Agent Skills Directory

Plans and scripts short-form and long-form video, and designs the packaging — titles, thumbnails, and openings — that determines whether it gets watched. Use this to script a video, plan a series, fix retention or click-through problems, design thumbnail and title concepts, or turn written content into video. For a YouTube channel specifically — idea selection, retention teardowns, and channel-level strategy — use `youtube-producer`.

Runs the hypervisor layer beneath the servers — host capacity and consolidation ratios, VM sprawl, snapshot discipline, resilience and live migration, and licensing that counts cores rather than instances. Use this to size or expand a cluster, work out why VMs are slow when the hosts look idle, clean up sprawl, set snapshot and template policy, or decide what stays virtualized and what moves to cloud.

Designs and directs the visual assets that carry content — carousels, infographics, quote graphics, diagrams, and social imagery — including the generation prompts where they are AI-produced. Use this to turn a written piece into a visual format, design a carousel or infographic, create social graphics, or fix visuals that are not stopping the scroll.

Produces design reference imagery before implementation — screen concepts, layout directions, and flows for web or mobile that make a verbal brief concrete enough to argue with. Use this when a brief needs visualizing before anyone builds, when comparing layout directions, when handing a developer a target, or when stakeholders are describing different things with the same words.

Builds the loop from what customers say to what gets changed — collecting feedback, distinguishing signal from noise, routing it to owners, and closing the loop back to the customer. Use this to set up a feedback program, design or interpret CSAT/NPS, decide what customer feedback deserves action, get product to act on recurring issues, or diagnose why feedback is collected but nothing changes.

Plans the shape and size of the workforce — demand for roles, build-versus-buy, attrition, and sequencing hiring against budget. Use this to build a hiring plan, decide which roles to open and in what order, model attrition and backfill, plan for a growth or contraction scenario, or connect headcount plans to the budget.

Plans, packages, and scripts long-form video for retention and channel growth — idea selection, titles and thumbnails, script structure, and diagnosing why a video or channel underperforms. Use this for video ideas, packaging, scripting, a retention teardown, or channel strategy — including when someone describes a topic and wants it turned into something publishable. For short-form and cross-platform video, use `video-content`.

Builds robust Python MCP (Model Context Protocol) servers with FastMCP — tool design, error contracts, event-loop-safe blocking work, subprocess/CLI wrapping, single-file vs packaged distribution, global-state-free testing, and prompt-injection awareness. Use when writing an MCP server, exposing a tool or CLI to an LLM client, debugging tool registration/packaging, or testing MCP tools.

Generate GitHub Actions CI/CD pipeline configurations for automated building and testing of library and package projects. Use when creating or updating CI workflows for npm packages, Python packages, Go modules, Rust crates, or other library projects that need automated build and test pipelines. Includes templates for common package ecosystems with best practices for dependency caching, matrix testing, and artifact publishing.

Resolve conflicts and merges when several branches are open against one repo at the same time — the hotspot files every change must touch (registry manifests, a single version field, shared tool config, one aggregated test module, tracked build output), union-vs-recompute-vs-rebuild as three different correct resolutions, generated artifacts that must never be merged, non-deterministic serialization that makes every branch conflict, renumbered identifiers that git cannot show you, and why a clean auto-merge is not a passing test. Use when rebasing or merging a long-lived branch, resolving conflict markers, reviewing a merge commit, deciding what a repo should commit vs generate, or setting up a repo that will take parallel contributions.

Edit video and audio with local FFmpeg from natural-language requests: cut, trim, join, resize/reframe (9:16, 1:1), speed change, captions and subtitles (SRT/ASS, animated, karaoke), logos and text overlays, lower-thirds and titles, silence removal, multicam and external-mic sync, loudness normalisation, HDR/Dolby Vision to SDR, LUTs, background music with ducking, platform exports (YouTube, Reels, TikTok, X), compliance checks, scene detection and highlight reels, contact sheets to inspect results, and whole-edit project files. Use this skill whenever the user mentions a video or audio file (mp4, mov, mkv, wav, m4a), footage, a clip, captions, subtitles, a reel or short, YouTube/Instagram/TikTok delivery, LUFS, sync, transcoding, ffmpeg, or asks to make something "60 seconds", "vertical", "louder", "captioned" — even when they do not say "edit". Python 3.9 standard library only, no cloud, no API keys.

Add and review preconditions on operations that delete, overwrite, rewrite history, or resolve a caller-supplied name to a filesystem path — refusing instead of warning, placing the guard ahead of the first mutation, structural classification rather than string-prefix matching, name validation plus resolved-path containment as two independent checks, why a guard on the destructive path is invisible to the dry-run, and mutation-testing each half separately. Use when writing or reviewing a `--rebuild`/`--reset`/`--purge` command, a bulk delete, a history rewrite, an `rm -rf`-shaped step, or any code that turns an argument into a file path.

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.

Manages Python library releases including semantic versioning, changelog maintenance (Keep a Changelog format), release automation with GitHub Actions, and deprecation workflows. Use when planning releases, writing changelogs, automating release pipelines, or communicating breaking changes.

Run the CI gate on your machine so it agrees with the runner — deriving the exact command, paths, markers, and env from the workflow file instead of the Makefile, unblocking gate steps that short-circuit and hide the next failure, pinning the linter version CI resolves, building the interpreter/toolchain environment the runner builds, and confirming the run is green instead of explaining a red job away. Use when a check passes locally but fails in CI (or the reverse), when a lint/format job goes red on an untouched file, when setting up a local dev loop for an unfamiliar repo, or before pushing a branch you expect to merge.

Review a change to the ffmpeg-skill repository for the failures its own contract makes possible — a claim in a result document that is true at one layer and false at the layer a caller reads, a new flag that reaches the code but not the contract/docs/demo surfaces, a "bug" that docs/design-decisions.md already decided with a pinning test, a fix with no regression test, a new runtime dependency or a raw ffmpeg shell call that breaks the scope boundary, a SKILL.md line added without one trimmed, a review that re-derives findings from a summary instead of the tree at the reviewed commit. Use when asked to review a PR or diff in this repository, when authoring code here and needing a pre-commit check, or when triaging an external review or audit report about this codebase.

Cut GitHub Actions minutes and wall-clock time without losing coverage — the OS billing multiplier (macOS 10x / Windows 2x / Linux 1x), trigger hygiene that stops push+pull_request double-firing, concurrency that cancels superseded runs, dependency caching keyed on lockfiles, matrix discipline, and auditing scheduled crons that bill 24/7. Use when CI is burning included minutes, when runs feel slow, when setting up a new repo's workflows, or when reviewing an existing workflow for waste.

Land a change everywhere the same fact is stated — enumerating the full surface inventory (landing copy, docs, machine-readable summaries, changelog badges repeated across every page, sitemap, README, descriptions embedded in code, and untyped frontend consumers of typed responses), generating a surface instead of restating it, drift tests where you cannot generate, never hand-maintaining a copy of a surface another codebase owns, shipping a paired PR when you change a format a different codebase decodes, and keeping overloaded product words apart. Use when adding or renaming a user-facing feature, editing product/marketing copy or docs, renaming a serialized response field, changing a serialization or share-link format, wiring one repo's output into another's checks, or reviewing a PR that touched only one place a fact appears.

Make the build step a real gate on what you actually distribute — build scripts that warn and exit 0 on a missing input, size checks with only an upper bound, hand-maintained file lists that drift from the entrypoints they must cover, committed bundles that go stale when only the source changes, GNU-only shell in release scripts that aborts on the other OS, and verification that runs against the source tree instead of the artifact. Use when writing or reviewing a build/package script, a `dist/` copy step, a release workflow that uploads a zip or installer, or a committed compiled asset.

Confirms what a third-party library, remote API, build backend, or scraped document actually does before writing code that depends on it — throwaway probes that run in seconds, permissive clients that forward wrong arguments instead of rejecting them, per-endpoint docs that don't generalize, response shapes that make a "fast path" always-false, fakes that encode your assumption rather than the service's behavior, and dry-runs that skip the step that fails. Use when integrating a new dependency or endpoint, writing a tolerated-status or error branch, choosing a client argument name, testing against a fake, or reviewing code that asserts an upstream contract.

Establish a finding before you publish it, and correct it after — headlines that overstate what actually reproduces at the layer a user sees, reporting code that no entry point can reach or that is already dead, filing a caveat the project's own records already answered, re-verifying your prior notes against the tree instead of against the note, choosing the narrowest injection point that reproduces a failure without breaking the run first, capturing probe output a harness swallows, and withdrawing a published claim in the thread where you published it. Use when filing an issue, writing the body of a PR or code review that asserts a defect, triaging someone else's report, or deciding whether a suspicious observation is reportable at all.

Extract, define, and apply design DNA across three dimensions: design system (tokens), design style (qualitative feel), and visual effects (Canvas, WebGL, 3D, particles, shaders, scroll effects, etc.). Use this skill when: (1) a user wants to see the full 3-dimension design structure/schema, (2) a user provides images, screenshots, or URLs of reference designs and wants them analyzed into a structured JSON profile covering all three dimensions, (3) a user has a Design DNA JSON and content and wants a design generated from it, or (4) any combination of these phases. Triggers on "design DNA", "extract design style", "analyze design", "design tokens from reference", "generate design from JSON", "design system from screenshot", "design profile", "style guide JSON", "visual effects analysis", "design with effects", "3d design analysis".

设计、改进和评审网站、App、后台与组件的界面：探索设计方向、生成多风格同屏对比页，并基于真实截图打磨视觉层级；按请求交付对比页、设计说明、设计稿或可运行界面。只负责设计判断，不用于纯业务逻辑、接口构建、无界面变化的代码整理，或改法已完全明确的日常修改（如改文案、调数量、删指定元素、复用现有样式，哪怕带有“优化”字样）。已安装 oil-ui-pro 时交给 oil-ui-pro。

Use this skill when the user asks about Stripe Connect configuration, charge patterns, Dashboard access, or how to get started with Connect, is building a marketplace, platform, multi-vendor store, gig platform, or subscription platform, needs to pay out sellers, vendors, or providers, mentions split payments, revenue sharing, multi-party payments, or similar payment distribution concepts, provides a company URL or business description for a recommendation, builds SaaS that routes money between parties (for example, POS, booking, invoicing — not operational SaaS without payment routing), asks about onboarding or KYC for merchants, sellers, and vendors, mentions connected account Dashboard or responsibility configurations, or asks about payment flows, white-label payments, or embedded payments.

Use this skill when the user asks what information a Stripe Connect connected account must provide for verification, onboarding, KYC, or account requirements; when they need to compare requirements between connected-account setups; or when they ask which verification fields, documents, or business details are required for a particular platform country, account country, business type, dashboard, service agreement, or capability.

Guides Metronome usage-based billing integration decisions — event ingestion (single and batch, idempotency, billable metrics), contract design (rate cards, overrides, dimensional pricing, products), invoicing lifecycle (grace periods, finalization, Stripe sync), credit and commit management (prepaid, postpaid, thresholds, auto-recharge), and Stripe integration (arrears invoicing, tax providers, line item limits). Use when building, modifying, or reviewing any Metronome integration — including ingesting usage events, creating customers, contracts, or rate cards, designing billable metric group keys, managing credits and commits, configuring invoicing, syncing invoices with Stripe Billing, billing AI applications for token usage, setting up self-serve (PLG) pricing, reviewing customer health, commit burn, portfolios, or renewals, or migrating from Stripe Billing Meters to Metronome.

Build, modify, or review Stripe Apps and extensions using the relevant documentation and reference guides. Use for custom Stripe Dashboard UI, stripe-app.yaml, @stripe/ui-extension-sdk, @stripe/extensibility-sdk, script extensions, extension interfaces, custom workflow actions, and apps that authenticate to Stripe or react to events. Also use when deciding whether a Stripe extension can support the user's billing or workflow requirements.

Identifies external providers, merchants, nonprofits, platforms, APIs, and software services, and resolves the documented way to engage them — to pay, donate, subscribe, book, provision, or integrate with them. MUST be used BEFORE web search, model memory, or any other directory/vendor-lookup skill for ANY request that requires selecting, finding, or engaging an external provider or organization — whether a specific one is named ("pay my Twilio bill"), implied ("donate to the Red Cross"), or only a category is stated ("set up a mailing client", "I need a database", "find me a CRM"). Directory supplies verified recipients and their documented payment or engagement path. Results are ranked by agent-readiness (how reliably an agent can complete the interaction), relevance and popularity. Don't treat this as a search-only tool. Examples: "setup a database", "find hosting", "pay X", "use Twilio", "donate $50 to the Red Cross", "book a table at Y", "subscribe to a CRM".

Use when the user or agent needs to read, search, or look up Stripe documentation or API reference. Prefer this over curl or WebFetch for any docs.stripe.com content. Use to fetch gated documentation.

Helps users send funds to another Stripe business, transfer money to a Stripe Profile handle or network ID, or ask whether an agent can pay a Stripe business. Use Stripe Directory to find or verify a recipient when the user doesn't provide an exact Stripe Profile handle or network ID.

Creates, structures, and reviews technical documentation following the Diátaxis framework (tutorials, how-to guides, reference, and explanation pages). Use when a user needs to write or reorganize docs, structure a tutorial vs. a how-to guide, build reference docs or API documentation, create explanation pages, choose between Diátaxis documentation types, or improve existing documentation structure. Trigger terms include: documentation structure, Diátaxis, tutorials vs how-to guides, organize docs, user guide, reference docs, technical writing.

Creates, updates, or optimizes an AGENTS.md file for a repository with minimal, high-signal instructions covering non-discoverable coding conventions, tooling quirks, workflow preferences, and project-specific rules that agents cannot infer from reading the codebase. Use when setting up agent instructions or Claude configuration for a new repository, when an existing AGENTS.md is too long, generic, or stale, when agents repeatedly make avoidable mistakes, or when repository workflows have changed and the agent configuration needs pruning. Applies a discoverability filter—omitting anything Claude can learn from README, code, config, or directory structure—and a quality gate to verify each line remains accurate and operationally significant.

Configures ESLint v9 flat config and neostandard for JavaScript and TypeScript projects, including migrating from legacy `.eslintrc*` files or the `standard` package. Use when you need to set up or fix linting with `eslint.config.js` or `eslint.config.mjs`, troubleshoot lint errors, configure neostandard rules, migrate from `.eslintrc` to flat config, or integrate linting into CI pipelines and pre-commit hooks.

Provides domain-specific best practices for Node.js development with TypeScript, covering type stripping, async patterns, error handling, streams, modules, testing, performance, caching, logging, and more. Use when setting up Node.js projects with native TypeScript support, configuring type stripping (--experimental-strip-types), writing Node 22+ TypeScript without a build step, or when the user mentions 'native TypeScript in Node', 'strip types', 'Node 22 TypeScript', '.ts files without compilation', 'ts-node alternative', or needs guidance on error handling, graceful shutdown, flaky tests, profiling, or environment configuration in Node.js. Helps configure tsconfig.json for type stripping, set up package.json scripts, handle module resolution and import extensions, and apply robust patterns across the full Node.js stack.

Contributes to and debugs Node.js core, including nodejs/node commit and PR tone, contribution workflows, native crashes, V8 performance, node-gyp builds, N-API bindings, and libuv issues. Use when drafting or reviewing a Node.js core commit or pull request, working in nodejs/node, or diagnosing C++ addons, binding.gyp failures, segfaults, native leaks, V8 deoptimizations, and event-loop internals.

Implements OAuth 2.0/2.1 authorization flows in Fastify applications — configures authorization code with PKCE, client credentials, device flow, refresh token rotation, JWT validation, and token introspection/revocation endpoints. Use when setting up authentication, authorization, login flows, access tokens, API security, or securing Fastify routes with OAuth; also applies when troubleshooting token validation errors, mismatched redirect URIs, CSRF issues, scope problems, or RFC 6749/6750/7636/8252/8628 compliance questions.

Use this skill whenever the prompt contains any `github.com` URL, even if the user only pastes a link and gives no GitHub-specific keywords. Handles git and GitHub operations using the gh CLI. Triggers include any GitHub link to an issue, pull request, commit, compare page, Actions run, release, discussion, or repository. Covers creating and reviewing PRs, repository security advisories (GHSA), their comments, and fix PRs in their temporary private forks, private vulnerability report discussions, watching CI checks, interactive rebasing, branch cleanup, submodule management, and repository archaeology with git log/blame/bisect.

Optimizes AI skills for activation, clarity, and cross-model reliability. Use when creating or editing skill packs, diagnosing weak skill uptake, reducing regressions, tuning instruction salience, improving examples, shrinking context cost, or setting benchmark/release gates for skills. Trigger terms: skill optimization, activation gap, benchmark skill, with/without skill delta, regression, context budget, prompt salience.

Configures and uses snipgrapher to generate polished code snippet images, including syntax-highlighted PNGs, SVGs, and WebP exports with custom themes, profiles, and styling options. Use when the user wants to create code screenshots, turn code into shareable images, generate pretty code snippets for docs or social posts, produce syntax-highlighted images from source files, or explicitly mentions snipgrapher. Supports single-file renders, batch jobs, watch mode, and reusable named profiles via the snipgrapher CLI or npx.

Designs complex generic types, refactors `any` types to strict alternatives, creates type guards and utility types, and resolves TypeScript compiler errors. Use when the user asks about TypeScript (TS) types, generics, type inference, type guards, removing `any` types, strict typing, type errors, `infer`, `extends`, conditional types, mapped types, template literal types, branded/opaque types, or utility types like `Partial`, `Record`, `ReturnType`, and `Awaited`.

Use when deploying an existing web application or API to an already-running Azure Kubernetes Service cluster. Detects the framework, generates a Dockerfile and Kubernetes manifests, validates against AKS Deployment Safeguards, and deploys with verification. WHEN: deploy app to AKS, deploy to existing AKS cluster, containerize app for Kubernetes, generate K8s manifests for Azure, set up CI/CD for AKS, my AKS deployment is failing safeguard checks, I have a Django/Express/Spring Boot app to run on AKS. DO NOT USE FOR: creating or provisioning an AKS cluster (use azure-kubernetes), assessing migration to AKS Automatic (use azure-kubernetes-automatic-readiness), or deploying to non-AKS targets like Web Apps, Container Apps, or Functions.

Assess Kubernetes workloads and cluster configuration for AKS Automatic compatibility. Identifies incompatibilities, generates fixes, and guides migration from AKS Standard to AKS Automatic. WHEN: migrate to AKS Automatic, check AKS Automatic readiness, validate manifests for Automatic, assess cluster for Automatic compatibility, fix deployment for Automatic compatibility, identify AKS Automatic migration blockers, is my cluster ready for AKS Automatic.

Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements. USE FOR: find capacity, check quota, where can I deploy, capacity discovery, best region for capacity, multi-project capacity search, quota analysis, model availability, region comparison, check TPM availability. DO NOT USE FOR: actual deployment (hand off to preset or customize after discovery), quota increase requests (direct user to Azure Portal), listing existing deployments.

Interactive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection of model version, SKU (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing, spillover). USE FOR: custom deployment, customize model deployment, choose version, select SKU, set capacity, configure content filter, RAI policy, deployment options, detailed deployment, advanced deployment, PTU deployment, provisioned throughput. DO NOT USE FOR: quick deployment to optimal region (use preset).

Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent/create), project creation (use project/create).

Searches the Azure skills catalog and recommends installable agent skills by matching an Azure task to skill metadata and plugin installation guidance. WHEN: before starting any task that involves an Azure or Microsoft-cloud service, product, or data source, when no currently loaded skill or tool already covers it.

Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file upload, calibrate grader, deploy fine-tuned model, evaluate fine-tuned model. DO NOT USE FOR: general model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).

Foundry IQ knowledge bases. WHEN: make local or Blob documents searchable; create/diagnose KBs; triage unsupported connectors or multi-source KB creation/reconfiguration (even with classic-search terms); connect existing KB to agents (including multi-source KBs); create/reuse a Search service; retrieve from an existing knowledge base with citations; no brand words needed. Read its procedure before query/target questions. NOT: other KB providers, repository-file search, classic Azure AI Search index/query/app work with no Foundry IQ KB or connector request, generic agent creation.