Skills
99,064 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Routes to the correct Hookdeck product skill. Covers Event Gateway (inbound: receive webhooks, webhook endpoints, local dev, event queue), Outpost (outbound: send webhooks to customers), and Inspect (free webhook test URLs with no account: see what a webhook sent). Use when working with any Hookdeck product and unsure which skill to use
**REQUIRED** - Always activate FIRST on any git/VCS operations (commit, status, branch, push, etc.), especially when HEAD is detached. If `.jj/` exists -> this is a Jujutsu (jj) repo - raw git commands can corrupt data. Essential git safety instructions inside. DO NOT IGNORE.
Write, edit, and review MaaFramework interface.json (Project Interface V2) — task entry declarations, controller/resource configuration, GUI option wiring (pipeline_override and override order), presets, pretask startup tasks, agent child process configuration, import splitting, and structure troubleshooting. Use when creating, editing, or reviewing an interface.json for a MaaFW project, adding user-facing options or presets, wiring pipeline_override, configuring pretask or agent child processes, splitting interface files via import, or diagnosing interface structure errors.
Install missing language runtimes and dev tools via mise. Use when (1) a command fails due to missing runtime (e.g. node not found, python3 not found, go command not found), (2) user asks to install/setup a language runtime or SDK (node, python, go, rust, java, ruby, etc.), (3) user mentions version management for languages, or (4) setting up a new development environment.
Compatibility guide for developers moving from MySQL to MariaDB, and for developers with MySQL experience working with MariaDB. Use when migrating a MySQL application to MariaDB, when MySQL syntax or habits cause unexpected behavior in MariaDB, when asking about MySQL/MariaDB compatibility, or when adapting code written for MySQL to run on MariaDB. IMPORTANT — MariaDB diverges significantly from MySQL 8.0 and is not a simple drop-in replacement for modern MySQL. Authentication plugins, JSON handling, GTID replication, and several SQL features differ in important ways.
Expert in Natural Language Processing, designing systems for text classification, NER, translation, and LLM integration using Hugging Face, spaCy, and LangChain. Use when building NLP pipelines, text analysis, or LLM-powered features. Triggers include "NLP", "text classification", "NER", "named entity", "sentiment analysis", "spaCy", "Hugging Face", "transformers"
Use when implementing paginated lists in Android or Compose with Paging 3 — PagingSource, Pager and PagingConfig setup, RemoteMediator for offline-first lists, LazyPagingItems and itemKey integration in LazyColumn, dynamic filters via flatMapLatest, and unit tests with TestPager and asSnapshot. Triggers include Paging 3, infinite list, infinite scroll, paginated list, LazyPagingItems, collectAsLazyPagingItems, and cachedIn.
Receive and verify PayPal webhooks. Use when setting up PayPal webhook handlers, debugging certificate-based signature verification, or handling payment events like PAYMENT.CAPTURE.COMPLETED, PAYMENT.SALE.COMPLETED, BILLING.SUBSCRIPTION.CREATED, or CHECKOUT.ORDER.APPROVED.
Owns Python code style for this stack: ruff for lint + format, numpydoc for docstrings. Three responsibilities — (1) place the project's `ruff.toml` from the bundled template once the stack and workspace are in place, (2) run ruff against any Python files Claude has just generated or edited, and (3) contextualize each touched file's comments to the data-science problem — rewriting any leftover template / workflow prose (skill names, gates, runner, digest, guard-rails) into concise, problem-specific docs so the user's committed files read like a colleague wrote them, not like a generated scaffold. Stops at "the touched files pass `ruff check` and document the problem, not the process." TRIGGER when (any of these): (1) a Python file was just created or edited via Write / Edit / MultiEdit — invoke this skill before declaring the task done so ruff is run AND the file's comments are contextualized to the problem; (2) a fresh ML workspace was just scaffolded by `organize-ml-workspace` and the project has no `ruff.toml` at its root yet — drop the bundled template; (3) the user asks about lint, format, docstring style, or reaches for `black` / `isort` / `flake8` / `pydocstyle` (redirect to ruff — the stack's canonical linter, owned by `data-science-python-stack` Tier 1). SKIP when: the project is non-Python; the only edits in this turn are to Markdown / TOML / JSON / YAML; the file lives in a third-party vendored directory the user doesn't own. HOW TO USE: run ruff manually on the files you just touched — do not configure a PostToolUse hook for this. **Read the "Stop conditions" block and emit the Pre-flight checklist as visible text in your response — both are mandatory before running ruff.**
Read GitHub repos the right way — via gitmcp.io instead of raw scraping. Why this beats web search: (1) Semantic search across docs, not just keyword matching, (2) Smart code navigation with accurate file structure — zero hallucinations on repo layout, (3) Proper markdown output optimized for LLMs, not raw HTML/JSON garbage, (4) Aggregates README + /docs + code in one clean interface, (5) Respects rate limits and robots.txt. Stop pasting raw GitHub URLs — use this instead.
Provides comprehensive guidance for Redux state management including stores, actions, reducers, middleware, selectors, and Redux Toolkit. Use when the user asks about Redux, needs to manage global state, implement Redux patterns, or work with Redux middleware.
Ship a release: the final pre-tag gate for OrchestKit itself, run once a change is already known good. Walks 12 ordered steps (build, full test suite, security tests, typecheck, manifest count validation, changelog entry, version bump across package.json and CLAUDE.md, selective staging, conventional release commit, tag, confirmed push), halting at the first failed step with remediation guidance. Use when cutting and shipping a version, not for judging whether a change is correct (that is /ork:verify).
Design Roblox admin tools and observability systems. Use for safe grant/revoke tools, moderation commands, audit logs, live diagnostics, economy inspection, player support, operational dashboards, and abuse-resistant admin workflows.
Write and change Rust the way THIS workspace already does it, NOT by generic defaults — a systems-programming reference carrying the real crate boundaries, error model, and conventions for storage engines, binary formats, Arrow/DataFusion, search and vector indexing, async concurrency, testing, and unsafe discipline, so a change lands idiomatic and review-ready instead of merely compiling. Use when a task touches this workspace's Rust crates and should follow its systems-level conventions rather than boilerplate.
Use when you have a security finding (from code audit or pentest) and need to fix it correctly with secure-coding patterns, then verify the fix actually closes it. Covers fixes for injection, access control, XSS, auth, secrets, and config across the stack.
Triage and remediate vulnerabilities found by a Strix pentest (open-source CLI or app.strix.ai cloud), then re-run Strix to verify each fix. Use after a Strix scan reports findings, or when the user asks to fix security issues from a strix_runs report, vulnerabilities.json, findings.sarif, or a cloud scan's vulnerabilities.
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).
Initializes an AI development session by reading workflow guides, developer identity, git status, active tasks, and project guidelines from .trellis/. Classifies incoming tasks and routes to brainstorm, direct edit, or task workflow. Use when beginning a new coding session, resuming work, starting a new task, or re-establishing project context.
Generate or update Claude Code settings from the project's REAL stack, not a generic allowlist — `.claude/settings.local.json`, `.claude/settings.json`, and `.mcp.json`. Detects the real toolchain and frameworks from lock files and manifests, diffs that against current settings, and proposes only the command permissions, doc domains, and MCP integrations the detected tools justify. User-only maintenance workflow that mutates durable config: every entry is EVIDENCE-driven (detected tools only), destructive, absolute, and user-specific paths are excluded, existing customizations are preserved, and nothing is written without explicit approval. Use to audit or refresh Claude settings for the current repo.
Call POST /chat/completions on Venice. Covers the OpenAI-compatible request shape, Venice-only venice_parameters (web search, scraping, citations, E2EE, characters, thinking control, X search), anon_user_id, multimodal inputs (images/audio/video/files), tool calls, reasoning controls (reasoning_effort, reasoning.enabled), streaming, prompt caching, structured output, per-model caps, and model feature suffixes.
Use Venice as a pay-per-call JSON-RPC proxy to 27 EVM, Starknet, and Solana networks. Covers the public GET /crypto/rpc/networks, POST /crypto/rpc/{network}, chain families and their explicit per-family method allowlists, the 1×/2×/4× method-tier pricing model (~$7e-7 per credit), the per-minute rate limit and per-user request serialization, idempotency keys for safe retries, single vs batch (≤100) requests, and the unsupported stateful/WebSocket methods (eth_subscribe, eth_newFilter, *Subscribe, etc.).
Use when the user asks to commit, stage, or "save" agent-assisted coding changes — including vague requests like "commit this", "commit please", "コミットして", or "/commit" — and the real work is deciding which files belong in the commit, excluding unwanted or generated files, splitting unrelated changes, or fixing a commit's file set, multi-line message transport, history (amend/rebase), or authorship trailers. This skill owns commit execution, message transport, and git safety.
Reviews watchOS code for app lifecycle, complications (ClockKit/WidgetKit), WatchConnectivity, and performance constraints. Use when reviewing code with import WatchKit, WKExtension, WKApplicationDelegate, WCSession, or watchOS-specific patterns.
Write, audit, or improve AGENTS.md — the tool-agnostic context file for coding agents — plus harness adapters (CLAUDE.md, .cursorrules, GEMINI.md, Copilot instructions). Use when creating one from scratch, auditing for bloat or anti-patterns, consolidating multiple tool files into one source of truth, or applying progressive disclosure.
Use when improving or comparing Ultralytics YOLO models in Platform or code, or running hyperparameter search/autotraining — Platform experiment comparison, the systematic improvement playbook, model.tune() genetic evolution, Ray Tune, search spaces, and deciding whether tuning is worthwhile. For one training run and its arguments, see yolo-training.
Use when upgrading an iOS or macOS app's Auth0.swift SDK from v2 to v3. Detects the current version, fetches the new SDK source to confirm API signatures, and applies only the breaking changes that affect real call sites — use even if the user says "update my Auth0 Swift SDK" or "migrate to Auth0.swift v3".
Use when adding or changing a Bagisto import — an Importer class, a file source, the importers registry, the queued import pipeline, or a stuck or failing import job. Trigger phrases include "import", "importer", "data transfer", "CSV", "XLSX", "XML", "bulk upload", "import batch", "queued import", "validate rows".
Use when building or changing a Bagisto admin listing page — a DataGrid class with columns, search, filters, sorting, row actions, mass actions or export, and the controller and Blade view that render it. Trigger phrases include "datagrid", "admin listing", "add a column", "mass action", "prepareQueryBuilder", "listing page", "grid filter", "export grid".
Run chief-agent in full autopilot. Requires goals and contracts to exist. Chief creates TODO, delegates to builder, and repeats until milestone is done. Auto mode makes all decisions autonomously; safe mode stops on ambiguity. Use "/chief-autopilot" for auto or "/chief-autopilot safe" for safe mode.
Use when recreating a reference website or brand hub in this Hydrogen plus Weaverse repo, especially when deciding whether to reuse sections, add global styles, update theme schema, or resolve conflicts between the live site and project brand guidelines.
Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task
This skill should be used when the user asks to "audit this codebase", "audit this code", "code audit", "check for bugs", "review code quality", "find dead code", "check for anti-patterns", "performance audit", "check for code smells", "technical debt", "code health check", "review test quality", or "check error handling". For security-focused audits (vulnerabilities, OWASP issues, injection, authentication or authorization weaknesses, secrets handling, cryptography review, dependency CVEs, IaC, CI/CD), use the `security-audit` skill instead.
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.