Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Triages production alerts using observability signal. Mode A gathers confirmed-vs-inferred context for a single alert or ticket and updates the tracker; Mode B fans out over alerts that fired in a window, suppresses muted and unrouted noise, dedupes via a stable fingerprint, and files or updates issues idempotently. Correlates alerts to recent changes through the O11y Change Context manifest. Use when investigating an alert or incident, or running scheduled oncall triage.
Workflow for optimizing ClickHouse and HogQL queries. Use when a HogQL query, query runner, insight, or report is too slow; when a hand-written ClickHouse query (via `sync_execute` or in a migration) is too slow; when ClickHouse times out or hits memory limits; when investigating a slow `system.query_log` row; or when reviewing a proposed HogQL printer change for performance. Covers extracting the ClickHouse SQL, common smells (`FROM ... FINAL`, `JSONExtract` over properties, missing skip indexes, self-joins, CTE blow-up), measuring against a real cluster, and applying the fix at the right layer (printer, query runner, or migration). Does NOT cover Postgres / Django ORM / app-database queries; for those use `profiling-slow-api-endpoints`.
Build and render a papercut episode from a storyboard with the library. Scaffolds the project, builds scenes with parallel agents, assets and audio, renders the mp4, then harvests reusables. Use for "build the reel", "scaffold an episode", "rebuild scene 4", "render it"
Semantically rename Penpot layers to HTML element names (nav, header, main, section, article, button, input, label, h1-h6, p, ul, li, img) or kebab-case role names, replacing auto-generated names like 'Rectangle 12'. Use to clean up layer naming, prepare a file for handoff, or as a precondition for accessibility audits (heading hierarchy) and design-to-code review (semantic mapping). Triggers: 'rename layers', 'semantic layer names', 'rename to HTML elements', 'clean up layer names', 'fix layer naming', 'add semantic names to layers', 'prepare layers for handoff'.
Every Instagram Business metric across all your brand accounts Trigger phrases: `compare my instagram brands`, `instagram follower growth`, `best time to post on instagram`, `top instagram posts this month`, `instagram competitor analytics`, `use instagram-pp-cli`, `run instagram analytics`.
Every Twilio Core feature, plus offline message and call history, FTS, and SQL-grade analytics no other Twilio tool... Trigger phrases: `send an SMS via Twilio`, `list Twilio messages`, `Twilio call recordings`, `Twilio usage cost`, `Twilio opt-out audit`, `use twilio`, `run twilio`
Professional full-pipeline AI assistant for generating PPT presentations. It simulates the complete workflow of a top-tier PPT design agency (requirements research -> material gathering -> outline planning -> planning draft -> design draft) and outputs high-quality HTML-format presentations. Trigger this skill when the user mentions making a PPT, creating a presentation, making slides, making a slide deck, creating report materials, creating training courseware, making a pitch deck, or making a product introduction page. It should also trigger even if the user only says "help me make an introduction about X" or "I want to report Y to my boss", as long as structured multi-page presentation content is implied. It also applies when the user says "help me turn this document into a PPT" or "turn this topic into a presentation" and other scenarios that require converting content into a presentation format.
Generate a conventionally-named branch and PR title from a feature description. Use when the user is starting a new branch, opening a PR, or asks how to name a branch or PR. Triggers on phrases like "create a branch", "name this branch", "open a PR", "what should I call this branch", "PR title for this".
Prisma ORM integration patterns with NestJS for production applications. Use PROACTIVELY when working with Prisma schemas, migrations, PrismaService, atomic transactions (including SELECT FOR UPDATE), repositories as infrastructure adapters in Clean Architecture, optimized queries (N+1, includes, pagination), seeds, and testing with Prisma Mock. Always activate when these keywords appear: Prisma, PrismaService, prisma.$transaction, prisma migrate, schema.prisma, PrismaClient, Prisma.validator, include/select, upsert, createMany, or any database operation with Prisma in a NestJS project.
Get PostHog data into a canvas correctly: the host-injected `ph` SDK (loadInsight, query, capture, state, connectors, openExternal, navigate), the data hierarchy (saved insights first, typed query nodes second, inline HogQL last), verifiability (insight-backed metrics link their saved insight in PostHog; ad-hoc queries expose the exact query that ran), per-insight-type result shapes, progressive per-query loading, date-range wiring, live third-party data through the viewer's own connections (ph.connectors), and event capture from a canvas. Use whenever a canvas shows metrics, charts, tables, any PostHog data, or data from GitHub or an MCP server, or needs to send analytics events.
Design and review production-grade low-latency VisionCamera v5 pipelines. Use for real-time GPU, ML, CV, Skia or WebGPU overlays, Nitro frame plugins, zero-copy interop, frame budgets, and latency profiling. Use the general react-native-vision-camera skill for setup, capture, controls, basic frame outputs, or v4 migration.
React 19 performance optimization guidelines for concurrent rendering, Server Components, actions, hooks, and memoization (formerly react-19). This skill should be used when writing React 19 components, using concurrent features, or optimizing re-renders. This skill does NOT cover Next.js-specific features like App Router, next.config.js, or Next.js caching (use nextjs-16-app-router skill). For client-side form validation with React Hook Form, use react-hook-form skill.
Work with Resumx, a Markdown-to-PDF resume renderer. Use when creating, editing, converting, building, styling, or tailoring resumes. Covers syntax, CLI, style options, icons, tags, views, variables, multi-language, page fitting, validation, custom CSS, and AI-assisted resume writing.
Provisions a Replay Vision `experiment` scanner that watches one experiment’s exposed sessions, records each session’s variant, samples variants evenly, and stops when the experiment ends. Covers status guards, a prompt that remains comparable across variants, sizing credit spend against the experiment’s own population, creating it disabled so its prompt can be previewed on real sessions, and reading results by variant. TRIGGER when: the user wants Replay Vision to watch an experiment, asks to scan or analyze an experiment’s recordings with AI, asks “what are users actually doing in the test variant,” or wants a scanner scoped to an experiment’s exposed sessions. DO NOT TRIGGER when: creating a general-purpose scanner not tied to an experiment (use creating-replay-vision-scanners), reading observations a scanner already produced (use exploring-replay-vision-observations), or manually browsing an experiment’s recordings without AI analysis (use analyzing-experiment-session-replays).
With the explicit OK of whoever is using the computer, installs a commit alarm (git pre-commit hook) that refuses the commit when it finds a CPF or CNPJ with a valid check digit, a passwords file (.env), a certificate with a private key (.pfx, .p12, .pem), or a new spreadsheet, explains why and how to fix it, cites git commit --no-verify, and says how to uninstall. Use when the user wants to protect the repository against customer data or an A1 certificate going into git, when preparing the office machine to work with SDD, or when a commit is refused by this alarm. Does not apply to deadlines (it neither consults the norm nor calculates). It does not fix git history, does not revoke a certificate, does not read a .xlsx spreadsheet internally, and does not give an opinion on LGPD or professional secrecy; to diagnose the environment without installing anything, use sdd-checar-ambiente.
Default search tool for all search and lookup needs. A multi-source search and deduplication layer with intent-aware scoring. Integrates Brave Search (web_search), Exa, Tavily, and Grok for high-coverage, high-quality results. Automatically classifies query intent and adjusts search strategy, scoring weights, and result synthesis. Use for any query requiring web search, including factual lookups, research, news, comparisons, resource finding, “what is X,” and status checks. Do not use raw web_search directly; always route through this skill.
Direct ByteDance Dreamina Seedance 2.0 Standard, Fast, and Mini video production across BytePlus ModelArk and verified gateways. Use for text/image/reference-to-video, native synchronized audio and dialogue, multimodal image-video-audio reference, first/last-frame animation, video editing or extension, model/gateway selection, prompt construction, async task handling, failure recovery, QA, and rights-safe production.
Populate person or group properties from a data warehouse table or materialized view, so warehouse columns become properties usable in feature flags, cohorts, and insights. Use when the user wants to "sync my Postgres columns to person properties", "map a warehouse table to people", "replace our daily identify cron", "update person properties from the warehouse", or asks for reverse ETL into PostHog. Covers picking the table and the identifier column, proposing a whole-table column mapping in one call, excluding identity and reserved properties, checking collisions with properties that already exist, and running the first backfill.
Shark UI skill for the Ark UI–based shadcn-style registry. Use when implementing or debugging components (overlays, menus, popovers, sheets, dialogs), collection-driven controls (combobox, select, list patterns), Field/forms, sidebar or chart docs patterns, Tailwind v4 tokens, or migrating Radix/shadcn examples to Shark. Also applies when using the shadcn CLI with `@shark/*`, `components.json`, or registry-style add/search/diff workflows.
Route coding-agent skill work between the public and private source repositories. Use when an installed skill change vanished, when adding, editing, renaming, splitting, or removing a skill, or when authoring its behavior evaluation cases
Apply Python development policy using uv-first execution, test-first behavior validation, and pre-commit quality gates. Use when implementing or refactoring Python code, when `uv.lock` changes unexpectedly on `uv run` or `uv sync`, when a lockfile carries an `[options]` block the project does not declare, or when uv prints `Resolving despite existing lockfile`.
Authors and structures professional-grade agent skills following the agentskills.io spec. Use when creating new skill directories, drafting procedural instructions, or optimizing metadata for discoverability. Don't use for general documentation, non-agentic library code, or README files.
Search, evaluate, and recommend agent skills from the skills.sh directory. Use when: (1) user asks to find/search a skill for X, (2) "есть скилл для...", (3) "skill for zoom/notion/stripe/...", (4) "поищи на skills.sh", (5) "нужен плагин/расширение/скилл для...", (6) "как подключить X к Claude Code", (7) any mention of skills.sh, (8) "найди скилл", (9) "find skill", (10) user shares a skills.sh link for review.
SkillOpt-flavored offline training loop for any SKILL.md. Treats accumulated learn-rule corrections as training trajectories, proposes bounded patches via an optimizer LLM, gates each candidate against a held-out validation set built from the user's own past corrections, and ships only candidates that demonstrably improve the score. Inspired by Microsoft SkillOpt's ReflACT pipeline (rollout → reflect → aggregate → select → update → evaluate) adapted to pro-workflow's SQLite store. Use when a skill has accumulated 8+ learn-rule rows and the user wants the skill itself to get better, not just longer.
Platform-specific organic social media strategy, content calendars, engagement tactics, community building, and performance measurement. Use when the user asks about social media strategy, organic social, content calendars, community management, or social media metrics.
Interactive ad-hoc Spark analysis through Fabric Lakehouse Livy API sessions ONLY. This skill NEVER authors or runs a notebook: any notebook cell (%%sql/%%configure) or a notebook-run-by-name (and reporting its run status) is `spark-authoring-cli`, not this skill. Scope: create a Livy session, execute PySpark, inspect output, and compute quick calculations over lakehouse data (DataFrames, cross-lakehouse joins, Delta time-travel, unstructured/JSON). For Spark failure triage use `spark-operations-cli`; for plain T-SQL Lakehouse/Warehouse queries use `sqldw-consumption-cli`. Triggers: "create Livy session", "run Livy calculation", "Livy session calculation", "interactive Livy session", "PySpark", "analyze with PySpark", "Spark DataFrame", "lakehouse with Python", "PySpark data quality", "Delta time-travel with Spark", "join tables across Lakehouses"
Administer Debian servers for applications and clusters with APT, systemd, SSH, nftables, sysctl, storage, users, updates, and Docker Engine. Use to prepare, review, or diagnose the host; use Ansible to automate state and Docker Swarm for cluster services.
Complete Java Spring Boot skill set for building enterprise applications. Includes modular architecture with optional components: PostgreSQL database with JPA/Hibernate + Flyway migration; Redis caching (optional); Kafka/RabbitMQ messaging (optional, choose one); JWT + OAuth2 authentication (OAuth2 optional); RBAC authorization (optional); TDD with Mockito; Spec-First Development with OpenSpec.
Generate SQL queries from natural-language requirements using SELECT, JOIN, GROUP BY, window functions, CTEs, and subqueries. Use when the user needs a new query from a business question or schema; use query-optimization when an existing query or execution plan is slow.
Use this skill when users need to define their ideal customer profile, identify target personas, map buying centers, or understand who they're selling to. Activates for "who is my customer," "define ICP," "target audience," or persona questions
Runs and reasons about the automated AI health check that suggests path-cleaning rules for web-analytics teams. Use when asked to generate path-cleaning suggestions for a team or cohort, to run the suggestion check, to review/apply AI-suggested rules, to inspect path_cleaning_suggestions health issues, or to extend the suggestion pipeline. Covers the suggest_path_cleaning_rules management command, the path_cleaning_suggestions health check, the cohort gating (precompute teams), and how suggestions are validated against real paths before storage. For hand-authoring or applying rules directly, use managing-path-cleaning-rules instead.
Migrating from Ethereum/EVM/Solidity to Sui Move. Use when the user is an Ethereum developer learning Sui, comparing Solidity patterns to Move equivalents, asking about differences between EVM and MoveVM, mapping Ethereum token standards to Sui standards, or translating access control, state storage, contract upgrade, or composability patterns from Ethereum to Sui.
Analyzes code to identify untested functions, low coverage areas, and missing edge cases. Use when reviewing test coverage or planning test improvements. Generates specific test suggestions with example templates following amplihack's testing pyramid (60% unit, 30% integration, 10% E2E). Can use coverage.py for Python projects.
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.