Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Establishes how to reach ClickHouse (MCP tool or clickhouse-client), the cluster name for clusterAllReplicas('{cluster}', ...) query packs, the default 24-hour time window, and the shared report header. Use first, before any other altinity-expert-clickhouse skill.
TypeScript / Python reference for the Claude Agent SDK (code.claude.com/docs/en/agent-sdk). Covers query(), ClaudeAgentOptions / Options, fallbackModel, maxTurns, maxBudgetUsd, custom tools (in-process MCP), createSdkMcpServer, hooks, permissions (canUseTool), subagents, sessions (resume / fork), streaming, structured outputs, Agent Skills (SKILL.md), slash commands (/compact, /clear), tool search, hosting / observability.
Generate API documentation by scanning Controller classes, extracting endpoint URLs, HTTP methods, parameters, and response structures, then producing standardized docs from templates. Use when the user explicitly mentions generating API documentation, creating API docs, scanning interfaces, or documenting REST APIs. Do not trigger for generic documentation requests without explicit API mention.
Use to implement fixes, add evidence, and unblock items in a UI acceptance report; not for an initial UI review, independent scoring, handling code review, or UI development without a report. Verify gaps, fix the UI, complete the environment and test evidence, share evidence for the same status, document the work, and return it for review.
App Store review readiness audit for iOS apps. Scans the codebase, entitlements, Info.plist, privacy manifests, paywall/subscription UI, and metadata for anything that could trigger a warning or rejection during App Store review. Invoke explicitly when preparing a submission. Do NOT trigger automatically.
Build portable, first-person colored ASCII city engines and small GIS-derived city packs. Use when designing terrain-following walking, raycast character rendering, city-provider schemas, or reproducible public-GIS ingestion. Do not use for conventional 3D/WebGL games, multi-level interiors, general GIS analysis, or committing full-resolution GIS archives.
Core Python library for astronomy/astrophysics: units with dimensional analysis, celestial coordinate transforms (ICRS/Galactic/AltAz/FK5), FITS I/O, tables (FITS/HDF5/VOTable/CSV), cosmology (Planck18, distance/age), precise time (UTC/TAI/TT/TDB, Julian, barycentric), WCS pixel-world mapping, model fitting. For general tables use pandas/polars; for radio interferometry use CASA.
Interact with Atlassian Jira and Confluence using REST APIs — no MCP server needed. Use this skill whenever the user mentions Jira, Confluence, Atlassian, tickets, issues, sprints, backlogs, epics, stories, or any project management task that involves creating/editing/searching/transitioning Jira issues, writing or reading Confluence pages, generating status reports, triaging bugs, converting specs to backlogs, capturing tasks from meeting notes, searching company knowledge, syncing local BMAD documents with Jira or Confluence, pushing docs to Jira, pulling from Jira, linking documents to tickets, downloading Confluence spaces to local markdown, or converting between Confluence storage format and markdown. Also trigger when the user says things like "move that ticket to done", "what's the status of PROJ-123", "create a bug for X", "search our wiki for Y", "file a ticket", "check for duplicates", "write a status update", "break this spec into stories", "sync this doc", "push to jira", "pull from jira", "sync to confluence", "link this to jira", "sync my epics", "download confluence pages", "sync confluence space", "convert confluence to markdown", or "pull docs from confluence". If there is even a chance the user wants to interact with Jira or Confluence, use this skill.
Performs an Azure security posture review against the CIS Microsoft Azure Foundations Benchmark v2.1.0. Auto-invoked when reviewing Azure infrastructure, Entra ID configurations, NSG rules, Defender for Cloud settings, or Key Vault access policies. Walks through all nine benchmark sections, evaluates each recommendation, and produces a prioritized findings report with remediation guidance mapped to specific CIS control IDs.
Baidu email assistant that reads, sends, and manages mail in Baidu enterprise mailboxes. It helps you manage Baidu enterprise mailboxes in natural language, supporting sending and receiving mail, viewing unread messages, managing folders, and more. When the user mentions things like "so-and-so is my leader/boss/supervisor", "remember so-and-so's email", "so-and-so needs special attention", or "record important contacts" — i.e. contact preference settings — use this skill's MEMORY.md to record that information.
AI charting and comprehensive analysis for BaZi and Zi Wei Dou Shu. Use when the user provides birth details (solar/lunar date, hour, gender) and asks about BaZi, Zi Wei, fate analysis, natal charts, or annual and major luck cycles. Produces accurate charts based on the Yiqi algorithm library plus the enrichBazi completion layer (avoiding LLM charting errors), and supports on-demand standalone BaZi analysis, standalone Zi Wei analysis, or cross-verification of both charts.
Color systems for digital products, from building and naming a palette to applying it with meaning and verifying contrast. Use when creating or extending a color palette, naming color tokens, theming light and dark appearances, auditing the colors in a codebase, or reviewing frontend code for color. Triggers on color palette, palette generation, color scale, color ramp, brand color, accent color, neutral palette, gray palette, status colors, design tokens, semantic color tokens, token naming, theming, dark mode colors, contrast ratio, APCA, gamut, display p3, oklch, color conversion, gradients, color meaning, increased contrast.
Extract, suggest, and sync tags and categories for blog posts across all major CMS platforms. Supports WordPress REST API, Shopify GraphQL, Ghost Content API, Strapi REST/GraphQL, and Sanity GROQ. Generates tag suggestions from content analysis (keyword frequency, heading extraction, semantic grouping), enforces minimum post-count thresholds to prevent thin tag archives, and syncs taxonomy via authenticated API calls. Use when user says "tags", "categories", "taxonomy", "tag suggestions", "sync tags", "WordPress tags", "Shopify tags".
Turns a sequential, ready-for-dev story backlog into conflict-free CONCURRENT WAVES. Builds a dependency DAG from epic order, per-story dependency maps, and Owned File/Module Scope overlaps, then topologically sorts it into parallel waves of mutually disjoint, dependency-satisfied stories (capped by maxParallel), and emits a parallelization-plan.md with per-story git-worktree branch names and an ordered merge sequence. Use when the user says "plan parallel work", "which stories can run in parallel", "parallelize the backlog", "build the wave plan", "parallelization plan", "conflict-free workstreams", "what can we run concurrently", "split into worktrees", "dependency graph for the stories", "merge order", or "how do I fan this backlog out to multiple dev agents". Run AFTER stories are ready-for-dev (scrum-master) and an architecture exists. This skill PLANS parallelism only — it does NOT run agents, spawn worktrees, write code, run tests, or perform git operations.
This skill should be used when the user asks about Bootstrap grid system, Bootstrap containers, Bootstrap breakpoints, Bootstrap columns, Bootstrap rows, Bootstrap gutters, Bootstrap responsive layout, Bootstrap CSS Grid, Bootstrap z-index, Bootstrap row-cols, Bootstrap offset classes, Bootstrap column ordering, how to create responsive layouts with Bootstrap, how to use Bootstrap grid, Bootstrap column sizing, Bootstrap auto-layout columns, or needs help with Bootstrap page layout and responsiveness.
Use when the user says 'extract my brand voice', 'what is my writing style', or 'analyze my tone', or before any skill that writes copy for the site. Reads 5-10 published posts and persists tone, lexicon, sentence patterns, formality, signature phrases, and phrases the site never uses.
write, review, and improve bruno api tests, assertions, pre-request scripts, post-response scripts, request chaining, schema checks, response visualizers, and edge-case coverage. use when working with bruno collections, opencollection yaml, .bru files, bruno runtime scripts, chai expect tests, request variables, environment variables, response validation, or api regression testing.
AI-powered generation of complete trading strategy code. Uses create_strategy and create_prediction_market_strategy to transform requirements into production-ready Python code. Most expensive AI tool ($1.00-$4.50 per generation). Generates complete Jesse framework strategies with entry/exit logic, position sizing, and risk management. Use after exploring data and optionally generating ideas. ALWAYS test with test-trading-strategies before deploying.
Builds and manages open source Python library communities including CONTRIBUTING.md, CODE_OF_CONDUCT.md, issue/PR templates, contributor recognition, and GitHub automation. Use when setting up community infrastructure, improving contributor experience, or managing project governance.
Use to close the loop on agent quality — turn a failure signal into a verified fix. Triggers: "improve my agent", "self-improving agent", "auto-tune / iterate on my prompt", "fix my agent from test results" — and production-call bug fixing: "fix this prod call issue", "debug and fix call ID", "reproduce this production bug", "regression test before raising PR". Works on any stack: provider-dashboard agents (VAPI, Retell, ElevenLabs, Bland) AND agents whose config lives in the customer's own repo, database, or prompt registry with the provider agent created at deploy time, or with custom mock servers. Fixed safety invariants (must-fail-first reproduction, attestation, no-prod-in-loop) + a per-project capability manifest declaring where config lives and how to read/render/apply/deploy/verify it.
Use when the user explicitly asks to "check/optimize the in-text citations of the review `{topic}_review.tex`" or to "run check-review-alignment". Checks citation by citation, via the host AI's semantic understanding, whether the citations match the content of the referenced literature; only when a fatal citation error is found does it minimally rewrite the "sentence containing the citation", and it reuses the rendering scripts of `systematic-literature-review` to output PDF/Word. Core principle: do not change things just for the sake of changing; when it cannot be determined whether an error is fatal, keep the original and flag it in the report. Not applicable: the user merely wants to generate a systematic review body (use systematic-literature-review); the user merely wants to add/verify BibTeX entries (use a dedicated bib management workflow).
Manage dotfiles and secrets with chezmoi. Use for initializing chezmoi, adding/editing configuration files, creating templates for multi-machine setups, encrypting sensitive files, integrating password managers (1Password, Bitwarden, pass, etc.), running scripts during apply, and syncing dotfiles across machines. Triggers on dotfile management, chezmoi commands, configuration templating, or secrets in config files.
A skill for lowering AIGC detection rates in Chinese academic papers. Targeting the detection mechanisms of CNKI, Wanfang, VIP, and Turnitin Chinese editions, it identifies and eliminates 17 categories of structured writing traces of Chinese large language models. It uses a five-step closed-loop workflow of "locate → diagnose → rewrite → self-assess → recheck", with differentiated strategies per section (abstract/introduction/literature review/methods/results/discussion/conclusion), passing detection while maintaining academic rigor.
Generate images, videos, audio, and more using Civitai's orchestration API. Use when the user wants text-to-image, video generation (11+ engines), text-to-speech, music, transcription, bulk batches, experiment sweeps, or buzz cost estimation. Not for browsing or searching Civitai models (use the Civitai MCP server).
Upgrade marketing, content, SEO/AEO/GEO, and revenue skills so changes are judged by platform analytics instead of vibes. Use when applying closed-loop learning to X, YouTube, SEO, AEO/GEO, outbound, paid creative, or revenue workflows.
Provides comprehensive guidance for Alibaba Cloud OSS including bucket creation, object storage, access control, and OSS management. Use when the user asks about Alibaba Cloud OSS, needs to store files in OSS, configure OSS buckets, or work with Alibaba Cloud storage.
Deploy and manage Cloudflare Workers, Pages, and services via Code Mode MCP (API queries) + wrangler (deploys). OAuth auth for wrangler (tokens lack Pages perms). USE WHEN Cloudflare, worker, deploy, Pages, MCP server, wrangler, DNS, KV, R2, D1, Vectorize.
Use when co-authoring documentation with users through a structured workflow. Triggers include requests to write documentation, proposals, technical specs, decision docs, RFCs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers.
Use when the user asks about code health, code quality, complexity, technical debt, which files are risky or hard to maintain, what to refactor next, untested hotspots, or coverage gaps in a Repowise-indexed codebase (.repowise/ directory exists). Also use to get a before/after health read when planning or finishing a refactor.
Explore and understand codebases using SocratiCode semantic search, dependency graphs, and context artifacts. Use when exploring code, understanding architecture, finding functions/types, analysing dependencies, searching database schemas or API specs, or when socraticode/codebase_search tools are available. Activates when the user asks about code structure, wants to find where a feature lives, or needs to understand how code is organised.
Delegate browser/UI verification and computer-use tasks to Codex — launching the app, clicking through flows, verifying UI/UX changes visually. Use when a change needs to be seen working in a real browser and screenshots would burn main-loop tokens.
Skill for analysing and drafting contracts under Polish law, with particular focus on B2B, IP and IT contracts (body leasing, NDAs, implementations, SaaS, copyright transfer, settlements). Created at Kancelaria Radców Prawnych Żurawska Piotrowski i Wspólnicy (ktzr.pl). Always use when the user asks to analyse a Polish contract, audit contractual risks, generate a new contract in the KTZR style, add/edit a clause, check contract consistency, or pastes/attaches a Polish contract document for review. Also use when the terms "Złote Reguły KTZR", "essentialia negotii", "baza klauzul KTZR" appear, or when the user mentions the KTZR law firm / their own law firm.
Use this skill to find, verify, classify, and rank direct, adjacent, and tangential competitors from public web evidence. Trigger it when entering a market, building a competitor set, validating perceived alternatives, or refreshing research after a pivot.
Handles Tambo component streaming, loading states, and persistent state. Use when implementing streaming UI feedback, tracking prop streaming status, managing partial props, or persisting component state across sessions with useTamboStreamStatus or useTamboComponentState.
Load this skill whenever building, editing, or deploying a Goldsky Compose app — it is the reference layer that gives the concrete rules for how to build one: the exact shape of compose.yaml (every top-level, task, and trigger field), every `goldsky compose` CLI flag, the TaskContext API (env, fetch, callTask, logEvent, evm, collection), wallet APIs (smart wallet, BYO EOA), gas sponsorship, contract codegen, the dashboard URL, and pricing. Consult it before writing or editing any compose.yaml or task file — do not synthesize the manifest/CLI/API shape from memory — and also to answer any user question about how Compose works or what a field, flag, or API does. Pairs with /compose (the entry-point build guide, loaded first); use /compose-doctor to debug a broken app. Do NOT load for Turbo, Mirror, Subgraphs, Edge, or Boost — those have their own reference skills.
Guide recurring human-relationship practices — success plans, health evidence, renewal and expansion signals, QBRs, handoffs, escalation, and closed-loop Voice of Customer. Do not use this skill for products without accounts, renewals, QBRs, or a customer-success team, including some internal tools, pure transactional products without recurring relationships, and public services without account-based engagement. Load only when the product context includes a recurring human relationship; decline or route away otherwise.
Provides structured incident containment strategies mapped to NIST SP 800-61 Rev 2 and MITRE ATT&CK techniques. Auto-invoked when a confirmed incident requires isolation decisions, credential revocation, network segmentation, or DNS sinkholing. Produces a containment plan with short-term and long-term actions, business impact assessment, and ATT&CK-mapped countermeasures.
contract-cli field configuration lookup skill: query the field configuration definitions of vendor, legal_entity, and vendor_risk. Triggered when the user wants to confirm the master data field structure with `contract-cli mdm fields list`. The bot identity currently supports only vendor/legalEntity.
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.