Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics
Full-stack frontend development combining premium UI design, cinematic animations, AI-generated media assets, persuasive copywriting, and visual art. Builds complete, visually striking web pages with real media, advanced motion, and compelling copy. Use when: building landing pages, marketing sites, product pages, dashboards, generating media assets (image/video/audio/music), writing conversion copy, creating generative art, or implementing cinematic scroll animations.
Generate images using Google Gemini via Chrome browser automation. This skill should be used when the user wants to create, generate, or produce images with Gemini, Google AI, or Imagen. Supports resolution control (0.5K, 1K, 2K, 4K), aspect ratios, up to 14 reference images, style transfer, text rendering, image editing, and inpainting. Automatically downloads generated images and moves them to the desired location. Triggers on requests like "generate an image", "create a picture with Gemini", "make me a 4K image", or "use Gemini to create artwork".
Fix a numbered GitHub issue end to end from an isolated clone: understand the issue, create a dedicated branch and linked draft pull request, push progress checkpoints, implement and test the fix, update the changelog, mark the pull request ready, monitor and repair CI until it passes, and merge the successful PR. Use when the user invokes `/gh-fix OWNER/REPO#ISSUENUMBER`, `/gh-fix ISSUENUMBER`, `$gh-fix OWNER/REPO#ISSUENUMBER`, or asks for this complete GitHub issue-to-merge workflow.
Use when the user asks to review a pull request by number, URL, or branch ("review this PR", "review PR 123"). Fetches PR details, reads diff and failing checks, and produces structured feedback across code quality, security, performance, testing, docs, architecture, dependencies, CI/CD coverage, and completeness. Accepts optional $ARGUMENTS for the PR reference.
Use when stale git branches pile up after pull requests merge—local branches marked [gone], squash-merged branches that `git branch --merged` does not list, or leftover remote branches in a repo without auto-delete. Also use when the user names branches to purge, or asks to clean up, prune, or purge branches.
Plan a product launch from pre-launch audience building to a 90-day growth plan, with named communities, platform-specific launch tactics, channel rankings, and a budget for $0-$500 a month. Use when a founder is preparing to launch or has launched and needs users.
Godot 4.x game architecture, authoritative state, data ownership, managers, autoloads, scene flow, and save/load boundaries. Use when deciding where runtime state lives, splitting scene-local and persistent systems, coordinating menus and gameplay scenes, designing new-run/reset behavior, or implementing versioned persistence.
Invoke when Earth Engine, GEE, ee., or geemap is named; when work needs its server-side catalog; or when choosing Earth Engine versus local xarray or desktop processing for a large area or long archive. Covers image collections, masking, compositing, reducers, zonal statistics, time series, classification, quota-aware batching, and exports. This is an execution platform skill; combine it with remote-sensing-analysis or change-detection when those skills own the scientific method.
Grilling session that challenges a plan against the existing domain model, sharpens terminology, and updates documentation (LANGUAGE.md, MAP.md, decisions) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language, system map, and documented decisions.
Opt-in gate for tempa-spec's dark mode (bounded autonomous decision-making across proposal-through-align, optionally through apply). Never offered proactively; activates only when the user asks for it unprompted, in their own words. Shows a mandatory risk warning before confirmation, then asks which variant (planning-only or +implementation) and creates dark.md. Use once, at or after the proposal interview, only on explicit user request.
Single source of truth for where an escalation-worthy finding goes when tempa-spec's dark mode is active (dark.md exists). Each of specs, design, align, and apply points here instead of inlining its own dark-mode carve-out. Specifies which findings route to hrt-dark-mode-decision-gate, which still go to the user, and which dark.md section records the result.
Turn supplied plans, evidence, comparisons and explanations into clear, expressive, accessible HTML people can inspect and use. Support useful interaction and requested live updates. Exclude originating domain conclusions, decision prototypes, production UI and deployment.
Diagnose CDN business abnormal HTTP status codes (4xx/5xx) using hcloud CLI. Discover and quantify 4xx/5xx volume, localize the exact status code and time window, fork edge-generated vs origin-generated via back-to-source status statistics, correlate top-N distribution, narrow root cause on CDN edge config or origin side, and 取证 per-request access logs. Use this skill when the user wants to: (1) diagnose CDN abnormal 4xx/5xx status codes, (2) root-cause a 403/404/5xx spike on a CDN domain, (3) tell whether abnormal codes are generated by the CDN edge or returned by the origin, (4) troubleshoot CDN business exception status codes during daily inspection or incidents. Triggers include: 状态码异常, 业务异常码, 4xx, 5xx, 403, 404, 502, 503, 504, status code, abnormal status, CDN异常, 边缘/回源, 限流, status code analysis, edge vs origin
Manage the full lifecycle of CloudRobo assets — query repositories and catalogs, create/list/show/update/delete assets and versions, batch-delete, tag management, predefined tag discovery, Action CRUD, permission checks, marketplace search, official/community asset listing, asset lineage, and local-to-OBS import/export. Triggers include: asset import, asset export, asset version management, tag management, Action configuration, permission check, marketplace search, lineage query, repository listing, catalog listing, publication asset discovery, 资产管理, 资产导入导出, 版本管理, 标签管理, Action配置, 权限校验, 广场搜索, 血缘关系, 资产仓库, 目录查询.
Huawei Cloud Flexus X Instance Deployment - DeepSeek Harness (dsh). ⚠️ Deployment involves actual charges, must confirm region/flavor/billing mode with user before execution. Triggers include: "部署DeepSeek Harness", "部署dsh", "部署DeepSeek智能体", "创建AI智能体服务器", "Deploy DeepSeek Harness", "Deploy dsh", "Create AI Agent Server", "Deploy AI Harness", "DeepSeek Harness", "dsh", "Flexus X", "ECS部署", "AI智能体".
Guide for creating and maintaining outbox-based eventually consistent operations in Sentry. Most commonly used for cross-silo data replication, but applicable anywhere eventual consistency is needed — including single-silo deferred side effects, audit logging, and event fanout. Use when asked to "add outbox", "add outbox replication", "replicate model to control silo", "replicate model to cell", "add outbox category", "write outbox signal receiver", "debug stuck outboxes", "outbox not processing", "data not replicating", "test outbox", "migrate model to use outboxes", "backfill outbox data", "outbox coalescing", "ReplicatedCellModel", "ReplicatedControlModel", "OutboxCategory", "OutboxScope", or "outbox_runner". Covers model mixins, category registration, signal receivers, testing, backfill, and debugging workflows.
Plan, write, time, style, and validate motion-graphic beats for long-form talking-head HyperFrames videos. Use when Codex is asked to add or improve visual beats, glassmorphism lower thirds, crumpled-paper full-screen takeovers, transcript-synced callouts, pacing coverage, YouTube retention graphics, or render-ready overlays in an existing HyperFrames video project.
Interactive loop that builds and tunes an AI prompt for evaluating whether a company fits a client's ICP. Run after any list-building skill (disco-like, blitz-list-builder, google-maps-list-builder, prospeo-full-export) to qualify companies before scaling. Iterates batches of 10 companies with user feedback, stops when 2 consecutive rounds have zero corrections, saves the final prompt for reuse. Always uses Claude Code Task sub-agents — never an external API key.
Strategic guidance for operationalizing machine learning models from experimentation to production. Covers experiment tracking (MLflow, Weights & Biases), model registry and versioning, feature stores (Feast, Tecton), model serving patterns (Seldon, KServe, BentoML), ML pipeline orchestration (Kubeflow, Airflow), and model monitoring (drift detection, observability). Use when designing ML infrastructure, selecting MLOps platforms, implementing continuous training pipelines, or establishing model governance.
Monitoring, logging, and tracing implementation using OpenTelemetry as the unified standard. Use when building production systems requiring visibility into performance, errors, and behavior. Covers OpenTelemetry (metrics, logs, traces), Prometheus, Grafana, Loki, Jaeger, Tempo, structured logging (structlog, tracing, slog, pino), and alerting.
Run an improve-my-MCP campaign: an autoresearch-style loop that measures the MCP agent experience with the eval harness, picks the highest-impact tool problem from production data, makes one bounded fix, and keeps it only if before/after scores improve. Use when asked to "improve my MCP", run an MCP improvement campaign, fix tool discoverability or descriptions based on evidence, or prepare an eval-backed PR for a tool change. Every shipped change must carry eval evidence; guardrails below are hard rules.
Configure IndyKite Agent Gateway (IAG) in front of agent-to-agent (A2A) agents or MCP servers—the self-hosted proxy that resolves the caller through ContX IQ whoami, asks AuthZEN for one admission decision against a KBAC policy comparing the delegation chain (`$ik_token.act_chain`) with a workflow in the IKG, limits the tools, resources, prompts, and A2A skills a caller may use (capability checks, `CAN_USE`), and forwards with a delegation token. Optionally use the self-hosted IndyKite Token Service (ITS) to mint the `X-IK-Token` so multi-hop chains grow, and the Intent Agent (`ibac.enabled`). Use when wiring up A2A or MCP policy enforcement, modeling `Workflow` / `Agent` / `INVOKES` / `CAN_TRIGGER` / `HAS` in the IKG, authoring admission or capability policies, configuring `JARVIS_*` / `config.yaml` (`token_service`, `authzen.capabilities`, `cors`, `ibac`), serving the agent card or OAuth metadata, running the Token Service, reading IAG audit records, or debugging IAG 401/403 responses
Author an IndyKite ContX IQ (CIQ) policy plus its Knowledge Query that creates a brand-new node in the IndyKite Graph (IKG), then run it via `POST /contx-iq/v1/execute`. Use when ingesting a new entity through CIQ - no relationship creation, no updates to existing nodes, no deletes.
Author an IndyKite ContX IQ (CIQ) policy plus its Knowledge Query that creates a brand-new relationship between two existing nodes in the IndyKite Graph (IKG), then run it via `POST /contx-iq/v1/execute`. Use when wiring two existing entities together through CIQ - no new nodes, no relationship updates, no deletes.
Audit Infrastructure-as-Code for security misconfigurations before it ships — Terraform (.tf/.tfvars/.hcl), CloudFormation/SAM (YAML/JSON), Kubernetes & Helm manifests, and Docker / Docker Compose. Reads the IaC offline and reports each misconfiguration at file:line with a severity (P0–P3) and a corrected snippet. A dependency-free scanner does the high-recall first pass; the model adds blast-radius and cross-resource judgment. No cloud credentials, no terraform apply, no pip install. Trigger when reviewing a Terraform plan before apply, auditing K8s/Helm manifests or a Dockerfile before deploy, checking CloudFormation for public S3 buckets or open security groups, doing a pre-deployment or compliance (SOC-2 / PCI-DSS / ISO-27001) security review, or when the user asks "audit this Terraform", "is this S3 bucket public?", "is this security group open to the internet?", "is this container running as root?", "what's the blast radius if this infra is wrong?", or "run an IaC security scan".
Best practices for internationalization (i18n) and localization (l10n) in Flutter, using the built-in `flutter_localizations` and `intl` setup with ARB files as the single source of truth. Use when adding, modifying, or reviewing ARB translations, locale setup (`l10n.yaml`, `generate: true` in `pubspec.yaml`, `flutter gen-l10n`, `localizationsDelegates`, `supportedLocales`), BuildContext l10n extensions such as `context.l10n`, hardcoded user-facing strings that should be localized, localized strings passed into shared or reusable widgets, or RTL/directional layout support with `EdgeInsetsDirectional`. Also use when asked to add or configure any third-party i18n or translation package (easy_localization, slang, flutter_i18n, or intl_utils), and when shipping or fixing a screen for a right-to-left language such as Arabic, Hebrew, Farsi, or Urdu, including mirroring padding, alignment, icons, or images, and replacing `EdgeInsets` left/right.
Analyze resumes and design interview strategies using evidence-based methodology. Transforms interview prep from "read resume → ask questions" into "define standard → forensic evidence → future simulation". Combines Geoff Smart's Topgrading, Lou Adler's performance-based hiring, and Daniel Kahneman's bias control. Use when preparing for interviews, creating structured interview guides, or designing questions to validate candidate competencies.
Investigate logs in a PostHog project: verify a service or deployment is healthy, explain an error spike, triage an incident, or understand what a log stream is saying. Use when the user asks to "check the logs", asks whether a service, deploy, release, or change is working or broke anything, asks why errors are up or what changed, wants the logs of one trace or run, or wants a daily service health report. Routes the logs MCP tools (service health, group-by, before/after pattern diffing, context around a trace or run, bucketed counts, raw rows) so investigations start from summaries instead of raw rows or hand-written SQL over the logs table
Build RTL-first UI component libraries and design systems for Israeli applications with Hebrew typography. Use when user asks about Hebrew UI components, "itzuv" (design), Israeli design system, Hebrew font pairing, RTL component library, "tipografia ivrit" (Hebrew typography), or gov.il design patterns. Covers RTL-first component architecture, Hebrew font pairings (Heebo+Inter, Rubik+Source Sans 3), gov.il design system patterns, Israeli formatting conventions (shekel sign, day-first dates, 24-hour clock), and culturally appropriate UI for Israeli users. Do NOT use for general RTL CSS (use hebrew-rtl-best-practices) or accessibility audits (use israeli-accessibility-compliance instead).
Route a Jam (a jam.dev screen recording or screenshot with the console, network and user actions attached) to the right Jam skill. Use when the user shares a jam.dev link with no clear ask ("look at this jam", a bare link), or types /jam. For a clear ask (fix, test, ticket, record, annotate), use that skill directly.
At the end of a batch of agent work (several fixes, a test run, a set of tickets), return one table that ties each claim to the Jam (a jam.dev screen recording with the console and network attached) that shows it, with its status and link, and file those Jams so they can be found later. Use when the user asks "give me the jams", "which jam shows this", "what was the jam I gave you", "show proof for each", or when a run that recorded Jams finishes and the user wants the proof listed.
Turn a narrated Jam (a jam.dev screen recording with the speaker's transcript, console, network and user actions attached) into a numbered list of every change the person asked for, each tied to the moment, the frame and the words it came from, then work through the list. Use when the user pastes a jam.dev link and says "do what I said in this", "consume this jam", "make it look like this", or shares a feedback, walkthrough or reference recording rather than a single bug.
File a Jam (a jam.dev screen recording with the console, network and user actions attached) as an issue in the team's tracker, such as Linear, GitHub Issues or Jira, with the link, repro steps, the key frame and the errors, after checking it was not filed already. Use when the user says "make a ticket for this jam", "file this jam as a bug", "put this jam in Linear", "open an issue for this recording", or asks whether a Jam was ever ticketed.
Use when user asks to create/design a big screen (大屏), full-screen data visualization, or says "创建大屏", "生成大屏", "新建大屏", "设计大屏", "做一个大屏", "BI大屏", "数据大屏", "可视化大屏", "监控大屏", "create big screen", "design big screen", "BI visualization big screen". Also triggers when user describes big screen requirements like "做一个销售数据大屏" or mentions full-screen display like "展厅展示", "监控室大屏". Make sure to use this skill for big screens (大屏) — NOT dashboards (仪表盘/看板), which use a completely different layout and styling system.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.