Skills
99,951 packaged capabilities and playbooks for agents. Install any of them with one command.
All
When the user wants to identify, quantify, and mitigate financial risks. Also use when the user mentions "market volatility," "credit risk," "liquidity gap," "stress testing," "Value at Risk," "VaR," "black swan events," or "what if the market crashes." Use this for portfolio management and enterprise risk.
Guide for writing idiomatic Rust code based on Apollo GraphQL's best practices handbook. Use this skill when: (1) writing new Rust code or functions, (2) reviewing or refactoring existing code, (3) deciding between borrowing vs cloning or ownership patterns, (4) implementing error handling with Result types, (5) optimizing Rust code for performance, (6) writing tests or documentation for Rust projects
Account-based B2B advertising — display ads, retargeting, cross-channel campaigns targeting specific accounts or segments. Use when ABM ads aren't reaching target accounts, display ad CTRs are low, retargeted visitors aren't converting, B2B audiences are too broad or too small, can't tie ad spend to pipeline, or not sure which B2B ad platform to pick. Do NOT use for email outbound (use /sales-cadence), general paid media/B2C ads (out of scope), or ZoomInfo-specific config (use /sales-zoominfo). For platform-specific help, use /sales-zoominfo.
Schedules sales meetings efficiently — booking pages, round-robin routing, calendar integration, reminders, no-show recovery, and meeting page conversion. Use when prospects aren't booking meetings, no-show rates are too high, round-robin isn't distributing evenly, booking page conversion is low, unsure which scheduling tool to use, or Mixmax meetings aren't working. For Yesware-specific help, use /sales-yesware. Do NOT use for lead routing rules (use /sales-lead-routing), cadence design (use /sales-cadence), or calendar-based CRM automation (use /sales-integration).
Use when making a finished mobile game user-acquisition (UA) video ad with Scenario at an exact length for TikTok, Reels, Stories, Meta feed, YouTube Shorts, or ad networks: from a one-line concept or the game's own screenshots, screen recording, gameplay video, characters, icon, or UI kit. Pin-pull, parking jam, match-3, swallow hole, evolution runner, stacker, draw to protect, odd one out, gacha, merge. Also hook, hand, HUD counter, end card. Not for ads from a product photo.
Scene Feedback surveys for Decentraland SDK7 playtests: plan questions and timing, organize test rounds and find testers, integrate or debug the module, or analyze exported CSV ratings and comments. For audiovisual reactions to gameplay actions, use add-interactivity, audio-video or build-ui.
Machine learning in Python with scikit-learn. Use for supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.
【Internal suite skill · Users usually don’t need to invoke it directly in the full workflow; simply describe the request to the orchestrator short-drama-director, which will route it to this skill automatically】【漫剧老李 V7.4.26 suite · Subskill · Track ② Overseas drama】Overseas drama script specialist engine: rules for the script layer of non-Chinese body text / authentic regional speech in North America and elsewhere / multilingual / dialect projects. Core capabilities—language and style contract (established before writing and carried across stages, not a post-draft polishing label), three calibration states (region_unvalidated / evidence_calibrated / human_reviewed; models must not upgrade them independently), North American English dialogue adaptation, no inferring permissions from identity, monolingual listener boundaries, and local-detail eligibility. Triggers: overseas drama, English script, North American English, American dialogue, multilingual, dialect, localization, ESL, subtitles. This skill is a suite member; enter the complete workflow through the orchestrator short-drama-director; the track is selected and locked by the orchestrator at 〇·0.
SDD step 7. Archive feature.md and plan.md into docs/specs-archive/<yyyymmddHHMM>-<feature-name>/ directory, then update docs/project.md with the new feature, and any architecture decisions made. Use after /sdd-review is complete and the feature is ready to merge.
When the user wants to optimize seasonal planning, manage seasonal buy decisions, or plan for seasonal demand. Also use when the user mentions "seasonal planning," "seasonal buy," "holiday planning," "back-to-school," "spring/fall collection," "seasonal inventory," "peak season," or "seasonal assortment." For demand forecasting, see demand-forecasting. For retail allocation, see retail-allocation.
Load PROACTIVELY when task involves security review, vulnerability assessment, or hardening. Use when user says "check for security issues", "audit for vulnerabilities", "scan for secrets", "review auth security", or "check OWASP compliance". Covers authentication and session security, authorization and access control, input validation and injection prevention, data protection and encryption, dependency vulnerability scanning, API security (CORS, rate limiting, headers), and infrastructure hardening. Produces structured reports with severity ratings.
Generate cinematic short-form video with ByteDance Seedance 2.0 Pro on RunComfy. Documents Seedance 2.0 Pro's strengths (multi-modal references — up to 9 images, 3 videos, 3 audio — synchronized in-pass audio with natural lip-sync, cinematic motion refinement), the 4–15s duration schema, and when to route to HappyHorse 1.0 / Wan 2.7 / Kling instead. Calls `runcomfy run bytedance/seedance-v2/pro` through the local RunComfy CLI. Triggers on "seedance", "seedance 2", "seedance v2", "seedance pro", "bytedance video", or any explicit ask to generate video with this model
This skill should be used whenever the user mentions a "semantic model", "data model", or "dataset", or asks to "build", "model", "design", "optimize", "review", or "audit" one, or to "add a measure", "add a relationship", "create a role" / "set up RLS", "add a calculation group", "set up incremental refresh", "fix a star schema", "reduce model size", "prepare a model for Copilot / AI", or "check model quality". Covers the full lifecycle (design, build, refresh, review) and drives every operation through the `te` CLI first, then TOM (connect-pbid) or a model MCP, then TMDL authoring (the tmdl skill). Not for report visuals (use pbir-cli) or isolated DAX query tuning (use the dax skill).
Apply Semantic Versioning 2.0.0 (semver.org) to decide version bumps, validate version strings, and compare version precedence. Use whenever a task involves choosing the next version number, judging whether a change is a MAJOR/MINOR/PATCH bump, checking that a string is a well-formed version, ordering versions by precedence, or building a pre-release or build-metadata version. Often used as a building block by release, changelog, and publishing workflows — trigger whenever version numbers are being reasoned about, even if "semver" is never said.
Senhasegura PAM platform integration — A2A OAuth 2.0, PAM Core credentials, SSH key rotation, DSM CLI for CI/CD, External Secrets Operator (Kubernetes), MySafe, and a runnable MCP server. USE WHEN senhasegura, segura, A2A application, DSM CLI, runb, MySafe, ExternalSecret + senhasegura, OAuth client_credentials for PAM, credential custody release, /iso/coe/senha endpoint, SCIM provisioning. NOT FOR HashiCorp Vault, AWS Secrets Manager, Azure Key Vault, GCP Secret Manager, 1Password, or generic OAuth 2.0 flows (use those directly).
Use when the main problem is a noisy or aliased analog/ADC signal and the task needs signal-chain diagnosis or filter-path selection across sampling, anti-aliasing, RC/input conditioning, ADC source impedance/settling, latency, startup, saturation, or raw/fault observability. Apply it when software filtering and hardware signal conditioning interact, even when the request only says that an analog sensor is unstable. Hand reusable Arduino snippets to arduino-code-generator, board facts to board-support, voltage/pin/rail safety to wiring-safety-check or circuit-debugger, and calibration after detection to sensor-calibration-workbench.
Migrate to Sentry span streaming (span-first trace lifecycle). Use when asked to "enable span streaming", "migrate to span streaming", "use traceLifecycle stream", "add spanStreamingIntegration", or switch from transaction-based to streamed span delivery.
Read the staged git diff and flag anything that shouldn't be committed — secrets or API keys, leftover debug code (dd(), console.log, etc.), large commented-out blocks, and accidentally added large or binary files. For each problem show the file and line and why it's a problem, then end with a clear PASS or BLOCK. Use before committing, when the user asks to "check what's staged", "review my staged changes", "anything I shouldn't commit", "scan the diff before I commit", or wants a pre-commit safety check.
Use Shopware CLI for Shopware project, extension, and account workflows — create and install new projects (project create, project dev install), validate projects or extensions (with --only/--exclude and --format json, junit, github, gitlab for CI), develop, build, upgrade, and troubleshoot. Also use when contributing to shopware/shopware-cli and reasoning about the CLI's user-facing behavior.
Write or rewrite Chinese technical content in Simplified Technical Chinese (STC): procedures, installation and deployment, troubleshooting, interface and parameter descriptions, technical concept explanations, and explanatory answers for readers. Use when the user mentions “简明技术中文”, “STC”, “受控中文”, “像 ASD-STE100 那样写中文”, or “一词一义”; also use when the user asks to make Chinese technical instructions clear or unambiguous. Not for marketing copy, narratives, legal originals, or code.
Analyze skill execution traces to identify issues and automatically evolve/improve skills. Use when users provide trace files (JSON) from skill runs and want to improve skill performance based on real execution data. Triggers on requests like "analyze traces", "evolve skill based on traces", "improve skill from execution history", "find issues in skill traces", or when working with skill trace/log files.
Meta-skill that forges, audits, and refines other skills. Three modes – forge a new skill from a brief, audit recent chat transcripts for new-skill candidates and pain points, or refine an existing skill with additive-only changes. Triggers on "skill-forge a thing that does X", "forge a skill", "skill-forge audit", "skill audit", "refine my skills", "skill-forge refine <name>", or "/skill-forge". Auto-opens a PR against mphinance/alpha-skills (never auto-merges).
Test engineer skill, responsible for software quality assurance and testing work. Applies to the following scenarios: (1) writing test cases and test plans (2) executing functional and regression tests (3) filing defects and tracking fixes (4) performing API testing and automated testing (5) executing user experience testing (6) analysing test results and quality assessment
Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".
Analyze file contents in a directory tree and intelligently rename files based on what they contain, optionally reorganizing them into a logical folder structure. Use this skill whenever the user wants to clean up messy file names, organize downloaded files, sort documents by content, rename files that have meaningless names (like IMG_20240101.jpg or document(3).pdf), or tidy up any folder where file names don't reflect their actual content. Also triggers when users mention bulk renaming, file cleanup, content-based organization, folder restructuring, collecting files by topic or purpose (e.g., "gather resume-related files", "gather dataset files", "identify disposable files"), or filtering and grouping files by category.
Prepares a Claude Code session for compaction. Reads the session and prints ready-to-paste blocks: a /compact line with focus instructions tailored to this session, and a resume prompt for right after the compact or for a fresh session. Writes nothing to disk by default; `handoff` also saves the resume prompt to one file outside the project. Works in any language: everything the user sees comes back in the language of their messages. Use when the context is filling up or right before running /compact. Triggers: "prep me for compact", "prepare for compact", "before I compact", "ready to compact", "context is almost full", "the chat is getting long", "prompt to continue after compacting", "/smart-precompact", "תכין אותי לקומפאקט", "תכין לקומפאקט", "צריך לעשות קומפאקט", "לפני קומפאקט", "אחרי הקומפאקט", "הקונטקסט מתמלא", "השיחה ארוכה מדי". Also runs when the context hook (smart-precompact) adds a note that the context passed a threshold: answer the user first, then run with `handoff`. NOT for saving notes or memories when no compaction is in play, and NOT for shortening or compressing text, titles or files.
Strategic sourcing playbook for hiring great designers OR getting hired as a designer. Based on Soleio's framework. Two modes: Hiring Mode (for founders, hiring managers, recruiters sourcing design talent) and Designer Mode (for designers positioning themselves to get hired by great companies). Triggers on: hire designer, source designer, find designer, recruit designer, design talent, get hired as designer, designer job search, designer positioning.
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.