Skills
100,344 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Set up the Datadog Confluent Cloud integration: create a Cloud resource management API key in Confluent Cloud (with the Confluent CLI or the console), register the account with Datadog, discover and register its Kafka clusters, connectors, ksqlDB and Schema Registry resources, and optionally add Schema Registry tags and Cloud Cost Management. Use when the user wants to monitor Confluent Cloud Kafka clusters, set up the Datadog Confluent Cloud integration, connect Confluent Cloud to Datadog, see Confluent metrics in Datadog, or monitor Kafka clusters on Confluent. Does not set up self-managed Kafka or the Datadog Agent. Requires a Datadog API key and application key; run `dd-account-setup` first if they are missing.
Set up Datadog Cloud Cost Management for Oracle Cloud Infrastructure (OCI) by enabling cost collection on an integrated parent tenancy—an API toggle on the existing tenancy integration, with no Terraform, storage buckets, exports, or extra IAM policies. Use when the user wants to track their OCI cloud costs or asks to set up Cloud Cost Management for OCI. Does not create the OCI tenancy integration itself or provision any infrastructure. Requires an existing Datadog OCI integration; run `dd-oci-integration` first if it is missing.
Deliver a change end to end by orchestrating agent profiles - grill, plan, test-first implementation, review, QA, then merge or open a PR. Use when the user's message starts with “deliver” or names `deliver` (or `flyingnobita-deliver`), whatever the size of the work.
Check delivery prerequisites and offer fixes, configure delivery profiles and project defaults, validate a delivery host, migrate legacy Orca orchestration settings to `deliver` (or `flyingnobita-deliver`), or move Herdr top-level role tables under [hosts.herdr.roles.<role>].
Scaffold a directions lab that shows shipped UI (Today) beside 2-3 design directions, with surface tabs, theme and animation toggles and the V1 MVP hover motion, registered in design-proposals Storybook. Use for a directions page or lab, or to explore design directions next to production.
Models currency income per stage (kills times enemy rewards, expected sell value of drops, other income) and an ordered purchase plan whose prices come from item prices, expected enhancement costs, crafting costs, permanent upgrade costs, or fixed amounts, then computes when each purchase becomes affordable within a run, which run a carried meta currency affords it, and how much currency is left over. Use when tuning rewards, prices, shop or upgrade pacing, or checking for currency piling up or running short, in any genre and engine.
Look up MCU peripheral registers, bit fields, reset values, and addresses (based on CMSIS SVD), with sources and evidence labels for every finding. Supports address reverse lookup; register value decoding and write-value calculation; bit-field quick reference and bitmaps; interrupt number and NVIC enable hints; CMSIS-style macro generation; cross-chip and peripheral-level comparisons; address range queries; SVD quality checks; local chip inventory and environment checks; Markdown table output; and parsed-result caching. Use when the user asks about a register, bit field, reset value, peripheral base address, or interrupt number; wants to decode or compute a register value to write, generate register macros, compare register definitions across devices, or find or verify SVD files on the machine. Keywords: 寄存器、位域、复位值、SVD、外设地址、寄存器值、掩码、位图、中断号、IRQn、NVIC、宏定义、对比、整体对比、质量检查、SVD 位置、芯片清单、读改写、USART1->CR1、register、bitfield、mask、reset value、decode、interrupt. Not for: pin multiplexing, manual chapter search, errata lookup, or verifying register writes in code (use embedded-register-verify).
Use when the user asks to fix, patch or upgrade a PHP vulnerability (e.g. 'Please fix my PHP vulnerability'), PHP2Shell, CVE-2026-109618 or CVE-2026-109619, or to find vulnerable PHP versions in Dockerfiles, distro packages, source builds, setup-php CI, Helm/IaC or Ansible/Chef/Puppet. Read-only inventory, approval gate, regression tests, focused PRs.
Align the current project's PRODUCT.md, DESIGN.md, GLOSSARY.md, and ARCHITECTURE.md after meaningful changes, and write the project Flow block on request. Use when the user says "update the docs", "sync the context", "keep the docs aligned", or "set up Flow here".
Set up a headless Mac (Apple silicon), Linux or Windows machine over SSH, step by step, from "an admin account with a password and SSH on" to a configured machine with key-only SSH, automatic sign-in, never-sleep settings and optional Tailscale - on a Mac with Determinate Nix and nix-darwin, on Linux with a NixOS module (installing NixOS with nixos-anywhere if the user wants) or a distro-neutral script for Debian, Ubuntu and Fedora, on Windows 11 or Windows Server with a rerunnable PowerShell configuration - then restart it and confirm it comes back. Use when the user wants to set up, configure, update or check a headless Mac mini, Linux server, Windows PC or other machine they reach only over SSH. The admin password stays in the user's secret store (Automic Vault, 1Password, Bitwarden, any command, or a private env file); you only ever name the store entry.
Build from a written issue or task, collaborating with the user: read the issue and related open work, ground it in the code, clarify requirements and design with the user, then implement after they confirm the plan. Use when the user says let's build, build together, or asks to build from an issue or task description.
Make a narrated, captioned faceless short video (AI images and AI voice) on the user's own AutoShort or StoryShort account. Works with either MCP server, detects which one is connected, agrees the script with the user, shows the credit price the server returns and renders only after an explicit yes, then polls the render and returns the video link. Use when the user wants to make, draft, render or publish a short video, YouTube Short, TikTok or Reel.
Use when the user asks to triage issues or a backlog, sort open issues into what to do now, next or later, find duplicates, decide what goes in the next batch, or label and comment on open issues after reading them, even if they do not name this skill. Reads every open issue in full, classifies each (bug with or without a reproduction, feature, chore, duplicate, not actionable) with evidence, requires a duplicate search before recommending anything for now, routes items to mstack-write-specs or mstack-diagnose when they need it, and outputs a table the mstack review workflows accept. Drafts comments and label changes but posts nothing without approval of the exact text. Works in Claude Code and Codex. It does not write specs or code.
Use when the user is running out of context or tokens, wants to pause, wants to hand long-running work to another agent, session or host, or says "write a handoff", "hand this off", "save where we are" or "continue from this handoff". Writes one resumable handoff file (branch, HEAD, uncommitted paths, pull request, issue status, gates green and due with exact commands, approved and blocked decisions, next commands first) without committing, stashing or leaking secrets, verifies it, and stops; or resumes from such a file. Works in Claude Code and Codex. It does not continue the work itself.
Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", "orca artifacts", "share HTML/Markdown", "public artifact link", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Orca's embedded browser.
Plan a multi-episode faceless short video series on the user's AutoShort or StoryShort account before anything is produced. On AutoShort, design the season, save the season plan, run the review, get the user's explicit confirmation, then quote and make one episode at a time. On StoryShort, agree the plan in chat, create the series paused, and resume it only after the user approves the cost. Use when the user wants a series, a season, a short drama, recurring characters or a scheduled channel.
Rebuild a web page, section, component or interaction from a reference (a live URL, a local HTML file, a screenshot or design export, or a screen recording or GIF) inside the user's own codebase. Then measure the rebuild against the reference (element boxes, computed styles, pixels, motion timing and easing) and iterate until a numeric Replica Score passes. Use when the user wants to clone, replicate, recreate, copy, port or match a site, landing page, hero, navbar, pricing table, card, modal, footer, hover effect, scroll reveal, page-load animation or any other UI, or to "make it look/feel/move like" one. Also use when they say "pixel-perfect", "1:1", "exactly like this" or "same as <url>", or hand over a screenshot, Figma export or video and ask to build it, including when they want their own copy, brand or extra features on top
Find short-video formats worth testing before making a video. Read the user's own post performance from their AutoShort or StoryShort account, browse the available niches and templates, study reference Shorts the user names, and turn the findings into format cards and a small test plan. Use when the user asks what to make next, which format or hook style to try, or how to learn from videos that did well.
Reviews a git diff through reviewer subagents on each lens (big picture, detail), then checks and triages the findings and fixes clear problems. Use when the user asks for a code review, PR review, sanity check on changes, or reviews with specific or multiple models.
Find where an agent pipeline can swap frontier models for cheaper ones without losing quality. Drive the installed rightmodeler TypeScript CLI through its resumable pipeline, interpret its machine protocol, present per-family verdicts, and open a reviewed model-swap pull request when the evidence supports one. Use when the user wants to cut model spend, right-size models per task, benchmark cheaper model substitutions, or analyze an agentic pipeline for cost optimization.
Initialize a new project from flow-next or flow-mono with verified setup, renamed identity, and an independent initial Git commit, while explore shapes the product. Use when the user says "start a Next.js project", "start a new project", or "start a monorepo".
Sets stat budget curves per tier, zone, or level with per-stat costs and multipliers (rank, rarity, slot), checks every item and enemy against its expected budget, drafts new items and enemies from archetypes that split the budget across stats, and suggests stat costs from the combat formula. Use when designing tier or zone progression, adding items or enemies so they fit a curve, finding over- or under-budget entries, or deciding how much one stat point is worth, in any genre and engine.
Sync a repository's documentation with what its code actually says: versions, dependencies, commands, project structure and feature claims in README.md, CLAUDE.md, AGENTS.md and docs/, each verified against the manifest, lockfile, scripts and files before it is written, with human prose, tone and section order left as they are. Use when: (1) a dependency, framework or runtime version changed and the docs still name the old one, (2) scripts, Makefile targets or the directory layout changed, (3) a feature was added, renamed or removed and the docs may no longer match, (4) an agent instruction file tells agents to run a command that may not exist, (5) the user mentions: sync docs, update the README, docs are stale, docs out of date, outdated version in README, fix CLAUDE.md, AGENTS.md, package.json, lockfile, pyproject.toml, Cargo.toml, go.mod, "npm run lint" missing script, "docs: sync documentation with codebase state". Carries the ground-truth table per ecosystem, the rule for declared range against resolved version, the flag-don't-guess rule for unverifiable feature claims, and a three-part report of changed, verified and flagged. Works on any project type, Node, Rust, Python, Go or a repository with no manifest at all; the repository's own manifests and files are the seam. Not a changelog or version bump tool, not a doc writer for missing files, and not an audit of the code against the docs
Write the AI SEO Tracker report brief from live MCP data. Use when the user wants a TL;DR of AI search visibility, a weekly recap, or the same brief as the in-app Report page. Trigger on "tldr the report", "AI SEO brief", "why am I missing in ChatGPT", or fetch https://aiseotracker.com/ai-seo-report/SKILL.md.
AI SEO Tracker setup skill. Use when the user wants AI search visibility, ChatGPT or Perplexity rankings, citation tracking, or MCP connection help. Trigger on "track AI mentions", "AI SEO", "how does ChatGPT rank us", or when the user asks you to fetch or run https://aiseotracker.com/SKILL.md. Fetch this file before quoting tools, pricing, or workflow from memory.
Astryx, a design system and UI library, is available on this computer through the astryx command; use it when building or changing UI, choosing components, layout, styling or theming, working with a design system, or in any project that depends on @astryxdesign packages or mentions Astryx.
Feed what a finished cycle taught back through the sources that produced it: measure the lesson, question the requirements it touches, land it in one owner, refresh that owner to a clean v0, cut its padding and realign its listings, each pass only when it applies. Use after a correction, a request the user had to repeat, a failed or disappointing cycle, or a cleanup pass over a repository's docs, rules or skills, when the lesson has to change the sources rather than sit in a memo.
100 questions about Binance Agentic Wallet. Uses Chinese Q&A to guide an agent in understanding Binance on-chain wallets, choosing official baw routes, checking transaction approvals and risk boundaries, and designing constrained automation extensions. Covers meme coin risks and honeypot detection, rug pull prevention, and verifying smart-money signals. For product questions, troubleshooting, trading strategy constraints, meme coin risk control, and wallet workflows; does not replace the official wallet skill and is not for placing Binance exchange futures orders.
Runs a local (LAN) and instant public host (Zero-Config Tunneling via Cloudflare/Localtunnel) for simultaneous multiplayer educational quizzes and board games in a classroom, without router configuration or a paid domain. Includes an automatic gradebook (real-time grade ledger), instant QR Codes for student smartphones, and export of grade summaries to Excel/JSON.
Plan and write blog posts that cover missing AI search prompts from live MCP data. Use when the user wants content for ChatGPT gaps, citation listicles, competitor sources, or a content campaign from AI SEO Tracker. Trigger on "write posts for missing prompts", "content coverage", "what should we publish", or fetch https://aiseotracker.com/content-coverage/SKILL.md.
When every option on the table is a variation of one route or waits on the same sign-in, approval, person or dependency, list the options that frame already gives, then map working mechanisms from five or more distant domains onto the problem and report the ones the first list lacked, each with where it breaks. Use when work is stuck inside one frame, when the user asks how another field or industry would solve it, or asks for an analogy that actually transfers. Not for re-reading a decision at a larger scale (macrothink), listing options when no single frame is stuck, or checking claims (factchk).
Find one person's or one organization's data leaked into a shared repository, folder or artifact, using needles built from that owner's own records (names in every script, handles, emails, phone numbers, addresses, account and client ids), replace each hit with a role or placeholder that keeps the artifact working, and scan git history read-only for the commits that still carry them. Use when a public or shared repository, a template, a fixture set, docs or a deliverable may hold an operator's, a client's or a teammate's personal or business data, when someone asks to de-identify, anonymize, scrub or depersonalize an artifact, before publishing or open-sourcing a repository, or when a person's data must leave a codebase every operator runs.
Assess, set up, and verify how an AI development environment uses an organization's actual design system. Use when someone wants to keep AI on their system's rails, connect system knowledge and tools to coding agents, establish reuse and gap policies, or check whether those guardrails work. Focuses on the workflow and its evidence; ordinary page building or a full system inspection alone does not require this skill.
This skill should be used when the user is building electrobun features for the milady-ai/milady project, submitting PRs to milady that will be reviewed by the agent-review system, asks about "electrobun milady", "milady electrobun PR", trust tiers, Biome compliance, or the release-electrobun.yml workflow.
Researches evidence unavailable locally: external documentation, public repositories at specific refs, archives, and published dependency artifacts (JARs, source JARs, POMs, dependency graphs), reusing a persistent cache of Git clones and Maven artifacts. Use for library docs, upstream source and history, dependency source or metadata, or any question needing external evidence
Use when an approved PR head must reach production through a gated release — exact-head merge, staged canary rollout with threshold verdicts, a SemVer-tagged release with notes, milestone close and roadmap update, plus a monitor handoff. Triggers on post-merge rollout work; not for continuous monitoring, review depth, or infra provisioning.
Use when the user asks to fix, patch or upgrade a self-managed GitLab vulnerability (e.g. 'Please fix my GitLab vulnerability'), CVE-2026-110264 or the GitLab 19.5.1 critical patch release, across Omnibus, Docker, Helm chart and IaC deployments. Read-only inventory, approval gate, post-deploy checklist, focused PRs.
Humanize prose or draft it from supplied facts when explicitly asked to "humanize", "de-AI", "remove AI-sounding language", or write in a human voice. Simplify by cutting filler, stale content, and needless complexity. Confirm scope each run and offer four voice presets.
Split anime or hand-drawn character art into the standard 19 component layers for 2.5D animation. First use ImageGen to create component reference images, then combine artwork segmentation and local shape completion to produce a layered PSD with independent masks. After the first draft, review each layer and fix layer bleed, gaps, and occlusion-related shape completion; use ImageGen for local repainting if needed. Use for character layer separation, character illustration splitting, See-through-style layering, converting SVG to a layered PSD, or processing a new image to the same standard as the previous character.
Lays out each level as an ordered list of encounters (rooms, waves, packs, time spans), scores every encounter's threat from the same enemy stats used by combat and stat budgets, compares it with a threat budget curve per stage and role, shows single-target kill time against stage length, and cross-checks placed enemies against combat stages and kill counts against the economy. Also lays out pacing: enemy-less stretches, encounter times against economy stage lengths and purchases, accumulated load between rest points and rewards, and runs of strong encounters. Use when composing levels, waves or rooms, sizing encounters, placing rests and rewards, or checking that a level agrees with combat and economy assumptions, in any genre and engine.
Use when the user asks about MLX serving, mlx_lm.server, oMLX, Apple Silicon LLM serving, or running a local LLM on a Mac, and when troubleshooting a model that fails to load, OOM during load or inference, a server that hangs or crashes at batch>1, tool calls returned as plaintext content, a throughput regression, or the choice between mlx-lm and oMLX. Also covers oMLX feature-flag tuning (turboquant_kv, dflash, MTP, specprefill, thinking_budget, max-concurrent-requests, force_sampling), the OptiQ proxy for models exceeding RAM, Llama-4 ChunkedKVCache batch handling, Llama-3 tool-call JSON format, and bench-driven validation of serving configs. Apple Silicon M-series only, not cloud LLM hosting, non-MLX backends such as llama.cpp, Ollama and vLLM, or model training.
Richtet alles ein, um mit Claude Code (oder Codex) Motion-Graphics-Videos per Code zu bauen, und hilft danach, einen guten Video-Prompt zu schreiben. Fragt, ob HyperFrames, Remotion, Tesseract oder nichts installiert werden soll, verbindet auf Wunsch Higgsfield für Bilder, Videos, Stimmen und Musik und führt dann durch ein kurzes Interview (Länge, Format, Ziel, Branding, Referenz, Erfolgskriterium). Nutze diesen Skill, sobald jemand „Motion Fabrik“ sagt, den Link zu diesem Repo schickt, mit Claude Videos, Erklärvideos, Werbespots, Shorts oder Motion Graphics machen will oder HyperFrames, Remotion, Tesseract oder Higgsfield einrichten möchte. Also use it in English when someone wants to set up AI video creation with code.
Use when the user asks which model or effort to use for a task, for Claude or Codex, such as “which model for this subagent”, “what effort should the review run at”, “is haiku enough for this”, “best Codex model for debugging”, or when another mstack skill needs a model and effort for a tier (cheap, standard, most capable) or a task before it starts a subagent, a lane or a reviewer. Works in Claude Code and Codex. Returns a model, an effort, how to set both, a reason and a next step, per vendor.
Use when the user asks “is there a skill for this”, “find me a skill for X”, “which skills help with this task”, “search skills.sh”, or wants to install a skill for a job, or when another mstack skill needs the installed skills that fit its tasks or work items (a plan's phases, a workflow's lanes, a skill being created). Works in Claude Code and Codex. Returns the matching installed skills per item with a reason, and vetted public candidates from skills.sh for the gaps.
Use when the user wants to set up, install or check what the mstack skills need, such as “set up mstack”, “install the dependencies”, “what is missing for mstack”, “install codegraph”, “my workflow stopped at its preflight”, on a new machine, or when another mstack skill stopped and named mstack-setup. Works in Claude Code and Codex, on Linux, macOS and Windows. Reports each dependency's state and installs the missing ones at user scope after one confirmation.
Build NHCX (India's National Health Claims Exchange) payer communication into an existing HMIS: receiving payer queries, notifications and notes on a pre-authorisation or claim, replying with text and documents, and acknowledging notifications, with the embedded NHCX gateway it needs. Use when a hospital system must answer insurer or PMJAY queries over NHCX.
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.