Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Publish VS Code extensions to the Visual Studio Marketplace. Use when asked to publish my extension, setup VS Code marketplace publishing, package vscode extension, create a publisher, setup PAT for vsce, automate extension releases with GitHub Actions, or need help with vsce commands. Don't use for building the extension features themselves, publishing to Open VSX (different marketplace), or PyPI/npm package release.
This skill should be used when debugging VTable (canvas-based table) rendering/interaction issues in the browser via Chrome DevTools by inspecting the VRender Scenegraph (Scenegraph.tableGroup). Use it for blank/white canvas, missing/misaligned cells, frozen header/body issues, hover/selection box issues, DOM overlay (react attribute) issues, and React18/React19 differences in custom-layout / react-reconciler (e.g., Fiber contamination, double React, older React element errors).
Run cold email, email warmup, LinkedIn, Instagram and WhatsApp outreach, email verification and a 200M+ B2B lead database from any MCP agent through WarmySender — the agent builds, launches and manages campaigns in plain language and never sends a message itself; WarmySender's scheduler paces every action inside safe limits.
Research-driven authoring of Lytics webhook templates -- fetches destination docs, drafts and tests the transform, and emits a ready-to-go webhook job blueprint. Use when the user wants to send Lytics audience triggers or enrichment requests to a custom webhook destination (e.g., Qualtrics, Slack, custom CRM).
WeChat Official Account article writing assistant (crayfish-adapted edition). First ask the user what to write, then search, write, and generate images in one seamless flow. Supports many styles such as technical explainers, product teardowns, news analysis, hands-on tutorials, and industry observations. Use when the user says "write an article about XXX", "analyze XXX product", or "help me research XXX".
Weekly analytics report combining GA4, Google Search Console, and Microsoft Clarity into a premium HTML email. Use for automated Sunday cron jobs that generate weekly product analytics reports. Tracks users, sessions, pageviews, SEO performance (queries, impressions, CTR, position), UX friction (dead clicks, rage clicks, quickbacks), and week-over-week trends. Includes accountability tracking (did we do what we said?), prioritized recommendations with impact/effort ratings, and actionable checklists. Persona: $15K/month SEO consultant. Outputs: HTML email + chat summary.
Run structured What-If scenario analysis with multi-branch possibility exploration. Use this skill when the user asks speculative questions like "what if...", "what would happen if...", "what are the possibilities", "explore scenarios", "scenario analysis", "possibility space", "what could go wrong", "best case / worst case", "risk analysis", "contingency planning", "strategic options", or any question about uncertain futures. Also trigger when the user faces a fork-in-the-road decision, wants to stress-test an idea, or needs to think through consequences before committing.
Create, inspect, and edit Microsoft Word documents and DOCX files with reliable styles, numbering, tracked changes, tables, sections, and compatibility checks. Use when (1) the task is about Word or `.docx`; (2) the file includes tracked changes, comments, fields, tables, templates, or page layout constraints; (3) the document must survive round-trip editing without formatting drift.
Develop and deploy code for WordPress VIP environments following platform requirements, coding standards, and best practices. Use when working with WordPress VIP projects, VIP-CLI, VIP-hosted sites, or when the user mentions WordPress VIP, WPVIP, VIP Go, or enterprise WordPress.
TDD planning pipeline with multi-mode routing (plan/verify). Session discovery → context gathering (spawn_agent) → test coverage analysis (spawn_agent) → conditional conflict resolution → TDD task generation (spawn_agent) → structure validation → interactive verification. Produces IMPL_PLAN.md with Red-Green-Refactor cycles, task JSONs, TODO_LIST.md.
Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge
Use when the user wants to integrate with the X (Twitter) API via Xquik to search tweets, look up user profiles, extract followers, run giveaway draws, monitor accounts, or access trending topics. Also use when the user mentions 'Xquik,' 'Twitter API,' 'X API,' 'tweet scraper,' 'follower extraction,' or 'Twitter monitoring.' Covers REST API, webhooks, and MCP server setup.
Build a multi-board dashboard for XIAO ESP32S3: each board joins WiFi (STA mode), publishes its touch sensor value over MQTT, and accepts LED on/off commands, while a browser dashboard shows every board live and lets you toggle each LED. Use this skill whenever the user wants several ESP32S3 boards reporting to one web page, an MQTT-based sensor dashboard, "여러 esp32s3 대시보드", "MQTT로 여러 보드 연결", or mentions Mosquitto/Eclipse MQTT with an ESP32S3. For a single board with no broker, use the `xiao-esp32s3` skill's own SoftAP + web server example instead.
Generate a complete video plan with optimized title, thumbnail, and hook concepts based on research. Orchestrates specialized skills (youtube-title, youtube-thumbnail, youtube-video-hook) to create production-ready video plans. Use after research is complete or when the user wants to plan a new video.
Answer questions in the persona, tone of voice, and mindset of "程序员鱼皮". 鱼皮 is a former Tencent full-stack engineer, an AI + programming knowledge blogger with 2 million+ followers across platforms, CEO of the tech company 鱼鸢网络, and founder of 编程导航. Use this skill when the user wants programming learning advice, job-hunting guidance, project selection, technology direction judgment, startup experience, self-media operation advice, or AI programming practice guidance from 鱼皮's perspective. It also applies when the user explicitly asks to answer "in 鱼皮's style" or "like 鱼皮". Typical questions covered include: programming learning paths, how to write a resume, whether to accept a certain offer, what technology to learn, how to do open source, how to do self-media, what programmers should do in the AI era, and what pitfalls were hit during startups.
Check Amazon listing health from a real consumer's perspective. Simulate the consumer browsing experience via web scraping to check key metrics such as page visibility, price, seller information, shopping cart, shipping, category node, ranking and negative reviews, and verify keyword search visibility. Use when: acceptance after a new product launch, routine inspection, troubleshooting listing anomalies. Trigger: /zach-listing-health-checker
Turn the business data the user already has (Airtable, Notion, Google Sheets, Lark Base, Excel, CSV exports, or a database someone once set up for them) into three things in one sitting: a plain-language account of what their database actually records, a findings list of data problems and blind spots, and a one-page dashboard answering the single most urgent money question, with alerts ranked by money at risk. Use when the user wants a dashboard or a read of their data ("build me a dashboard", "turn my spreadsheet into a dashboard", "what is my data telling me", "帮我做仪表板", "分析我的数据/表格"), pastes a link or drops files from one of those products and asks what the data says, or returns with a fresh export to refresh a page built earlier. NOT for designing or restructuring the database itself (that is breakthrough-base-schema-design), NOT for setting up a second brain or vault, and NOT a live auto-updating dashboard: every page is a snapshot of one export.
End-to-end implementation and self-review in a single invocation — implements from an Issue, plan file, or free-text description, then runs a lean fresh-context review. With --guard it also waits for CI and peer review, addresses feedback until the PR is review-ready, and ends with a risk verdict (merge-ready or review-ready, or merged when the project opts in). Use when the user wants to implement and review without manual handoff between skills
Writes and edits in Gabo Esquivel's voice and identity for any channel, including gaboesquivel.com, the gaboesquivel package, blog, LinkedIn, Twitter/X, outreach, and spoken or voice-agent lines. Use whenever the user mentions Gabo Esquivel, Blockmatic Labs, personal brand, how Gabo talks, or asks to sound less like AI marketing. Site routes, package fields, SEO, and generate/link live in those repos' docs, starting at AGENTS.md, not in this skill.
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.
Impression share analysis and root cause diagnosis for Google Ads Search campaigns. Auto-invoke when investigating underspending, analyzing auction competitiveness, or diagnosing budget vs. quality issues. Interprets Search IS, Budget Lost IS, and Rank Lost IS metrics in smart bidding context
Evaluate changes to agent prompts, skills, routing policies, and harnesses against reproducible baselines, held-out suites, and regression benchmarks. Use when optimizing agent system prompts, measuring skill triggering accuracy, evaluating routing changes, or running benchmark regressions — even if the user does not explicitly say "fable-eval" (e.g. "benchmark this prompt", "evaluate agent behavior", "test skill performance", "run the eval suite"). Do NOT use for routine application unit tests (use fable-verify).
Author, evaluate, refine, optimize, and package autonomous AI agent skills across multi-agent ecosystems with BinEval scoring and description tuning. Use when creating a new skill from scratch, editing an existing skill that misfires or undertriggers, authoring test suites for skills, optimizing skill descriptions, or packaging skills for distribution — even if the user does not explicitly say "fable-skill-creator" (e.g. "create a skill", "build a new skill", "optimize skill description", "package this skill", "teach the agent to do X"). Do NOT use for general application code changes or non-skill tasks.
Autonomous dutiful junior maintainer for software repositories. Automates CI troubleshooting, PR conflict resolution, automated code review, issue triage, nightly codebase sweeps, and weekly dependency maintenance. Use when managing automated repository health, investigating failing CI workflows, resolving merge conflicts on open PRs, or conducting proactive maintenance sweeps.
Generates Tzatziki-based Cucumber tests (Gherkin .feature files) from a functional specification. Use this skill whenever a user wants to write Cucumber tests, add BDD scenarios, create feature files, generate tests, or test application behaviors with Gherkin — especially in Java/Spring projects. Use this skill for tests involving HTTP, relational database (SQL), JPA, Kafka, MongoDB, OpenSearch, logging, or MCP. Also use when the user mentions writing integration tests, acceptance tests, or end-to-end tests.
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.
Use when the user wants to audit or correct drift across canonical project context files such as `AGENTS.md`, `CLAUDE.md`, `ARCHITECTURE.md`, `CONSTRAINTS.md`, `JARGON.md`, `EPISTEMIC-MAP.md`, `README.md`, and `openspec/config.yaml`, or mentions context drift, memory-file drift, redundant project docs, wrong document, layered documentation, or doc ownership. This skill checks whether each fact lives in the right document, identifies redundancy and layer-boundary violations, and prepares lossless move/delete proposals with diff previews and per-change approval. Prefer it over ad-hoc cleanup because these files are load-bearing and misplaced content can change agent behavior or tool behavior.
Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
Turns one long video or podcast (a local file or a YouTube link) into the best 3-5 short vertical clips, each cut and styled in the user's profile style. Transcribes once, splits the talk into candidate clips at sentence boundaries inside the chosen length, scores every candidate in code (speech rate, loudness, laughter, numbers and names said), shows the shortlist on one page with a preview of each, then trims, cuts and style-edits each pick as its own edit. Use when the user says "clip this video", "make shorts from my podcast", "find the best clips", "cut this into TikToks", "turn this YouTube video into reels", "repurpose this long video", or drops a long video (over about 3 minutes) or a YouTube link and wants short clips. Not for editing one short take (that is start or cut), and not for measuring someone else's style (that is creator-teardown).
Defines refined code through the three lenses of constraints, simplicity, and parametricity, with rules for type proofs, no partial calls, explicit signatures, unrepresentable wrong states, hot-path discipline, and style. Use when writing, changing, or reviewing code to a refinement bar, or whenever the user asks for code to follow the rules in code-refinements
Cuts raw talking-head footage into a clean jump cut. Takes one take or several joined (mp4 or mov, any aspect, 4K phone footage is fine), transcribes it word by word, removes retakes, false starts, fillers and dead pauses, and renders cut.mp4 at the source resolution plus words.json timed to the cut. The user approves the cut on a page with the whole transcript and every removed word struck through. Use when the user says "cut my video", "just cut it", "remove my mistakes", "cut out the retakes", "remove the pauses", "clean up this take", "jump cut this", "tighten this clip", or asks only for the cut of a raw take; start calls it for a full edit. Runs before style-edit. Not for a general request to edit a video or to make it look like a creator (that is start), not for adding captions, zooms or cards (style-edit), and not for analysing someone else's videos (creator-teardown).
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.