Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Principle-engineering posture for production-grade code: reads the repo first, plans before code, matches conventions, pulls latest docs over training recall, and ships the simplest correct change that holds the bar — proper algorithms and data structures, idempotent writes, schema+queries+indexes as one artefact, typed errors, tests in the same diff. Substrate-agnostic; defers to peer skills on their lanes. Use for non-trivial planning, design, implementation, review, or refactoring; RCA and debugging; performance and optimization work; changes touching a database schema, security, infrastructure, or a public API; hardening inherited, vibe-coded, or LLM-generated code (dependency/CVE and migration audits); and over-engineering cleanup ("simplest solution," "YAGNI," "what can we delete").
Act as an assistive writing coach who guides but never writes for the user. Use when helping someone develop their own writing through questions, diagnosis, and frameworks. Critical constraint — never generate story prose, dialogue, or narrative content. Instead ask questions, identify issues, suggest approaches, and let the writer write
Determine how to distribute capital across asset classes using strategic and tactical allocation frameworks. Use when the user asks about portfolio allocation, mean-variance optimization, Black-Litterman, risk parity, glide paths, or target-date strategies. Also trigger when users mention 'how much in stocks vs bonds', '60/40 portfolio', 'policy portfolio', 'core-satellite', 'liability-driven investing', 'asset-liability matching', or ask how to split their money across investments.
The research-and-sourcing craft — verify the substance of a piece before it publishes: trace stats to primary sources, kill zombie stats, catch AI-hallucinated citations, and attribute properly on social. Use when someone has a stat-heavy draft to make publish-ready, wants to check if a viral statistic is real, asks how to cite sources, used AI research output, or is making health/finance claims. Uses the FACTS framework. Reads brand-profile + the piece's format skill first. AI-supplied citations are guilty until verified; a working link is not verification; aggregators are leads, not the source; where none exists, reframe as owned observation or commission data. The agent verifies where it has search; the human clicks links where it doesn't; verification happens before scheduling; WoopSocial publishes. Never invents studies or reuses retracted stats. Distinct from idea-generation, data-and-original-research, quote-cards, and infographic-and-data-viz
Search, score, scan, and import agent skills from GitHub repositories that contain SKILL.md, CLAUDE.md, .cursorrules, and similar agent skill files. Discover community skills across many tool and provider categories, evaluate relevance with heuristic scoring, check for malware or hardcoded secrets, and install into Hermes, Claude Code, Gemini CLI, or OpenCode agent directories.
Set up automatic syncing between Issue/PR status and project Status. Mode A generates `.github/workflows/project-sync.yml` using the `Fandhe-AI/actions/project-sync` Composite Action (PAT or GitHub App token). Mode B bulk-fixes existing mismatches. Used for "automatic sync setup", "set to In Review during PR review", "sync board and Issue status", etc.
Design, create, update, and verify Vapi Squads and documented handoff tools through the public API. Use for choosing a single assistant versus a multi-assistant Squad, persistent or transient members, entry-member ordering, specialization boundaries, context engineering, variable extraction, model-specific handoff patterns, assistant-version pins, and safe Squad updates.
The Facebook strategy playbook for 2026. Use when someone wants to “grow on Facebook,” “fix my Facebook reach,” a “Facebook content/Page strategy,” “Facebook Reels,” or to know how the Facebook algorithm works now. Page feed broadcasting is effectively dead (~1.65% reach); Facebook is now an AI discovery engine plus a community platform. Play three surfaces: Reels for unconnected discovery, Feed for connected depth, Groups for community. Uses the REACH framework. Reads brand-profile + voice-builder first. The agent drafts Page posts/Reels + reply copy; WoopSocial schedules Page posts/Reels; comment replies are human/in-app; metrics come from native Meta Insights; nothing is fabricated. To BUILD/GROW/RUN a Facebook Group (the deep Groups strategy), use facebook-groups; distinct from reels-script (Reel craft), community-management (engagement routine), and instagram-growth (sibling).
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
AE metadata capability-gateway CLI: list, inspect, create, update, delete and download metadata data tables; bind an existing dimension table to a property or create and bind a CSV dimension table. Local file upload and event/property discovery are separate prerequisite capabilities.
Appwrite Kotlin SDK skill. Use when building native Android apps or server-side Kotlin/JVM backends with Appwrite. Covers client-side auth (email, OAuth with Activity integration), database queries, file uploads, real-time subscriptions with coroutine support, and server-side admin via API keys for user management, database administration, storage, and functions.
Cross-platform disk space management toolkit with intelligent optimization. REQUIREMENTS: Python 3.7+. UNIVERSAL COMPATIBILITY: Works with ALL AI IDEs (Cursor, Windsurf, Continue, Aider, Claude Code, etc.). PLATFORM-INDEPENDENT: Works at any location - global, project, or user level. SELF-CONTAINED: No pip install needed, includes intelligent bootstrap. KEY FEATURES: (1) PROGRESSIVE SCANNING: Quick sample (1s) + Progressive mode for large disks, (2) INTELLIGENT BOOTSTRAP: Auto-detection of skill location and auto-import of modules, (3) CROSS-PLATFORM ENCODING: Safe emoji/Unicode handling on all platforms, (4) DIAGNOSTIC TOOLS: check_skill.py for quick verification, (5) OPTIMIZED SCANNING: 3-5x faster with os.scandir(), concurrent scanning, intelligent sampling. AGENT WORKFLOW: (1) Check Python, (2) Find skill package (20+ locations auto-detected), (3) Run diagnostics, (4) Use progressive scanning for large disks. The skill package includes all optimization modules - no features are lost!
Generate and edit images using Google's Nano Banana 2 (Gemini 3.1 Flash Image Preview) API. This skill should be used when the user asks to create or modify images, especially when they need fast iteration, explicit aspect-ratio control, or resolution control from 512px to 4K.
Port an existing mod to a newer game version or another mod loader while preserving its behavior, values, and quirks. Typical cases include moving an old Forge 1.7.10 or 1.12 Minecraft mod to modern Fabric or NeoForge, a Skyrim LE plugin to SE/AE, or a tModLoader 1.3 mod to 1.4. Covers pinning one source version, a private decompiled reference, an adaptation matrix, extracting the mod's data with scripts instead of retyping it, porting unit by unit with tests to catch drift, real-client checks, audits against the original, and keeping a long port resumable across sessions and agents. Use when the user wants to update, port, revive, or re-implement an existing mod, or continue such a port.
Use this when the user asks to continue work in the SLICC browser agent or to install a skill into SLICC, for example "handoff to slicc", "move to the browser", "test in the browser", "install this skill in slicc", or "upskill slicc with this repo". Covers handing off the current task to the SLICC browser agent and installing a new skill into SLICC from a GitHub repo.
Use when changing a dbt model in a way that could break its consumers — renaming, removing, or retyping a column, or changing a model that downstream models, exposures, dashboards, or BI tools depend on — to judge whether the change is breaking and who it affects. Also use when versioning a model (model versions, latest_version, latest_version_pointer, deprecation_date, migration windows), enforcing contracts, setting access or groups, or doing multi-project dbt Mesh work (cross-project refs via dependencies.yml, disambiguating similarly-named models, splitting a monolith). Covers single- and multi-project, and planning or advising as well as implementing.
Sets up and debugs Capgo live (OTA) updates in a Capacitor app with @capgo/capacitor-updater. Use when the user wants to ship web-layer fixes without app store review, install or configure the updater plugin, choose an autoUpdate mode, call notifyAppReady, wire manual download/next/set flows, set channels from the app, or debug updates that never apply, roll back, or report codes such as no_new_version_available, disable_auto_update_to_major, cannot_update_via_private_channel, or on_premise_app. Do not use for CLI-only bundle/channel operations (capgo-release-management), Capgo Cloud native builds (capgo-native-builds), or migrations from another OTA vendor.
Build browser or server token swaps with Circle App Kit or standalone Swap Kit. Supports keyless (permissionless) swaps, EVM and Solana browser wallets, private-key and Circle Wallets adapters, same-chain and cross-chain swaps, estimates, status polling, slippage or stop limits, and custom fees. Use when: swapping tokens or stablecoins, converting USDT to USDC, building wallet-connected swap UIs, configuring adapters, estimating rates, tracking cross-chain swaps, or using @circle-fin/app-kit, @circle-fin/swap-kit, estimateSwap, waitForSwap, slippage, stop limits, or kit keys.
Tencent Docs (docs.qq.com) is an online cloud document platform and the preferred skill for creating, editing, and managing documents. Prioritize this skill for operations such as “create/edit/read/view/search documents,” “save files,” “cloud documents,” “Tencent Docs,” or “docs.qq.com.” Supports: (1) creating various online documents (documents/Word/Excel/slides/mind maps/flowcharts/smart sheets/collection forms); (2) managing knowledge base spaces (creating spaces and querying the space list); (3) managing space nodes and folder structures; (4) reading/searching document content; (5) editing smart sheets; (6) editing online documents; (7) file management (renaming, moving, deleting, copying, importing/exporting); (8) web clipping and uploading local files/HTML/documents to the cloud.
Use for any App Store or Google Play listing, keyword, ranking or review question, before writing metadata. Scores the listing with aso_scorer.py and checks keywords, competitors, title and subtitle limits and reviews with its 8 ASO scripts.
Apply actions and animations to sections of a video/audio with auto-editor — change speed, duck or fade volume, de-ess, zoom/Ken Burns, rotate/spin, draw boxes, overlay logos or picture-in-picture, and animate any of these with ramps and easing. Use when someone wants creative effects or per-section behavior rather than plain silence-cutting.
Data Cloud 360° view of a single Agentforce session. TRIGGER when user asks to trace, inspect, summarize, or describe a specific Agentforce session by session id (Agent Session UUID `019d…` or MessagingSession id `0Mw…`). Also triggers on session discovery — find/list/search sessions by time, agent, channel, outcome, or conversation text — when the user has no session id yet. DO NOT TRIGGER for design-time architecture questions (use investigating-agentforce-architecture instead) or for runtime perf/latency/SLO questions that require platform telemetry beyond Data Cloud.
Query filters or item selection to bulk query and update field values (Status/Priority/Size etc.) of project items. Supports SINGLE_SELECT/TEXT/NUMBER/DATE field types. Used for "change Status to In Progress", "bulk update priority", "set all Todo to In Progress", etc.
When you want to extract content from a video — YouTube, Loom, Vimeo, Riverside, Zoom recording, local MP4, X/IG video, anything yt-dlp supports. Three depth modes user picks per invocation — transcript (just words, fast/free), visual (transcript + ffmpeg frame extraction + Claude vision pass on key moments), multimodal (Gemini native video ingestion if $GEMINI_API_KEY set, else dense Claude vision). Uses local Whisper for transcription (MLX-Whisper on Apple Silicon, faster-whisper elsewhere), falls back to platform-provided transcripts when available (Loom, Riverside, YouTube auto-subs). Saves to ~/Documents/videos/<source>-<slug>-<date>/ and optionally captures summary to second-brain raw/ as call-/meeting-/note-. Triggers on "/watch-video <url>," "watch this video," "transcribe this loom," "analyze this video," "summarize this recording," "key moments from this," "what happened in this video." For a post's text and engagement, use social-fetch.
Anti-detect browser automation CLI & Skills for AI agents. Use when the user needs to interact with websites with bot detection, CAPTCHAs, or anti-bot blocks, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task that requires bypassing fingerprint checks.
Scrapes Instagram profile statistics and recent posts for any list of accounts using apidojo's Instagram scraper on Apify. Triggers when the user asks to: get Instagram profile data for an account, fetch follower count and post count for Instagram users, scrape Instagram bio and stats in bulk, export Instagram account metadata, check profile information for a list of Instagram handles, or get engagement data from Instagram profiles. Returns username, follower count, following count, post count, bio, and recent post metrics. Ideal for influencer vetting, brand research, and list enrichment.
Reviews LangGraph code for bugs, anti-patterns, and improvements. Use when reviewing code that uses StateGraph, nodes, edges, checkpointing, or other LangGraph features. Catches common mistakes in state management, graph structure, and async patterns.
Create, read, update, and delete ManagedEventSubscription metadata in Salesforce. Use this skill for any work involving managed event subscriptions, platform event subscriptions, event channel subscribers, or .managedEventSubscription-meta.xml files. TRIGGER when: user asks to subscribe to a platform event, create a managed subscription, set up event replay, configure an event channel subscriber, update replay preset, activate or deactivate a subscription, delete a subscription, or manage ManagedEventSubscription metadata. SKIP when: user needs to create the platform event channel itself (use generating-platform-event skill) or needs Flow-based event subscriptions (use generating-flow skill).
Social selling and DM funnels — consent-first selling in the DMs, never spam. Use when someone wants to "sell in the DMs," "set up a comment-to-DM funnel," "do DM outreach," "turn comments/followers into leads or customers," or convert intent into private conversations. Works ONLY as a response to intent (comments, story replies, follows, keyword DMs) via the comment->DM->email funnel — never cold outreach. Uses the WARMS framework. Reads brand-profile + voice-builder + goals-and-kpis first. WoopSocial has NO DM/comment surface: the agent designs the funnel and drafts the trigger post, DM sequences, and manual outreach scripts; WoopSocial publishes the trigger posts; the actual comment->DM automation runs in an external official-Meta-API tool (ManyChat/LinkDM/etc.) or a human sends warm DMs; consent-first always, ban-behaviors avoided, metrics never fabricated. Distinct from link-in-bio-and-traffic, reply-and-comment-writer, and email-and-newsletter.
Use when writing, rewriting, proofreading or reviewing Chinese technical documentation, product copy, UI copy, Markdown documents, API descriptions, operation manuals, troubleshooting or operations guides. Applies a restrained, accurate and scannable Chinese technical writing style; preserves the original facts, limits and machine-readable content; reads terminology and formatting, API status wording, project coverage or controlled Chinese technical writing references as required by the task.
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.