Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
All
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.
Framework-independent decision process for instrumenting a GenAI/LLM app (Python or TypeScript, any provider/agent SDK) so it emits OTel GenAI semantic-convention (gen_ai.*) spans queryable in Dynatrace. Four steps: detect, instrument, enrich, validate. Decides which approach a given SDK needs; does not replace the concrete per-framework recipes in dynatrace-oss/dynatrace-ai-agent-instrumentation-examples. Trigger: "instrument this GenAI app", "add tracing to this LLM app", "how do I get gen_ai spans into Dynatrace", "onboard this agent app to AI Observability". Do NOT use for analyzing telemetry from an already-instrumented app (use dt-obs-genai) or for languages other than Python/TypeScript
Migrate a GenAI/LLM app off Traceloop/OpenLLMetry onto OpenInference with its OTel gen_ai.* semconv option enabled (`enable_genai_semconv` / `OPENINFERENCE_ENABLE_GENAI_SEMCONV`). Covers detecting the existing Traceloop setup, swapping the instrumentor per SDK, and the ingestion-shape question that decides what's fixable afterward — an app-owned OTel trace exporter vs. instrumentation-only with OneAgent picking up the spans. Flags that the semconv option is additive, not a replacement — legacy llm.*/openinference.* attributes keep emitting alongside gen_ai.* — and covers the resulting cardinality trade-off and removal options (Collector transform vs. OpenPipeline), checking which is actually available first. Trigger: "migrate off Traceloop", "migrate off OpenLLMetry", "move to OpenInference", "enable OpenInference GenAI semconv". Do NOT use for a first instrumentation with no existing Traceloop setup, or an OpenInference app that never enables semconv (both dt-setup-genai).
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).
Close out acceptance testing. Finds the open docs/acceptances/ATTENTION.<feature>.md candidate files that start-acceptance left, compares each candidate with docs/acceptances/ATTENTION.md, and for every one not already there asks the user, one at a time, whether it is systematic and settles the exact wording with them before it is moved; then retires the feature file. Runs the project's full test suite, lint and typecheck once first, since the acceptance session skipped them. Use when the user says acceptance is finished, asks to promote or review the acceptance lessons, or invokes /end-acceptance [feature]. Never promotes a lesson in its own wording.
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".
Use when a human wants to create, hire, activate, or set up a new AI employee from a plain-English description, e.g. wanting something that writes a weekly recap or replies to guest messages. Drives the Hiring Dozal's multi-turn setup wizard (the hiring chat), relays its button questions (show me first or just send it) to the human, and hires the finished Dozal. Use it for any new-employee request. Load operate-ai-employees first for auth and base-URL setup.
Use when a human wants to see, list, pause, reactivate, rename or inspect their existing AI employees (config, status active/paused/draft), or manage connected apps, schedules, handoffs, members and invitations, usage and bills, e.g. what employees do I have, pause the recap bot, how did last Friday go. Not for running one now (run-ai-employee), a task's output, approval or logs (monitor-and-review-ai-employee-work), or creating one (hire-ai-employee). Load operate-ai-employees first.
Merge a branch of Windows-first (and Android) work into the mac branch, making sure every change translates to macOS or is written down as not yet doing so. Use when the user asks to merge into mac, merge the mac branch, catch mac up, or bring Windows work over to mac. Follows merge-branch's review gate in full, then adds a mac-translation pass whose verdict for each change — translated, needs mac work, or deferred — is recorded in the project's platform catch-up tracker (CATCHUP.md unless the project keeps it elsewhere), so no Windows behaviour goes silently missing on a Mac.
Use when a human asks whether an AI employee task is done, wants to see its output, or wants to approve or reject its work: is the recap ready, show me what it wrote, approve it, reject and shorten it, why did that run go wrong, show its logs, watch it live. Reads task status via phase_category, drives the approve/reject decision, and reads run logs, activity and live status. Load operate-ai-employees first for auth setup.
Use when a human asks you to operate their AI Employee platform account: hiring an employee, running one, checking on a task, approving or rejecting work, listing or pausing employees, or managing connections, schedules, handoffs, members, usage, bills, activity and run logs. Load this first to route between the four job skills. The umbrella skill: dze_ API key auth and its level, the production base URL, tenant resolution, the async model, and person-only steps.
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.
Reviews PostHog's warehouse suggestions with a person and acts on them. Explains why a view should be materialized, unmaterialized, certified or deprecated using the numbers in the suggestion, changes a materialize suggestion's refresh mode, keys or interval when the person wants something else, then accepts or dismisses it. Use when the user asks what PostHog suggests for their data warehouse, whether to materialize a view, why a view should refresh incrementally or every few hours, or wants to accept, change or dismiss a warehouse suggestion.
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.
Use when a human wants to run, trigger, start, or test-run an existing AI employee, e.g. run the recap bot now, kick off the guest responder, or run it once per topic from a list of inputs. Triggers the employee, can dry-run to list required inputs, and hands back task handles without blocking. Load operate-ai-employees first for auth; use monitor-and-review-ai-employee-work to check the result.
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".
Open a pull-request review session — you are the reviewer, not the author. Asks for the spec the change was written from, reads the project's principles and best practices, then reviews the diff for unnecessary complexity, smelly code and drift from the spec, reporting findings first and recording what the user decides on the PR itself. Hands over to start-acceptance once the findings are settled. Use when the user says they are starting a PR review, asks to review a pull request or a branch someone else wrote, or invokes /start-pr-review <pr or branch>.
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 release descriptor and notes for the next release on a channel (stable, beta, nightly, or whatever the project names), following the project's own release-writing instructions. Use when the user asks for release notes, a changelog entry, a release descriptor, or “the next nightly / beta / stable.” Gathers what is published now and what this tree holds, lets the project's instructions choose the version and format, writes the file, and never publishes.
Bans the 43 tells of a vibecoded website (purple gradient on black, indigo Tailwind buttons, bento grid, liquid glass, sparkles icon, fake counters, "Most popular" pricing, the "Create Next App" tab, no legal pages...) while Claude builds or reviews a site, so it looks made by a human. Use when building, redesigning or reviewing a website, landing page or web app UI, or when the user types /anti-vibecode, "vibecodé", "ça fait IA", "looks AI generated".
Make videos in pure code (mp4, 16:9 and 9:16): narrated explainers with captions and music, and promo / launch videos for websites, apps and software with beat-synced music and sound effects. The user picks only the style: whiteboard, risograph, ink-wash (水墨), launch motion, origami, pop art, op art, Matisse cut-outs, ASCII art, shadow puppets (皮影戏), Bauhaus, pixel art, chat log, toy 3D, old newsreel, film-room breakdown, suspense mystery, isometric miniature world, movie trailer, news clippings, manga (日漫), animated map. Use for science / concept explainers, problem walkthroughs, vocabulary, history, places and maps, how-tos, news / data, and product promos from a URL. Use when the user asks for an "explainer video", "whiteboard animation", "a promo / launch video for this website / app", or in Chinese "做个科普视频" "把这道题做成讲解视频" "白板动画" "讲个历史故事的视频" "给这个网站 / App 做个宣传片" "产品发布视频", or names one of the styles (孔版印刷, 水墨, 折纸, 波普, 欧普, 剪纸, 字符画, 皮影戏, 包豪斯, 像素, 聊天记录, 玩具三维, 老新闻片, 录像分析, 悬疑探秘, 等距微缩世界, 电影预告片, 剪报解说, 日漫, 地图动画).
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.
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.
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 work arrives at the software factory at any lifecycle stage — a new request, an informational question, a CI failure on a delivered PR, review findings, a merge notification, or a reply to a factory question — and must be routed to the right factory skill, human gate, or follow-up context.
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.
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.
Build NHCX (India's National Health Claims Exchange) payment notices into an existing HMIS: receiving the payer's payment notice and reconciliation breakdown, matching it to the claim, and acknowledging it, with the embedded NHCX gateway it needs. Use when a hospital system must record insurer or PMJAY payments arriving over NHCX.
Build NHCX (India's National Health Claims Exchange) claim reprocess and balance release into an existing HMIS: asking the payer to look again at a decided claim, asking for the unpaid balance of a partly paid claim, and applying the payer's answers, with the embedded NHCX gateway it needs. Use when a hospital system must contest a claim decision or recover a withheld balance over NHCX.
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.
Audit the skill inventory for quality, coverage, and staleness. Detect overlapping, incomplete, or outdated skills and produce a health report. Activate when: skill audit, stocktake, skill inventory, check skills, which skills exist, audit skills, skill quality, skill coverage.
Connects and operates the Visant Labs MCP (requires a Visant Labs account): brand guidelines, mockups, creative studio, canvas, budgets, moodboard, PDF extraction. Use on "connect visant", "use the visant tools", "setup visant mcp", "conecta o visant", "usar as tools do visant", "extrair PDF pelo visant".
Visant's official brand-building methodology: 9 stages in 3 phases and the dependency cascade between them. Use to generate or audit a full branding, or to write the prompt for one stage. Use on "Visant methodology", "full branding", "audit branding", "metodologia Visant", "branding completo", "auditar branding".
Preflight for a large client project: one question round with whoever owns the work, plus five premise checks (brand source of truth, loadable fonts, photo resolution, brand files, sourced numbers). Use BEFORE "new site", "redesign", "new proposal", "criar site", "redesenhar", "nova proposta", "montar campanha", "hidratar a marca".
Assembles a rough cut in Premiere Pro via premiere-pro-mcp from a JSON cut plan: frame-exact cuts, markers, punch-ins, cards, b-roll, -14 LUFS delivery. Use on “build it in Premiere”, “Premiere rough cut”, “punch-in”, “cover with b-roll”, “monta no Premiere”, “marcadores pra narrar”, “exporta as aulas”, /visant-premiere-editor.
Edits vlogs, event videos and video lessons from raw footage: breakdown, silence cuts that never clip a word, loudness and chapters, with a self-test against silent failures. Use on “edit this vlog”, “cut the silence”, “edit this lesson”, “monta um vlog”, “decupagem”, “edita essa aula”, “tira o silêncio do vídeo”, /visant-video-editor.
Build a website with someone without prior knowledge in eight fixed steps: mockup, design (two or three options based on characteristics), framework, PRD for approval, build and show locally, send to the harbor and show it there in a browser, assembly line, site or server. Open the island in Cockpit and report each step with schritt_melden. Use this skill whenever a website is being built: after webseite-planen, after the inventory in webseite-modernisieren, or for “build me the site”, “mockup”, “draft”, “PRD”, “view locally”, or “what happens after the plan”.
Help a person with no prior knowledge decide whether their website needs a content management system (CMS), and set it up if needed, for example Strapi in Docker on the Albatros server, accessible through a secure tunnel. Explain CMS using the image of a bulletin board. Use this skill for “CMS,” “Strapi,” “change content myself without code,” “blog,” “news,” “manage events,” “my colleague should be able to edit text,” “WordPress,” and “admin area.”
Work step by step with a person who has no prior knowledge and their AI to improve a small website's usability and appearance. First review it from three perspectives (flows, access, states, and language), then fix usability, offer three clearly different directions to choose from, set fixed values for colors, typography, and spacing (tokens), and rebuild all pages with photos at mobile and desktop widths. Use this skill for “design,” “looks boring,” “looks homemade,” “make it prettier,” “colors,” “font,” “redesign,” “three options,” “looks unprofessional,” and “layout.”
Help the person create an honest budget for their project: Albatros subscription, domain, AI subscription, email, add-on services, and later a server of their own. Explain which costs are fixed and which are variable, how to avoid unpleasant surprises, and when moving is worthwhile. Use this skill for “what does this cost,” “costs,” “prices,” “too expensive,” “budget,” “bill,” “is it worth it,” “how much does a server cost,” and before the person adds a new paid service.
Review the diff since a fixed point along Standards and Spec axes in parallel sub-agents, reporting findings without editing the target or deciding the final verdict. Use when the user wants to review a branch, PR, or work-in-progress diff, or when review-loop or project-review requests a specialist software check
Execute one bounded, already-decided work item — code, document, configuration, research artifact, Skill, or generic project task — by inspecting relevant context, offering agent-config routing when materially useful, verifying locally, and handing the result to review-loop with the appropriate specialist reviewer
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent. Light Skills version of mattpocock/skills `research`; install one or the other, not both
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.