 暂时支持 AIME 2025 和 GPQA,其他数据集需要再结合 aisbench tools目录下 herding_coreset_selector 源码进行分析。 | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| ascend-fusion-op-replaceAscend/msagent针对昇腾 NPU 上的 PyTorch 模型,识别可做融合算子替换的代码段、替换为 torch_npu 融合算子并做性能/精度验证。当用户提到融合算子、NPU 算子替换、RMSNorm/SwiGLU/RoPE/Attention 融合、torch_npu 亲和算子等关键词是,使用本 Skill。 | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| clean-codebinayshaw7777/Leaflekt-MapsALWAYS invoke this skill before writing, editing, generating, or refactoring ANY code. Do not write or modify code directly without first loading and following these Clean Code guidelines. Use when writing new functions/classes, refactoring existing code, reviewing code, fixing bugs, or any task that produces code output. | Stars: 16 | Updated | Claude CodeCodex | Verified | Install |
| freehire-searchMahmoud-Qandeel/GetJobIQUse this skill to search live software / tech / data / engineering job listings across many countries and markets (and remote) via the freehire.me aggregator's public API, or to look up a specific posting. It aggregates roles from ~50 ATS platforms into one schema, so a single skill covers many markets — but its faceted filtering (skills, category, seniority) is tuned tech-first, so scope triggers to technical roles. Trigger phrases: find a tech job, software job search, developer jobs, engineering vacancies, data/ML jobs, DevOps roles, remote developer jobs, "are there any <tech role> jobs in <place>", look up this freehire job posting. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| alphaear-predictorRKiding/Awesome-finance-skillsMarket prediction skill using Kronos. Use when user needs finance market time-series forecasting or news-aware finance market adjustments. | Stars: 3.1k | Updated | Claude CodeCodex | Unverified | Install |
| omniflow-studiodeepankar-sah/OmniFlowStudio-SkillsAutonomous AI media generation, cinematic multi-shot film production, and Google Flow automation bridge. Enables AI agents to queue text-to-video, text-to-image, character consistency, and autonomous self-healing workflows with zero API costs. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| agent-hardeningarjunprabhulal/agent-skillsMakes an agent safe to run with real permissions on real data — scoping what it can do, handling prompt injection, adding confirmation and dry-run for irreversible actions, and bounding cost. Use this whenever an agent is about to touch production, act autonomously, handle untrusted input, or use credentials, and whenever the user asks about agent safety, guardrails, permissions, or prompt injection. Also use when an agent has broad API access that nothing in code restricts. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| issue-investigationarjunprabhulal/agent-skillsDigs into a murky, wide-open problem where the question itself is not yet clear — "the system is slow lately", "customers are complaining", "something is off with the numbers". Use this whenever the user describes a vague or systemic problem with no single failing case to point at, asks you to look into or dig into something, or when a first look at a bug reveals it is bigger than one bug. For a specific reproducible failure, use debugging; this skill is for when you cannot yet write the reproduction. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| crypto-trade-contextCoinLobster/agent-skillsThe data picture around a crypto position. Use when the user is about to enter or exit, is holding a position and wants what to watch, asks if their side is crowded, what holding costs, whether whales are on their side, or wants their own signal cross-checked against smart-money flow. Reports state and recorded history with sample sizes; never advice, never a forecast. Keyless on every streamed pair: trade_context, whale_context and funding_matrix on MCP, or /api/public/baseline, /api/public/whale-context, whale trades and liquidation history over plain curl. Percentile judgment vs a pair's own recorded days is keyless too, and so are whale USD magnitudes over /api/public/whale-context. Depth (whale USD on the MCP tools, crowding, full 24h stats) needs an active developer plan (from $29/mo), and so does squeeze_score outright; liq_zones is keyless on the free pair only. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| creator-outreachcreativault/skillsCreator outreach skill. MUST be used when the user wants to send, reply, batch send, batch outreach, follow up, check conversation history, manage todos, or contact creators/KOLs/influencers by email. Emails are sent by the platform through OpenAPI; never ask the user for SMTP or replace outreach with manual email/web search. Use when: email outreach, creator outreach, influencer outreach, send email to creator, batch email, batch outreach, reply to creators, follow-up, conversation history, outreach todo, campaign outreach, contact influencers, 邮件建联, 建联, 达人建联, 批量建联, 批量发邮件, 回复达人, 合作邀约, 跟进达人, 沟通历史, 待办跟进, 发合作邮件. 邮件建联全流程能力,覆盖发送、任务查询、沟通历史、待办跟进、效果指标、渠道配置、附件上传。由该平台统一代发,无需用户提供任何邮箱或 SMTP 配置。 Use when: 建联, 发邮件, 批量发送, email outreach, send email, outreach | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| write-skillhassan-mohiddin/freeflowUse when creating, rewriting, tightening, or reviewing an agent skill's instructions, trigger description, structure, examples, or bundled resources. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |