Explore skills
Showing 66541–66570 of 77104 skills
This skill should be used when installing or debugging a self-hosted Forgejo (Gitea fork) git server as a native binary + systemd service — not Docker. Covers the three required secrets (SECRET_KEY/INTERNAL_TOKEN/JWT_SECRET) and the permission-denied crash-loop from a locked-down config file, unattended install without exposing the web setup wizard, why Forgejo's built-in git-SSH server needs firewall-level scoping instead of an app-level bind address, a non-obvious API scope requirement for repo deletion, and Vultr Block Storage's region-locking. Trigger phrases include "forgejo install", "forgejo systemd", "forgejo app.ini", "JWT_SECRET failed loading", "save oauth2.JWT_SECRET failed", "forgejo not supposed to be run as root", "forgejo admin user create", "forgejo random-password", "forgejo generate secret", "forgejo INSTALL_LOCK", "forgejo git-ssh port", "forgejo delete repo API 403", "write:user scope forgejo", "vultr block storage wrong region", "no active instances available in this region", "vultr NVMe block storage not available".
jackson2w/claude-code-skills
Stars: 1Claude CodeCodexThis skill should be used when building or debugging a macOS launchd automation that uploads a camera SD card's contents to Immich on insert (via @immich/cli), or when building a workflow to prune Immich assets that were deleted from their source card/folder after import. Covers the Immich CLI's non-obvious API key permission requirements (album.create vs albumAsset.create, the "Found 0 new files" scoped-key bug), launchd's StartOnMount trigger and its missing-Homebrew-PATH gotcha, parsing `immich upload -j` JSON output, the Immich bulk-delete (trash vs permanent) endpoint, and — critically — why a delete/prune workflow across multiple source cards feeding one album must scope its diff by a per-source manifest rather than diffing the whole album, or a second card mounted alone will make every surviving photo from the first card look deletable. Trigger phrases include "sd card to immich", "immich cli upload", "@immich/cli permissions", "albumAsset.create", "Found 0 new files and 0 duplicates", "launchd StartOnMount", "immich upload -j json output", "immich bulk delete trash", "DELETE /api/assets force", "prune immich assets deleted from card", "multiple sd cards same immich album".
jackson2w/claude-code-skills
Stars: 1Claude CodeCodexThis skill should be used when deploying an application that only ships via Docker Compose (no native/bare-metal install path — e.g. Immich, and similar multi-container stacks with a custom database extension baked into a maintained image) inside a Proxmox VM, managing its Docker Compose file and secrets as code via Ansible, debugging a Compose service that's unexpectedly reachable on the plain LAN IP instead of only over Tailscale Serve, wiring up a hardware-acceleration `extends:` stanza (hwaccel.yml, OpenVINO/VAAPI image tags) that ships commented-out in the upstream Compose file, or exposing one feature of an otherwise tailnet-only app (e.g. Immich share links) to people outside the tailnet via a purpose-built proxy sidecar + narrow Funnel rather than punching a hole in the app's own API. Also covers verifying an async first-run job (ML indexing, search embedding, etc.) actually processed something rather than just checking container health, and a shared Ansible `file` loop silently drifting a sensitive directory's mode. Trigger phrases include "tailscale serve nftables allowlist not working", "restrict tailnet peers serve", "docker compose in a proxmox vm", "immich docker deployment", "no bare-metal install path", "docker compose ports binds 0.0.0.0", "docker-proxy 0.0.0.0", "ansible deploy docker-compose.yml", "verify smart search indexed", "async job queued but not verified", "second disk for docker volumes proxmox", "hwaccel.yml extends", "immich openvino image tag", "docker compose hardware acceleration", "share immich link outside tailnet", "immich public proxy", "expose one path publicly without exposing the app", "funnel to a proxy not the app".
jackson2w/claude-code-skills
Stars: 1Claude CodeCodexThis skill should be used when a host or device on a network with both Tailscale and Pi-hole seems to bypass Pi-hole's ad-blocking despite DNS still resolving fine, when deciding whether to use Tailscale's tailnet-wide "Override DNS servers"/Global Nameservers setting (including whether to enable it for roaming ad-blocking), when a device's DNS silently breaks after that Override toggle is turned off, when Pi-hole silently rejects/resets DNS queries arriving over a Tailscale interface, or when systemd-resolved needs to be configured so a host gets Pi-hole for general DNS while keeping Tailscale MagicDNS working for *.ts.net hostnames. Trigger phrases include "tailscale override dns servers", "pihole bypassed tailscale", "resolv.conf generated by tailscale do not edit", "magicdns not resolving publicly", "systemd-resolved pihole tailscale", "Domains=~. resolved.conf", "tailscale accept-dns per device", "DNS=~. wildcard route", "pihole-dns-client playbook", "host missed by dns overhaul", "apt-get update failed after systemd-resolved install", "SSH_CLIENT tailscale IP over LAN hostname", "magicdns wrong answer right after tailscaled restart", "pihole listeningMode LOCAL", "dns.listeningMode ALL", "pihole rejects tailscale query connection reset", "roaming ad-blocking over tailscale", "nftables flush ruleset wipes tailscaled", "cloudflare backup nameserver tailscale unreliable", "tailscale global nameserver backup order", "ssh could not resolve hostname", "getent hosts not found but dig works", "ResolveUnicastSingleLabel", "single-label hostname resolution fails", "bare hostname ssh resolve failure ansible", "resolvectl query not found LLMNR", "restart of systemd-resolved failed exit status", "dns using direct mode directManager", "tailscale apt upgrade broke dns", "systemctl restart tailscaled did not fix dns", "resolv.conf plain file instead of symlink".
jackson2w/claude-code-skills
Stars: 1Claude CodeCodexThis skill should be used when helping Will (or someone he's helping) with Wikidata items or Wikipedia articles — creating a Wikidata item for a person, organization or publication; walking a human through the Wikidata editing UI; linking a website to its Wikidata item via schema.org sameAs; making a site's articles cite cleanly in Wikipedia's citation tool (Citoid); judging whether a person meets Wikipedia notability; helping save an article at Articles for Deletion (AfD); or researching someone's public footprint for references. Built 2026-11-08/09 (Abernathy Q142086921, Will Q142087430, Deepa Purushothaman's AfD). Trigger phrases include "wikidata", "wikidata item", "Q-number", "QID", "sameAs wikidata", "wikipedia article", "wikipedia deletion", "articles for deletion", "AfD", "notability", "WP:GNG", "WP:NBIO", "WP:NAUTHOR", "reliable sources", "conflict of interest wikipedia", "COI disclosure", "Edit COI", "citoid", "cite web", "wikipedia citation", "references for wikipedia", "press links for wikipedia", "find sources about me", "public footprint".
jackson2w/claude-code-skills
Stars: 1Claude CodeCodexUse when the user asks to track, scan, monitor, digest, or maintain a reading queue for new papers from top journals, Nature/Science/Cell/PNAS families, or any research field. Works with any discipline — ecology, environment, CS, medicine, physics, social sciences, etc.
LiAngsong98/frontier-tracker
Stars: 26Claude CodeCodexUse when the user wants to translate a repository README, make a repo multilingual, localize docs, add a language switcher, internationalize the README, or update localized README variants in a GitHub-style repository.
artubss/SKILLS-CLAUDE-CODE
Stars: 12Claude CodeCodexUse quando o usuário pergunta como construir com produtos ou APIs da OpenAI e precisa de documentação oficial atualizada com citações (por exemplo: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, capacidades ou limites de modelos); priorize ferramentas MCP de docs da OpenAI e restrinja qualquer fallback de navegação a domínios oficiais da OpenAI.
artubss/SKILLS-CLAUDE-CODE
Stars: 12Claude CodeCodexUse o servidor Figma MCP para buscar contexto de design, screenshots, variáveis e assets do Figma, além de traduzir nós do Figma em código de produção. Ative quando uma tarefa envolver URLs do Figma, IDs de nós, implementação design-to-code ou configuração e troubleshooting do Figma MCP.
artubss/SKILLS-CLAUDE-CODE
Stars: 12Claude CodeCodex管理所有已安装的 AI 技能(Skills),支持 Claude Code、OpenClaw、Codex、Trae、Hermes 等多种智能体。在编程/开发任务的计划阶段自动分析项目并推荐技能组合,推荐尽可能简洁且必须基于已有的技能。若现有技能无法满足需求,再推荐可下载的技能。询问用户是否按以上技能组合,想替换哪些技能?如果有的话可以说。在同一任务的后续步骤中,询问用户是保持原有技能组合还是推荐新的组合。安装新 Skill 时自动同步到 Excel 仓库。用户询问技能管理、计划推荐、技能调换时触发:列出、推荐、分类、调换。Manage all installed AI skills for Claude Code, OpenClaw, Codex, Trae, Hermes and other agents. Automatically analyzes projects and recommends skill combos during task planning. Recommendations must be concise and based on already installed skills first. Only recommend downloadable skills when existing skills cannot meet needs. Ask user whether to use this combo and which skills to replace if any. In follow-up steps of the same task, asks user whether to keep existing combo or recommend new one. Auto-syncs to Excel database when new skills are installed.
971184676/skill-manager
Stars: 1Claude CodeCodexa user-authored audit skill
aktonay/skillz
Stars: 0Claude CodeCodexCustom VM and bytecode reverse engineering playbook. Use when CTF challenges or protected software implement custom virtual machines with proprietary bytecode, dispatcher loops, or maze-style challenges.
ShulkwiSEC/bb-huge
Stars: 27Claude CodeCodexbikidsx/comp
Stars: 0Claude CodeCodexBest practices for Remotion - Video creation in React
kbarbel640-del/skills
Stars: 1Claude CodeCodex基于已摄取文献和本地数据,生成经管实证研究设计:问题、机制、变量、模型、识别、机制、异质性、稳健性
Lambenthan/empiricalwiki
Stars: 103Claude CodeCodex将实证研究设计转成 Stata 执行计划或 do 文件骨架,包含数据合并、变量构造、描述统计、回归和稳健性
Lambenthan/empiricalwiki
Stars: 103Claude CodeCodex汇总某个经管实证变量在文献中的测算口径、数据来源、模型角色和项目可用性
Lambenthan/empiricalwiki
Stars: 103Claude CodeCodex分析 msProbe compare 精度比对结果文件(CSV/XLSX),定位整网精度问题与数值差异。支持统计量模式,输出分析报告。支持辅助信息协助定位:辅助信息(历史结论/已知根因/已排除算子/嫌疑区域等)建议在请求中附带(不依赖交互工具)。若请求中未附带且运行环境无 AskUserQuestion,则跳过辅助信息收集、照常完成分析,报告中省略辅助信息章节并注明原因。
Ascend/msagent
Stars: 0Claude CodeCodex分析 PyTorch memory snapshot pickle 文件(_dump_snapshot 导出的内存快照),提供内存峰值、碎片、泄漏、OOM 检测与交互式 HTML 报告。仅当用户明确提及 memory snapshot、内存快照、_dump_snapshot、pickle 内存文件 或需要对 snapshot pickle 做内存分析时才触发,不处理一般的 NPU 性能分析、SQLite 查询或通用内存问题。
Ascend/msagent
Stars: 0Claude CodeCodexDocker-based ROS2 development for robot software stacks. Use when containerizing ROS2 workspaces, writing Dockerfiles or docker-compose files, debugging DDS discovery across containers, configuring GPU, USB, X11 or Wayland passthrough, building devcontainers, or running ROS2 CI/CD in containers. Covers multi-stage builds, CycloneDDS and FastDDS container networking, shared memory, and deployment patterns for Humble, Iron, Jazzy, and Rolling on Ubuntu 22.04 or 24.04.
elliewlh2094/codex-robotics-skills
Stars: 0Claude CodeCodexProduction bringup patterns for ROS2 robots on onboard computers. Use when configuring robot startup on boot, writing systemd units for ROS2 launch, composing full-stack launch files, ordering startup with health checks, configuring udev device names, adding watchdogs or restarts, managing logs, debugging boot-time races, setting up multi-machine networking, or handling graceful shutdown for long-running robot services on Ubuntu with ROS2 Humble, Iron, or Jazzy.
elliewlh2094/codex-robotics-skills
Stars: 0Claude CodeCodexRobot perception best practices for cameras, LiDARs, depth sensors, IMUs, and multi-sensor pipelines. Use when working with OpenCV, Open3D, PCL, RealSense, ZED, OAK-D, RGBD, point clouds, calibration, AprilTags, ArUco, detection, segmentation, tracking, frame synchronization, coordinate transforms, perception latency, or production deployment of robotics perception systems.
elliewlh2094/codex-robotics-skills
Stars: 0Claude CodeCodexRobotics architecture patterns and design recipes. Use when designing robot software architecture, choosing behavior trees, finite state machines, subsumption, hardware abstraction layers, watchdogs, heartbeats, safety systems, sensor fusion, perception-planning-control pipelines, sim-to-real structure, digital twins, fleet management, or real-time versus non-real-time boundaries.
elliewlh2094/codex-robotics-skills
Stars: 0Claude CodeCodexSoftware design principles for robotics modules and libraries. Use when designing robot modules, structuring codebases, reviewing robotics code, refactoring robot software, applying SOLID, clean architecture, dependency injection, hardware interfaces, real-time constraints, fail-safe defaults, configuration management, separation of concerns, composable behaviors, or robotics API design.
elliewlh2094/codex-robotics-skills
Stars: 0Claude CodeCodexTesting strategy for robotics software. Use when writing unit, integration, simulation, hardware-in-the-loop, or regression tests for robot systems; testing ROS nodes with pytest or launch_testing; mocking sensors or actuators; building robotics CI/CD; using deterministic replay, golden files, property-based tests for kinematics, fuzz tests for message handlers, or validation for perception, planning, and control pipelines.
elliewlh2094/codex-robotics-skills
Stars: 0Claude CodeCodexROS1 development guidance for legacy and migration work. Use when building or maintaining ROS1 nodes, catkin packages, launch files, message types, services, actionlib actions, tf transforms, nodelets, dynamic reconfigure, pluginlib, rospy or roscpp code, debugging roscore, rostopic or roslaunch behavior, maintaining legacy ROS1 systems, or planning ROS1 to ROS2 migration and bridges.
elliewlh2094/codex-robotics-skills
Stars: 0Claude CodeCodexROS2 bag recording and replay guidance for rosbag2 CLI and programmatic capture with rosbag2_py or rosbag2_cpp. Use when recording robot data, replaying bags for debugging or regression tests, choosing SQLite3 versus MCAP, splitting or compressing long recordings, using ros2 bag record, play, info, use_sim_time, clock replay, StorageOptions, ConverterOptions, BagWriter, BagReader, or application-level data capture.
elliewlh2094/codex-robotics-skills
Stars: 0Claude CodeCodexClean Architecture, Hexagonal Architecture, and Ports and Adapters for ROS2 codebases. Use when starting or refactoring a ROS2 package larger than a single node, separating domain logic from rclpy, rclcpp, or tf2_ros infrastructure, making robot logic testable without spinning ROS, applying dependency inversion, creating adapters, or untangling nodes that mix CV, math, state machines, and ROS plumbing.
elliewlh2094/codex-robotics-skills
Stars: 0Claude CodeCodexROS2 diagnostics, health monitoring, and structured logging patterns. Use when adding diagnostic_updater health checks, publishing diagnostic_msgs on /diagnostics, monitoring topic frequency, wiring diagnostic_aggregator, reporting hardware status, using OK, WARN, ERROR, or STALE states, building health dashboards, checking whether a node or sensor is healthy, or fixing log spam with throttled or structured logging.
elliewlh2094/codex-robotics-skills
Stars: 0Claude CodeCodexROS2 launch and configuration patterns. Use when writing XML or Python launch files, composing multi-node systems, externalizing parameters into YAML, splitting large launch files, including subsystem launch files, declaring launch arguments, using LaunchConfiguration, FindPackageShare, IfCondition, TimerAction, event handlers, namespaces, remapping, parameter files, or composable-node containers for intra-process communication.
elliewlh2094/codex-robotics-skills
Stars: 0Claude CodeCodex