Skills
100,344 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Debugs issues users encounter with Tuist-generated projects by reproducing the scenario locally, building Tuist from source when needed, and triaging whether it is a bug, misconfiguration, or something that needs team input. Use when users report generation failures, build errors after generation, or unexpected project behavior.
Find the mocks, stubs, fakes, hidden fallbacks and placeholder implementations standing on a real code path outside the tests, where nothing real runs and a success report is false, and propose the real dependency or an honest failure for each. Use when a change or a named file, directory or diff may ship a test double or a swallowed error into production, when a catch or except returns an empty list, None, a default or true, when a guard lets a request through because its key, config or input is missing, when a function raises NotImplementedError or returns a TODO value on a live path, when a feature reports success but nothing seems to happen, or before calling work done that touched error handling, integrations or service clients.
Builds a one-screen executive report dashboard for teachers and lecturers. Presents all key class indicators (assignment submission rate, average CPMK, grade distribution, alerts for students needing attention) with a responsive Mobile-View First design and strict credential security.
Connect a JavaScript or TypeScript app to Fallow Cloud production runtime coverage. Use when asked to set up Fallow Cloud, add the Fallow beacon, send runtime coverage to Fallow Cloud, or find out why Fallow Cloud shows no data for a repository. Do not use for local code-quality tooling; use fallow-setup for that. Do not use to read runtime data of a repository that is already set up; use the fallow skill for that.
Use when the user asks to fix, patch or upgrade a Node.js vulnerability (e.g. 'Please fix my Node vulnerability'), the October 21, 2026 Node.js security release, CVE-2026-111497 (Brotli RCE), or end-of-life Node 20, across Docker images, .nvmrc/.tool-versions, setup-node CI, Lambda and IaC. Read-only inventory, approval gate, regression tests, focused PRs.
MANDATORY - use before planning, building, or redesigning an ArcGIS application, including requests that do not specify an ArcGIS technology. For existing applications, use when a change could affect architecture, product, technology, data access, or authentication. Review context, clarify consequential unknowns, and route to relevant authentication and build skills.
Guides day-to-day work in Tuist-generated Xcode workspaces, including generation, build and test commands, and buildable folders. Use when working in a Tuist-generated project or when users mention `tuist generate`, `xcodebuild test`, or generated workspaces.
Design and build self-contained interactive HTML5+CSS3+JS presentation slides in 16:9 format, with keyboard navigation, full-screen mode, interactive QR codes for students, and print-ready layouts for instant PDF export without distortion.
Turns one image of any subject (an AI image, a render, a photo of a figurine or product, a drawing, or an idea turned into an image first) into a watertight 3D sculpt that is measured against the image and recorded step by step in Blender: front maps (mask, metric depth and focal length, normals), generated views of the unseen sides (registered over the whole circle and screened), a visual hull, then many recorded fit passes against every normal map, silhouette and the photo's depth, with symmetry, focus regions, gap cuts and smoothing. Ships a CLI (`scripts/i2s.py`) for case scaffolding, fal calls with a budget, registration, carving, fitting, map checks, Blender replay, timelapse and turntable films, exports (GLB, OBJ, STL) and a report. Use when the user wants a 3D model or sculpt "from this image", a figurine or character turned into a mesh, a sculpting timelapse, or a check of a 3D model against a reference image. Not for scenes or rooms, text-to-3D without any image, rigging or animation, PBR texturing, or CAD-accurate parts.
Aggregate and read real user monitoring (RUM) data via KubeSense MCP — sessions, views, actions, errors, resources and long tasks from browser and mobile apps. Covers the rum_<type> signals, the per-event-type field catalog, which fields accept LIKE or group-by, nanosecond durations and their _ms/_s twins, feature flags and attributes, and the dashboard panel shape. Counts, rates and percentiles with analyze-telemetry, raw rows with search-rum. There is no alerting, SQL or SPL for RUM.
Diagnose why a Mac (especially one running Claude Code, other AI coding tools, or several Electron-based IDEs at once) is slow, hanging, or freezing due to memory pressure and swap thrashing. Covers reading real swap/memory numbers, finding MCP-server and plugin process bloat, spotting orphaned or duplicate background processes, safely clearing regenerable caches, and recognizing when a killed process keeps respawning because something else supervises it. Use this whenever the user says their Mac/MacBook is slow, laggy, hanging, freezing, "using too much memory," has "high memory pressure," or asks to find/stop/kill whatever is eating RAM or CPU. Every fix in this skill is reversible (stop, kill, disable, clear cache) — it never deletes or uninstalls anything, and it says so explicitly before running anything.
Rewrites a bolted-on feature so it reads as if it was always part of the original design. Use when a diff, branch, or commit adds a feature through special cases, flags, aliases, parallel components, or preservation tests instead of reshaping the existing code
Builds a professional Excel spreadsheet workbook (.xlsx) for calculating Outcome-Based Education (OBE) assessment fulfillment, mapping CPL and CPMK attainment per student, grade distribution matrices, and visualizing accreditation achievement charts.
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser through the `orca` CLI. Use when the user says "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "handoff" / "handover" / "give this to another agent", "Orca browser", "orca artifacts", or "share skills". Prefer it over raw git worktree, ad hoc PTYs, or Computer Use when Orca state is involved. Use Computer Use only when a visible window needs GUI control that a CLI, filesystem, or API cannot do.
Transform mocked-up UI specs (specs-ui skill project) into a purely UI clickable prototype in HTML + Tailwind + Alpine.js: main flows are wired up (navigation, forms, states, simulated data stored in the browser, reset), with guided test scenarios for user testing and demos, published as a multi-page artifact. Use whenever someone wants a prototype, clickable mockup, interactive demo, user-testable flow, user test, or a version "you can click through" based on existing specs or mockups, even without saying "prototype".
Land handed-over material of any shape (a note, a link, a dump, a correction) in the document of an existing knowledge base that owns it: read the base's own routing documents first, edit in each document's own grammar, hash files before writing, and report what cannot be placed instead of guessing. User-invoked. Not for researching the subject or designing a new structure.
Keep a repository's README for the person deciding whether and how to use it, its AGENTS.md (or a CLAUDE.md read through it) for the agent working inside it, and the manifests hosts read first (package.json, plugin and marketplace files, agents/openai.yaml) on the repository's one name: audit them with the bundled script, then move each line to the file whose reader needs it and fix each disagreeing manifest. Use when writing, rewriting or reviewing a README or an AGENTS.md, when an agent-only command shows up in a README or marketing copy in an agent guide, when deciding which file a section belongs in, or after a rename. Not for contracts, ledgers, changelogs or release notes.
Republish a GitHub repository as one signed commit: squash its whole history into one commit with the same tree, then delete the remote and recreate it under the same name and settings, because a force push leaves the old commits reachable by hash, in forks and in pull requests. User-invoked, and the deletion cannot be undone.
Resolve one bug report that a customer or tenant member filed through an in-app reporting bridge into an issue tracker: read the issue and the bridge metadata, decide whether there is enough to act on, rebuild what the reporter did from production data read only, fix the root cause and every sibling of it, prove the fix fails on the old code and passes on the new one in the running app, commit with the closing keyword, and answer the reporter through the bridge in plain language with a request to confirm. Use when: (1) the user hands over an issue number or URL of a report a customer filed, (2) a report has a title and an empty or thin description, (3) the user asks to check whether there is enough information before fixing, (4) the user asks to reply to the reporter once it is fixed, (5) the evidence shows the app working as built and the fix is a product decision, (6) the report asks for something the app already has and the answer is a how-to, (7) the report asks for a feature the app does not have and the reporter needs an answer now, built or not, (8) a reply already sent was wrong and needs a correction, (9) the user mentions: resolve issue, fix issue #, tenant-report label, customer bug report, "check if you have everything you need", /reply, leave a reply for the reporter, ask the reporter to confirm, audit log, production read only, supabase db query --remote --read-only, PostgREST max_rows, 1000-row cap, "Fixes #", "settled separately instead of together", "it already exists", "for the whole salon", "can it be done", feature request, feature freeze, out of scope, "only clients starting with A", "explain where the list is", "I am at reception and cannot settle", wrong role, permission override, "could not move the visit". Carries a sufficiency matrix, a read-only production protocol with the user's approval, a reporter timeline query, a root-cause table with the check that tells each cause apart, the variants to put to the user when the cause is behaviour, a guard test that fails on the old code, a claim check before any reply, and reply templates for a fix, a how-to, a feature not built now, the account's setup and a correction. Any git repository with the gh CLI and a Postgres backed multi-tenant app; the tracker, the reply channel, production access and the app's verify procedure are the seams. Not the bridge itself, not bulk triage, not outage response.
Use when studying a SaaS web product from the outside in order to rebuild, clone or copy it (ClickUp, Pipedrive, Notion, a CRM, a project tool), when documenting its UX, screens, components, data model, business rules or API through a browser the agent drives, when assessing what would block a clone from launching (permissioned integrations, regulation, certifications), or when an agent must explore a live SaaS account without damaging production data or notifying real people.
Check whether an item falls inside a target's existing scope, as the target's own written sources define it; it never sets or narrows the scope of a piece of work. Use before a skill, script, module, rule, feature, doc section, or file is added to, moved into, promoted into, merged into, or upstreamed to a suite, repository, plugin, package, or document, and when someone asks whether X is in scope for Y, whether X belongs in Y, or which of several homes should own X.
Organizes and builds a per-session/class-meeting directory structure for courses or classes interactively and with full confirmation. Prepares subfolders for materials, presentations, exercises, games, practical work, and student assignment submissions.
Records the best scenes of a website or web app (WebGL hero, 3D, scroll) as 1080p MP4 for decks, uploads them to Figma Slides, and builds brand or product showreels in Remotion. Use on "record the site scenes", "site video for the deck", "showreel", "launch video", "gerar vídeo do site", "vídeo pro deck", "reel do produto", /site-reels.
Rules, Remotion helpers and audio scripts for stop-motion style video cut to music, proposing Remotion by default to make it. A low frame rate is kept on purpose, with one pose per eighth note of the song. Pages start on bar lines, clicks land on kicks and snares, and the skill teaches when to skip a beat. Use when making or reviewing stop-motion, low frame rate, beat-synced or music-synced video. Also use for cutting a video to a song, Remotion launch films cut to a track, compositions timed to a BPM, metronome or click tracks, kinetic type timed to a beat, or scenes played live on a web page in time with a metronome. It covers measuring a song's tempo, bars and drops, and deciding where a cut, a click, a hold or a transition should land.
Generates periodic learning progress report files and individual student learning portfolio books in Microsoft Word (.docx) or Excel (.xlsx) format, presenting work samples, grade history, and reflections on competency attainment.
Automatically assess student assignment files collected in the submissions folder against a grading rubric. Provide transparent analytical scores and constructive formative feedback, and automatically identify remedial and enrichment needs.
Use tdir-cli to query and directly generate the EMDR security operations threat daily report (including security incidents, endpoint and insight/ticket distribution, response times, and items requiring attention). Use when the user requests generating, recalculating, or reviewing an EMDR threat daily report or operations daily report. Does not handle TDIR global weekly reports, in-depth forensics of individual insights, or security incident response.
Verify web UI changes in headless Chrome with agent-browser, signed in as the project's Clerk test users, and run the project's relevant existing tests. Use after changing anything visible, or when asked to check, inspect, screenshot or exercise a browser flow.
Build a public catalog of Agent Skills in a Next.js App Router site, generated at build time from each skill repository's own files: a sync script that mirrors SKILL.md, README.md, CHANGELOG.md, provenance.md and evals/ into the repository, a loader that reads rules, releases and the provenance ledger from them, a catalog page with search and category filter, one page per category and per skill, the agent eval results (newest run per agent and prompt, failing runs included), JSON-LD, sitemap entries and a content validator. Use when: (1) a site should list the Agent Skills an organization publishes on GitHub, with install commands, rules, versions and agent eval results, (2) skill pages show an old version after a release, or an eval run never appears on the page, (3) adding agent eval results, prompts or a provenance ledger to existing skill pages, (4) the user mentions: skills catalog, Agent Skills page, skill directory, SKILL.md, skills.sh, npx skills add, evals/prompts.md, eval results, agent evals, Claude Code, Codex CLI, Gemini CLI, skills:sync, sync.json, raw.githubusercontent.com, provenance.md, CHANGELOG.md, Keep a Changelog, TechArticle, SoftwareSourceCode. Carries a sync that reads every file of a skill at one commit and swaps the mirror in whole, a loader that never fetches, an eval parser that rejects a malformed run with its reason instead of dropping it, and a validator that fails the tests on it. Next.js App Router; where the skills come from is a seam (GitHub or local checkouts) and the section layout it reads is one table. Not a way to write a skill, not an eval runner and not a package registry.
Point at something on the human's macOS screen with a big arrow and a sign ("Franz, click HERE"), and hand over values, secrets and questions on a floating cue card, using the bigarrow CLI. Use whenever the human has to look at, click, type into or choose a specific spot, button, field, window, tab or menu: show me where, point to it, which button, where do I click, zeig mir wo, guide me through this UI, the human must approve or sign something, or you need the human's hand and they may not be looking at the terminal; also to hand over credentials, a password, token, 2FA code, IBAN or command to paste, or to ask the human a question or a choice while they are away from the terminal. Mandatory when it is time-critical: a code that expires, a login or payment page that times out, a build waiting on the human.
Generates interactive quizzes and assignments based on educational board games (snakes and ladders, crossword puzzles, concept Monopoly, academic bingo, question mazes, spin wheels/Jeopardy) as standalone interactive HTML5 and printable worksheets (PDF/A4).
恢复被 C3RB3R / Cerber 系勒索软件（文件后缀 .L0CK3D、勒索信 read-me3.txt）加密的群晖（Synology DSM）或其他 Btrfs NAS 上的数据，无需密钥：利用 Btrfs 写时复制留下的旧 extent 逐字节还原原文件，并用 Btrfs 校验和逐块证实。覆盖 CoW / NoCOW 判定、子卷快照代数（lastsnap）效应、extent 树精确重组、大文件跨 extent 推测、统计、导出、验证和报告。只要用户提到 NAS / 群晖 / 黑群晖 被勒索、.L0CK3D、read-me3.txt、C3RB3R、Btrfs 文件被加密想恢复、"没有备份没有快照怎么救"，即使没提 Btrfs 或 extent，也应使用本 skill。Use for ransomware recovery of .L0CK3D files on Synology/Btrfs volumes without the key.
Assemble Chinese running-script calligraphy from original glyphs, look up character forms and sources, inspect radicals, and synthesize missing glyphs. Use for calligraphy composition, character images, or copybook references. Read this skill for exact CLI syntax before running commands
Connects player, item, upgrade, and enemy data through one stat model and a chosen defense formula (flat, ratio, level-scaled ratio, or capped percent), computes hits and seconds to kill and to die for each stage and enemy, and flags results outside designer target ranges. Use when setting or reviewing combat stats, choosing a defense formula, or checking difficulty per zone, level, or wave in any genre and engine.
Turn the changes in a git working tree into clean Conventional Commits: read the diff, run the repository's own check, stage by path, split unrelated changes into separate commits, write the message, and verify what landed. Use when: (1) the user wants to commit, save progress, record WIP or wrap up a finished task, (2) a working tree mixes unrelated changes that should become separate commits, (3) a change breaks existing usage and the release tooling must see it, (4) the user mentions: commit, commit this, commit my changes, save progress, WIP commit, conventional commit, commit message, git add, staged, untracked, BREAKING CHANGE, feat!, Co-Authored-By, pre-commit hook, "split this into commits". Carries the staging rules that keep secrets and build output out, the breaking-change markers that `bumpv` reads to choose a MAJOR release, the hook and amend rules, and a post-commit check that no attribution trailer landed. Any git repository and any stack; the repository's own check and documented conventions are the seam. Not a release tool, not a changelog writer and not a push or pull request flow
Models item enhancement (cost, success rate, and keep/downgrade/destroy on failure per level) and synthesis (fixed recipes and random merges that combine matching items into one of a matching set), computes the expected cost and attempts to reach each level, the value ratio of each recipe against stat budgets, and the expected crafts to get one specific result, and finds item-multiplication loops and items no drop, recipe, or declared source can produce. Use when designing or reviewing upgrade systems, crafting, merging, salvage, or item acquisition paths in any genre and engine.
Model database schemas, write and check migrations so they run safely on a live database, find why a query is slow from its plan, and audit a schema and its migration history in four modes: design, migrate, tune, and audit. Use when the user says “design the schema for …”, “write a migration to …”, “is this migration safe”, “check this migration”, “why is this query slow”, “explain this query plan”, “add an index for this query”, or “audit our database schema”.
Install the Datadog Agent on a Docker host—standalone Docker (Linux or Windows) or Docker Compose—with infrastructure metrics, container logs, APM trace intake, and DogStatsD enabled by default, plus optional live processes, tags, hostname, proxy, and container filtering. Keep the API key in a restricted env file rather than on the command line. Use when the user has Docker containers on a single server, wants to install Datadog on their Docker host, or wants to set up Datadog with Docker Compose. Does not install the Agent on Kubernetes or directly on a Linux, macOS, or Windows host (use dd-agent-install-kubernetes, dd-agent-install-linux, dd-agent-install-macos, or dd-agent-install-windows). Requires a Datadog account with a valid API key and application key; run `dd-account-setup` first if they are missing.
Install the Datadog Agent on Linux hosts—a single machine or a fleet—with support for cloud rollouts (AWS Systems Manager, GCP VM Manager, Azure Run Command), remote configuration management, proxy, FIPS, custom tags, and advanced configuration. Infrastructure metrics, logs, and the APM trace receiver are enabled by default; host Single Step Instrumentation is enabled only when requested (for an SSI-first request, use `dd-apm/linux-ssi` `agent-install`). Use when the user wants to monitor Linux servers, install the Datadog Agent on an Ubuntu or other Linux host, or roll the Agent out to an EC2 or other cloud VM fleet without SSH. Does not install the Agent on Windows, macOS, Docker, or Kubernetes (use dd-agent-install-windows, dd-agent-install-macos, dd-agent-install-docker, or dd-agent-install-kubernetes) and does not connect a cloud provider integration. Requires a Datadog account with a valid API key and application key; run `dd-account-setup` first if they are missing.
Set up Datadog Cloud Cost Management for AWS by configuring a Cost and Usage Report - either CUR 2.0 (recommended) or a Legacy CUR - and provisioning the S3 bucket, bucket policy, IAM read policy, role attachment, and Datadog registration with Terraform. Use when the user wants to track their AWS cloud costs, set up cost and usage reports, set up Cloud Cost Management (CCM) for AWS, set up CCM with CUR 2.0, or connect an AWS Data Export to Datadog. Does not connect a new AWS account to Datadog and does not set up cost management for other clouds. Requires an existing role-based Datadog AWS integration; run `dd-aws-integration` first if it is missing.
Set up AWS log forwarding to Datadog with Terraform: deploys the Datadog Forwarder Lambda in the user's AWS account, seeds the Datadog API key into a Secrets Manager secret out-of-band so it never lands in Terraform state, and registers the forwarder ARN on the existing AWS integration so Datadog automatically subscribes CloudWatch log groups and S3 buckets. Use when the user wants to forward AWS logs to Datadog, send CloudWatch logs to Datadog, or set up the Datadog Forwarder Lambda. Does not create the AWS integration itself or set up metrics collection. Requires the Datadog AWS integration (datadog_integration_aws_account); run `dd-aws-integration` first if it is missing.
Set up Datadog Cloud Cost Management for Azure with Terraform. Provisions (or reuses) a Storage Account and Container, creates actual-cost and amortized-cost Cost Management exports, grants the existing Datadog app registration read access through role assignments, and registers the exports with Datadog through datadog_azure_uc_config in a two-phase apply around the manual file-partitioning step. Use when the user wants to track Azure cloud costs, set up Azure cost exports for Datadog, or set up Cloud Cost Management for Azure. Does not create the Azure integration or its app registration/service principal. Requires an existing Datadog Azure integration; run `dd-azure-integration` first if it is missing.
Set up automated Azure log forwarding to Datadog by running Datadog's official Log Forwarding Orchestrator (LFO) install script through the Azure CLI - deploys the managed control plane that auto-discovers resources across the monitored subscriptions and provisions and scales the log forwarders itself, with no per-resource diagnostic settings. Use when the user wants to forward Azure logs to Datadog, send Azure resource logs to Datadog, or set up Azure log forwarding. Does not generate Terraform and does not create the Azure integration or set up metrics collection. Requires the Datadog Azure integration; run `dd-azure-integration` first if it is missing.
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.