RADAR DES SKILLS · GITHUB
Des Agent Skills utiles, classés selon leur usage réel.
Comparez les Skills vérifiés par fonction, contenu, installations et fiabilité de la source avant de les ajouter.
- PÉRIMÈTRE
- VÉRIFIÉ
- Skills
- 10 772
- dépôts
- 1711
- dernière synchronisation
- 23 sept. 2026
pollyglotgplay-monetization
Manage the monetization catalog, subscriptions and one-time products, as declarative files with gplay subscriptions and iap. Use when putting a catalog under version control, editing a product's prices/offers/listings, reviewing catalog drift in CI, promoting a legacy in-app product to the v2 model, or migrating live subscribers to a new price.
- installations
- 1
- GitHub Stars
- 5
- Mis à jour
- 3 sept.
pollyglotgplay-release-flow
Ship Android releases through Google Play with gplay releases. Use when uploading an AAB or APK to a track, promoting a build up the internal → alpha → beta → production ladder, steering a staged rollout (halt / resume / complete), inspecting or downloading what sits on a track, attaching ProGuard/R8 mappings for vitals symbolication, sharing a private Internal App Sharing build, or managing legacy OBB expansion files.
- installations
- 1
- GitHub Stars
- 5
- Mis à jour
- 3 sept.
vl4dtgodot-47-migration
Godot 4.7 migration guide: new features (HDR, Steam Frame, AreaLight3D, VirtualJoystick, tweenawait, Perfetto tracing), breaking changes, and step-by-step migration patterns for existing Godot 4.x projects. Use when upgrading a Godot project to version 4.7.
- installations
- 1
- GitHub Stars
- 4
- Mis à jour
- 25 août
vl4dtgodot-physics
Physics systems for Godot 4.x: collision layers/masks, rigid body dynamics, character controllers (CharacterBody2D/3D), area nodes for triggers, physics interpolation, bulk queries, and performance optimization. Use when implementing physics, collisions, movement, or triggers in Godot.
- installations
- 1
- GitHub Stars
- 4
- Mis à jour
- 25 août
chidiokoenewriting-fragments
Writing, explore — mine raw fragments, no structure yet.
- installations
- 1
- GitHub Stars
- 3
- Mis à jour
- 20 juil.
arjunprabhulalci-pipelines
Builds and fixes continuous integration and deployment pipelines — what runs, in what order, how fast, and what blocks a merge. Use this whenever the user is writing a GitHub Actions workflow or other CI config, mentions a slow or flaky pipeline, a failing build, caching, or asks what should run before merge. For the rollout strategy a pipeline deploys with, use agent-deployment for agents or the project's own release process.
- installations
- 1
- GitHub Stars
- 2
- Mis à jour
- 4 août
arjunprabhulalincident-response
Runs a live production incident — stabilising first, communicating, and preserving evidence while the system is still on fire. Use this whenever something is broken in production right now, the user mentions an outage, users are affected, a pager fired, or a deploy has gone wrong. This is the during, not the after — for the write-up once it is over, use root-cause-analysis; for a bug that is not currently hurting anyone, use debugging.
- installations
- 1
- GitHub Stars
- 2
- Mis à jour
- 4 août
arjunprabhulalinfrastructure-as-code
Defines and changes cloud infrastructure through version-controlled configuration — Terraform, Pulumi, CloudFormation, Kubernetes manifests. Use this whenever the user is writing infrastructure config, mentions Terraform or IaC, needs to provision cloud resources, is dealing with state drift, or is about to click something into existence in a cloud console. For linting existing config, use code-linting.
- installations
- 1
- GitHub Stars
- 2
- Mis à jour
- 4 août
arjunprabhulallog-analysis
Extracts an answer from logs, traces, or metrics — finding the relevant lines in volume, correlating across services, and telling signal from noise. Use this whenever the user points at a log file, asks what happened at a particular time, mentions grepping logs, wants to know how often something occurs, or is trying to reconstruct a sequence of events across services. For fixing what the logs reveal, use debugging; for the write-up afterwards, use root-cause-analysis.
- installations
- 1
- GitHub Stars
- 2
- Mis à jour
- 4 août
arjunprabhulalroot-cause-analysis
Runs a blameless postmortem after an incident — what broke, why it broke, why it was not caught, and what changes as a result. Use this whenever the user mentions a postmortem, retro, incident review, "five whys", or a root cause analysis, and also when a serious failure has been fixed but never written up. Blamelessness here is a mechanism for getting accurate information, not a courtesy. For the live incident, use incident-response; for finding the cause of a bug, use debugging.
- installations
- 1
- GitHub Stars
- 2
- Mis à jour
- 4 août
netdatatroubleshoot-coredns
Use when diagnosing issues with CoreDNS: upstream black hole, cache collapse (thundering herd), kubernetes api disconnect, memory blowout, or forwarding loop. Queries Netdata via MCP for CoreDNS health signals, applies the diagnostic tree from the Netdata operator playbook, and recommends remediation.
- installations
- 1
- GitHub Stars
- 2
- Mis à jour
- 31 mai
netdatatroubleshoot-kubernetes-api-server
Use when diagnosing issues with Kubernetes API Server: the webhook stall, the list storm, the etcd latency cascade, the memory cliff, or the rbac/auth slow bleed. Queries Netdata via MCP for Kubernetes API Server health signals, applies the diagnostic tree from the Netdata operator playbook, and recommends remediation.
- installations
- 1
- GitHub Stars
- 2
- Mis à jour
- 31 mai
netdatatroubleshoot-nginx
Use when diagnosing issues with nginx: connection exhaustion, file descriptor exhaustion, backend cascade failure, buffer spill to disk, or ssl cpu saturation. Queries Netdata via MCP for worker process count, stub status endpoint availability, requests per second, active connections, request processing time, applies the diagnostic tree from the Netdata operator playbook, and recommends remediation.
- installations
- 1
- GitHub Stars
- 2
- Mis à jour
- 31 mai
netdatatroubleshoot-vmware-vsphere
Use when diagnosing issues with VMware vSphere: cpu starvation, memory pressure cascade, storage latency cliff, numa penalty, or snapshot accumulation. Queries Netdata via MCP for cpu ready time (per vm), cpu co-stop (per vm), memory balloon (per vm and host), host swap activity (vmkernel-level swap), datastore latency; davg, kavg, gavg, applies the diagnostic tree from the Netdata operator playbook, and recommends remediation.
- installations
- 1
- GitHub Stars
- 2
- Mis à jour
- 31 mai
superset-shsuperset-automate
Turn a recurring chore into a Superset automation — drafts the agent prompt, confirms schedule and target, creates it with the CLI, and reviews the first run together. Use when the user wants a scheduled or recurring agent, a daily/weekly job, or to automate a repeating task with Superset.
- installations
- 1
- GitHub Stars
- 2
- Mis à jour
- 5 août
superset-shsuperset-feedback
Collect and submit feedback about Superset — bug reports, feature requests, or general feedback — privately to the Superset team or as a public GitHub issue. Use when the user wants to report a Superset bug, request a feature, or send feedback about Superset.
- installations
- 1
- GitHub Stars
- 2
- Mis à jour
- 5 août
ucloudastraflow-api
当用户需要调用星图平台（AstraFlow / UModelVerse）的管理API时使用，包括创建或管理推理API Key、查询账单与订单、查询模型广场数据、导出或查询推理请求日志等场景。提供UCloud通用签名认证的完整准备工作（如何获取PublicKey/PrivateKey、如何计算Signature、如何确定Region与ProjectId），并在 references/ 目录下收录了全部21个已知管理API的详细请求/响应参数规范。
- installations
- 1
- GitHub Stars
- 2
- Mis à jour
- 2 sept.
uclouducloud-sandbox-site
当用户提供以 site 开头的 UCloud 站点空间连接 Key（格式为 site ），并要求连接、验证或操作站点空间时使用。适用于在 Linux、macOS 或 Windows 中通过 ucloud-sandbox-cli 校验连接 Key 并派生沙箱 ID、识别旧版 site 格式并引导用户到星图站点空间页面重新获取连接语句、验证站点连接、识别访问码保护、执行命令、浏览与管理文件、上传或下载代码、读取站点环境变量，以及生成、构建、部署和排查运行在 80 端口的网站服务；同时遵守站点连接 Key、站点访问码等敏感信息的单沙箱权限边界和脱敏要求。
- installations
- 1
- GitHub Stars
- 2
- Mis à jour
- 2 sept.
adevraunity-multiplayer-mobile-webgl
- Build real-time multiplayer games in Unity (C) targeting mobile and WebGL2 browsers using Colyseus or Nakama game servers with WebSocket transport. Covers client-server architecture patterns, state synchronization (prediction, interpolation, rollback), Schema-based serialization, room/match lifecycle, matchmaking, reconnection, and cross-platform deployment. Use this skill whenever building Unity multiplayer games, integrating Colyseus or Nakama, handling WebGL2 networking constraints, optimizing multiplayer performance for mobile or browser, choosing between game server frameworks, or deploying multiplayer backends. Also trigger when the user mentions real-time networking in Unity, WebSocket client setup, authoritative servers, lobby/room systems, or network state sync — even if they don't say "multiplayer" explicitly.
- installations
- 1
- GitHub Stars
- 1
- Mis à jour
- 31 mars
gorden888happycode-imagegen
Generate or edit raster images through the HappyCode OpenAI-compatible GPT Image 2 API. Use when the user requests HappyCode or this project uses it as the default backend for new images, reference-image transformation, composition, inpainting, editing, batches of 2-5 images, or first-use configuration.
- installations
- 1
- GitHub Stars
- 1
- Mis à jour
- 17 juil.
kavionaiai-automation-workflow
Use this skill for prompts, Gemini CLI extensions, MCP servers, agent workflows, tool integrations, embeddings, retrieval, LLM features, and automation scripts.
- installations
- 1
- GitHub Stars
- 1
- Mis à jour
- 6 mai
lvtd-llcgame-playtest-planning
Plan, run, and interpret game playtests. Use when validating prototypes, onboarding, difficulty, mechanics, UI clarity, retention, or fun; when writing playtest scripts, surveys, observation plans, or telemetry requirements.
- installations
- 1
- GitHub Stars
- 1
- Mis à jour
- 28 juil.
patinaprojectautomate-me
Use 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 plugin-dev:skill-development + unslop, optionally pulling fresh evidence from recent transcripts.
- installations
- 1
- GitHub Stars
- 1
- Mis à jour
- 8 sept.
patinaprojectbabysit
Watch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user wants the agent to shepherd it without re-prompting.
- installations
- 1
- GitHub Stars
- 1
- Mis à jour
- 8 sept.