Skills
100,696 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when writing or reviewing Gleam code on the Erlang target - especially Wisp + Mist HTTP services, OTP-based processes (gen_server / supervisor analogues), justfile workflows, gleeunit testing, `gleam format`, GitHub Actions CI, and performance measurement. Trigger on `gleam.toml`, `.gleam` files, or Erlang/BEAM-related symptoms even if the user does not say "Gleam" by name.
How Go tests are written in these repos: assertions, tables, test doubles, helpers, async waits, golden files, fuzzing, benchmarks, and integration tests against a real Postgres via the bundled pgtest helper (one shared testcontainer, a fresh database per test). TRIGGER — load BEFORE writing, editing, or reviewing any *_test.go file, testdata/ golden file, fuzz target, or benchmark, or when the task mentions go test, test helper, fake, mock, stub, table test, testcontainers, TestMain, test database, flaky test, or coverage in a Go repo. Plain requests count: “write the tests,” “add a test for this,” “fix the failing test,” or a feature task whose last step is testing it. Load alongside go-idiomatic and tdd, not instead of them. SKIP when no Go test code is written or judged
Write or improve a README.md for an open source project. Use this for any request to create, rewrite, review, or polish a README, project description, or "getting started" docs for a library, framework, or tool, or to make an open source project more popular or attractive to users. Do NOT use for internal/private repo docs, API reference generation, or CHANGELOG/CONTRIBUTING files.
Google Analytics 4 implementation and analysis reference. Use when querying live GA4 report data, setting up a GA4 property or data stream, installing gtag.js, designing event or ecommerce tracking, registering custom dimensions or audiences, sending server-side events via Measurement Protocol, linking GA4 to BigQuery and understanding the export schema, debugging with DebugView, or configuring Consent Mode and data retention. Do NOT use for general GTM container work such as triggers, variables, custom templates or server-side containers - use google-tagmanager; Google Ads scripting or ad reporting - use google-ads-scripts; writing or running SQL against GA4 export tables - use the bigquery skill; Universal Analytics or non-Google analytics tools.
Grooms a GitHub Projects backlog: verifies issues against the code, ranks and clusters them, and plans milestone, link, and closure changes, or promotes issues to Ready. Proposes tracker changes; each requires approval. Use when the user says "groom the backlog", or when asked to groom, triage, or prioritize a backlog, or to promote issues to Ready.
A pattern for adding a self-narrating (typed out) guided walkthrough to any HTML/web application. Use this skill whenever the user wants to add a guided demo, auto-narration, self-running presentation, or step-by-step tour to an HTML page, web app, prototype, HTML slide deck, dashboard, or data story.
Turn a script into MiniMax H3 shot lists with working emotional performance — beat tables, shot counts, expression direction, and the acting techniques that actually render. Use when breaking a script or scene into H3 shots, writing beat timings, directing a character's face or emotion, fixing flat/wooden performance, deciding shot length or how many beats a shot can hold, or writing prompts for episodic narrative work. Complements the minimax-h3 skill, which covers prompt syntax and ComfyUI setup but not performance or shot breakdown.
One-screen quick reference for the Origin plugin. Lists the daily verbs, the daily flow, where data lives, and how to view it without a GUI. Use when the user says "help", "what can I do", "list origin commands", "how do I use origin", or invokes `/help`.
Diagnose CDN domain DNS resolution issues using hcloud CLI and Python DNS probes. Query the CDN domain detail to obtain the expected CNAME, probe the actual DNS resolution of the domain via scripts/dns_resolve.py (dnspython) to collect resolved IP addresses, and verify the IP attribution against Huawei Cloud CDN via ShowIpInfo/v2 to determine whether the domain has been correctly resolved to Huawei Cloud CDN. Use this skill when the user wants to: (1) diagnose CDN DNS resolution failures, (2) check why a domain is not resolved to Huawei Cloud CDN, (3) verify DNS configuration for CDN domain access, (4) troubleshoot DNS anomaly or resolution timeout issues. Triggers include: "DNS解析诊断", "DNS异常", "域名解析失败", "CDN解析异常", "DNS配置", "DNS diagnosis", "resolution diagnosis". User utterance examples: "域名解析不到华为云CDN", "CNAME 配置了但没生效", "DNS 解析超时了", "解析出来的 IP 不是华为云的", "域名没解析到 CDN". Do NOT use for: HTTPS certificate errors, origin-pull failures, domain ownership verification, or any CDN/DNS configuration change (this skill is strictly read-only).
Run the R2C (Robot-to-Cloud) data-plane client — start the robot-side edge client (Zenoh pub/sub with mTLS credential bundle, hardware adapter, translator, control loop). The credential bundle is produced by the robot skill's export-certificate command. This skill does NOT cover robot registration or certificate export (use the robot skill). Triggers include: r2c client, robot edge client, Zenoh, mTLS, credential bundle, hardware adapter, robot config, dry_run, observation recording, custom adapter, robot-to-cloud, R2C客户端, 硬件适配器, 机器人配置, 凭证包.
Huawei Cloud CloudDeploy (CodeArts Deploy / 部署) management, execution, and failure analysis using the KooCLI hcloud command-line client. Covers deploy application listing and creation, deployment task listing/detail/creation, task start, task deletion, deployment failure root-cause analysis (agent offline, timeout, missing artifact, permission), and OBS artifact link verification. Query and Analyze actions run automatically (R3); Create/Start actions require preview and user confirmation (R2); Delete requires explicit confirmation (R1). Supports AK/SK credentials and local hcloud profile authentication. Triggers include: "CloudDeploy", "CodeArts Deploy", "部署", "deploy task", "deployment", "deployment task", "deploy application", "部署任务", "部署应用", "start deploy", "发布部署", "release", "artifact deployment", "制品部署", "deploy failure", "部署失败", "pipeline deployment", "CI/CD deployment".
Huawei Cloud MRS cluster fault diagnosis skill. Diagnoses service faults, instance faults, and host faults through progressive root cause localization: quick log scan first, host troubleshooting when host issues are found, detailed investigation when no conclusion is reached. Diagnosis is driven by the built-in LakeWatch API client (lakewatch mode) or the MRS Manager API client (manager mode) and the per-layer knowledge base under fault_layer/ and scenarios/ (lakewatch) or fault_layer_manager/ and scenarios_manager/ (manager). The API mode is auto-detected by check_api_mode.py. No commands outside the knowledge base are fabricated. Applicable to MRS fault diagnosis and root cause localization scenarios where a service name or node name is provided. Trigger words: "故障诊断", "故障定位", "fault diagnosis", "fault diagnose", "MRS故障", "服务故障", "实例故障", "主机故障", "集群排查", "集群诊断", "启动失败", "停止异常", "KrbServer故障", "DBService故障", "fault troubleshooting"
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
Image resizing and compression tool skill. Used to resize images by specified pixel width and height, ratio, or maximum size limit, and supports smart compression to a specified file size. Applies to scenarios such as batch image processing, generating thumbnails at specific sizes, and compressing images to meet file size limits.
Configures Zero Trust Network Access (ZTNA) in AWS, Azure, and GCP using identity-aware proxies, micro-segmentation, and continuous verification with conditional access policies, replacing VPN-based access with BeyondCorp-style architectures. Use when replacing VPN remote access with identity-based controls, limiting lateral movement via micro-segmentation, or exposing cloud workloads to authenticated users without public internet exposure.
Route Data Analytics plugin-level requests and broad analytics work to the right focused workflow. Use when Data Analytics is at-mentioned, or for analytics requests involving data, metrics, dashboards, reports, charts, notebooks, spreadsheets, KPIs, market sizing, or semantic layers.
Daily industry intelligence scanner. Scans web, social media, news, blogs, and communities for industry-relevant events, trends, and signals. Produces a comprehensive intelligence briefing plus strategic GTM opportunity ideas. Orchestrates existing scraping skills — does not reimplement data collection.
Install the base skills every agent should have, globally and in one command - /initialize itself (so it can be rerun), skill-manager, /show-me, /grill-me, /wait-what, /connect-tool and /use-style, all from this kit - plus the settings that stop Claude Code and Codex from asking before each action, the cc / cx shortcuts, the usage band above the prompt in the Claude desktop app and the terminal status bar (context, cost, 5-hour and weekly limits), then asks the user which visual style they like and makes it the default for every file the agent creates. Use when the user types /initialize, sets up a new computer, says "installe les skills de base" or before setup-brain.
Real Chrome/Brave + macOS Computer Use from inside the browser — zero CDP fingerprint, real sessions; mandatory for visual deploy verification. Drive clickwork yourself. USE WHEN verify deploy, confirm UI, screenshot verification, computer use, macos automation, debug web, troubleshoot, visual check, motion/animation bug, jank, transition stutter, scrub a flow, console logs/errors, runtime/JS/react errors, mismatch warning, network traffic/log, HAR/pcapng export, hydration/blank-page debug, flash then blank/page broken, why is this not working/what's happening on the page, authenticated page, bot detection bypass, reproduce bug, drive native app, about to ask the operator to click/navigate/fill a form/log in/approve OAuth, OAuth consent flow, complete a web login, do this in your browser. NOT FOR residential-proxy crawling (BrightData) or social actor scraping (Apify).
Deep interview analysis using dynamic expert routing. Automatically selects top domain thinkers based on role type to distinguish genuine capability from performance, identifying Battle Scars over Methodology Recitation. Applicable to any professional position including product management, engineering, design, operations, sales, and data science.
Answers why code is shaped as it is with an evidence-rated report, tagging each claim [Direct], [Supported], [Inferred], or [Speculative] and closing with a Sources Consulted list that covers git, PRs, tickets, docs, chat, and observability, naming the sources left unchecked. Read-only. Use when the user says "why is it built this way?", or when asked why code is shaped as it is, why a value or limit was chosen, what alternatives were rejected, or what forces shaped a decision, including when the asker offers a guess at the reason. Use it even when commits or PR text are already in context, since a plain answer from them omits the tiers and the unchecked sources. Not for how code works; use explaining-architecture.
Reviews iOS animation code for correctness, performance, accessibility, and Apple API best practices. Use when reviewing .swift files containing animation code — withAnimation, .animation(), PhaseAnimator, KeyframeAnimator, matchedGeometryEffect, navigationTransition, CABasicAnimation, CASpringAnimation, UIViewPropertyAnimator, UIDynamicAnimator, symbolEffect, scrollTransition, contentTransition, or custom Transition conformances.
Composable transformations of Python+NumPy programs. Differentiate, vectorize, JIT-compile to GPU/TPU. Built for high-performance machine learning research and complex scientific simulations. Use for automatic differentiation, GPU/TPU acceleration, higher-order derivatives, physics-informed machine learning, differentiable simulations, and automatic vectorization.
Triggers when the user says 「批量修复」「批量 jira-fix」「jira-fix-batch」「批量修复多个 Jira」「批量修复以下 bug」/ batch fix, batch jira-fix. Thin trigger shell: parse Jira IDs/URLs and enqueue them into goal-driven-batch with Engine jira-fix-workflow. Does not run fixes or merge. Do NOT use for a single issue (jira-fix-workflow) or a non-Jira queue (goal-driven-batch).
Prevents, detects, and remediates files that should never be committed — secrets (.env, API tokens, hardcoded credentials) and dev artifacts (build output, scratch databases, editor/OS files). Covers .gitignore (and why it does not untrack), git rm --cached, auditing tracked files, history scrubbing, and credential rotation. Use when a repo has committed secrets or junk, when setting up a new repo's ignore rules, or when reviewing what a repo actually tracks.
Use when executing an approved Krypton plan, GOAL.md, or implementation plan that already defines intent, ownership, contract, cutover, task boundaries, and acceptance evidence. Use for main-agent execution with explorer, plan-reviewer, reviewer, maintainer, or verifier gates.
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.