Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Query and subscribe to Midnight blockchain data via the Indexer GraphQL API v4. Covers contract state reads, transaction lookups, block queries, real-time subscriptions (contractActions, blocks, unshielded/shielded transactions), state deserialization, the offset/null bug workaround, and TypeScript helper patterns. Use when a user needs to read on-chain state after a transaction, watch contract events in real time, look up blocks or transactions, query unshielded balances, or monitor DUST generation status.
Converts NetBox device-type and module-type definitions (the netbox-community devicetype-library format, also published via the NetBox Data Exchange / NDX) into Infrahub object templates as Infrahub object YAML, using a bundled Python converter driven by a schema mapping profile. TRIGGER when: importing NetBox device types or module types, exporting device types from a running NetBox instance, building object templates from vendor device models, converting line cards / PSUs / transceivers from NetBox module types into Template* objects, re-running a conversion after changing the mapping profile, debugging a wrong or failed conversion. DO NOT TRIGGER when: importing CSV/TSV data (use infrahub-importing-data), authoring schemas from scratch (use infrahub-managing-schemas), writing ordinary object data files (use infrahub-managing-objects), or setting up continuous two-way replication with a live NetBox (that is infrahub-sync, a separate product; a one-off export of device types is in scope here).
Use when running or writing shell commands with the Inkbox CLI (`inkbox` / `@inkbox/cli`) for identities, email, mailbox imports, phone, text/SMS, iMessage, A2A task/message history, contacts, notes, contact rules, vault, mailbox storage, mail clients (IMAP/SMTP), phone number, webhook, or signup workflows.
Use when writing TypeScript or JavaScript code that imports from `@inkbox/sdk`, uses `npm install @inkbox/sdk`, or when adding email, mailbox imports, phone, text/SMS, iMessage, A2A task/message history, contacts, notes, contact rules, vault, tunnels, mailbox storage, mail clients (IMAP/SMTP), or agent identity features using the Inkbox TypeScript SDK.
Source the next ML experiment proposal by **reading the audit digest** at `scratch/audit/<stem>/audit.md` (produced by `audit-ml-pipeline` at § 4 record-outcome). For every row in the digest's `## Checks summary` whose `severity` is `issue` or `tip`, follow the row's `documentation_url` to draft a Backlog row whose `Item` is the mitigation the docs recommend. The `## Metrics summary` provides context for the human summary paragraph but does not drive Backlog rows on its own. Returns the enriched Backlog rows + a one-paragraph summary back to `iterate-ml-experiment`, which writes the rows into `JOURNAL.md` and re-presents the sourcing menu so the user can promote a `B<N>` row. Stops at "Backlog enriched, summary returned"; never writes a per-experiment design note, never picks the "winning" finding — the user picks via `B<N>`. TRIGGER when: `iterate-ml-experiment` is picking a sourcing strategy and the user picks `skore` from the menu; the user says "mine the report", "what does skore see?", "fill the backlog from the diagnostic"; the previous experiment has finished and the user wants the report converted into actionable backlog items. SKIP when: the previous experiment hasn't run yet (no audit digest on disk); the user has a concrete modelling idea (use `iterate-from-user`); the task is the *mechanics* of running / opening a report — route to `evaluate-ml-pipeline`; the user wants a narrative read of one specific section of the report (route to `evaluate-ml-pipeline`). HOW TO USE: read the existing `scratch/audit/<stem>/audit.md` digest as text — do NOT re-open the skore Project, do NOT call `report.*` accessors. For each row in the `## Checks summary` section whose severity is `issue` or `tip`, follow the `documentation_url` (via WebFetch) and draft one Backlog row citing `audit:<stem>:checks.<code>`. Dedupe against rows already in `JOURNAL.md` Backlog by source citation. Return the candidate rows + a one-paragraph human summary. The parent skill writes the rows to `JOURNAL.md` and re-shows the sourcing menu.
Source the next ML experiment proposal from the user via one of three entry points selected by `AskUserQuestion`: (a) a scientific article URL the agent must read and synthesize, (b) a resource link or path (GitHub issue / spec file / reference repo), or (c) free-text the user types directly. In every branch, the agent reads the source, synthesizes its understanding of what to implement, and confirms with the user *before* returning the Proposal block. Hand the confirmed Proposal back to `iterate-ml-experiment`, which writes it into `journal/NN_short_name.md` and seeks the user's design-note approval. Stops at "Proposal returned, user-confirmed"; never writes a design note, never authors acceptance criteria. TRIGGER when: `iterate-ml-experiment` is picking a sourcing strategy and the user picks `user` from the menu; the user volunteers a concrete idea ("I want to try X"); the user pastes or links a scientific article, GitHub issue, spec file, or reference repo and asks us to read it. SKIP when: the user wants to mine the previous report (use `iterate-from-skore`); the user is asking for a symbol lookup or pipeline mechanics (use the `python-api` skill); the work is evaluation mechanics on a single report (route to `evaluate-ml-pipeline`). HOW TO USE: open with an `AskUserQuestion` for the entry point — article-link / resource-link / free-text. In each branch: gather the source material with the appropriate tool (`WebFetch`, `gh issue view`, `Read`), synthesize what you understand into the three shaping questions, and **confirm with the user via plain text** (one or two sentences: "you'd like to implement X by changing src/<pkg>/<file>.py — right?") before returning the Proposal. Do not write any design note. Do not author acceptance criteria.
Production guidance for Kling AI Open Platform Advanced Lip-Sync. Use for identifying/selecting one face in an existing video, assigning URL/Base64 or Kling TTS audio, cropping and inserting audio in milliseconds, mixing original sound, creating and monitoring tasks, downloading expiring results, consent/privacy review, sync QA, and repair. Do not use for still-image avatar generation or ordinary Kling video generation.
Publish the nurb model leaderboard from merged benchmark submissions. Sanity-checks every run landed since the last regeneration, writes or refreshes the editorial verdicts, regenerates the benchmarks repo's REPORT.md and this repo's site/benchmarks.html, and opens the publish PRs. Use when the user says "update the leaderboard", "publish the benchmarks", "regenerate the benchmark page", or after merging submission PRs.
LinkedIn post writing with hook formulas, formatting rules, and engagement patterns. Covers post types, algorithm signals, character limits, and content pillars. Use for: LinkedIn posts, professional content, thought leadership, B2B content, personal branding. Triggers: linkedin post, linkedin content, linkedin writing, linkedin strategy, linkedin engagement, linkedin algorithm, linkedin hook, linkedin formatting, thought leadership, professional content, b2b content, linkedin growth
Manages CockroachDB cluster capacity across all tiers. Self-Hosted covers node decommissioning for permanent removal and adding nodes for expansion. Advanced/BYOC covers scaling node count and machine size via Cloud Console, API, or Terraform. Standard covers adjusting provisioned compute (vCPUs). Basic auto-scales — guidance covers spending limits and cost management. Use when scaling capacity up or down, permanently removing nodes, or managing costs.
Create professional, consultant-grade PowerPoint presentations from scratch using python-pptx with McKinsey-style design. Use when the user asks to create slides, pitch decks, business presentations, strategy decks, quarterly reviews, board meeting slides, or any professional PPTX. Generates clean, flat-design presentations with 36 layout patterns, consistent typography, and zero file-corruption issues.
Install and configure MCP servers across desktop and CLI clients (Claude, Cline, Windsurf, Cursor, VSCode, Gemini CLI, Codex, Trae, Antigravity, etc.) on macOS/Windows/Linux, preferring @smithery/cli when supported and otherwise performing manual JSON config updates and path discovery.
Generates Mermaid mindmap diagrams from codebases, topics, files, or conversations. Visually summarizes source material as branching diagrams. Use when asked to create a Mermaid mind map, visualize a topic, map out a codebase, summarize a file as a diagram, generate a concept map, or create a visual overview.
Cryptographic primitives used by the Midnight node — Blake2-256 hashing, sr25519/ECDSA/Ed25519 signatures, twoxhash storage keys, and how they map to consensus, P2P, and state. Use when debugging node crypto, signature verification, or hash function choices.
Midnight RPC interface — JSON-RPC methods for contract state, ZSwap chain state, ledger version, Polkadot SDK defaults, and Partnerchain RPCs. Use when building dApps, wallets, explorers, or configuring node RPC exposure for validators vs observers.
Use when moving a Node.js, npm, Yarn, pnpm, or Bun project to Deno, or when adopting Deno incrementally in an existing JavaScript or TypeScript codebase. Covers using Deno as a drop-in package manager, running existing package.json scripts, CommonJS versus ESM, node_modules layout, lockfile migration, permissions, whether to adopt the built-in toolchain, and per-tool command equivalents.
Calligraphy and OCR — query running-script calligraphy (ancient texts / single-character details / radicals / character composition) and recognize text in calligraphy images. Use when you need calligraphy material or need to recognize images of stone rubbings. [Important] You must first read the original skill text to get the correct command format; do not guess.
Generate a high-cut-density action / fight scene by first composing a 16-cell storyboard image, then driving Seedance 2.0 image-to-video off that storyboard. Stacks GPT-Image-2 (character sheet + storyboard), Nano-Banana-2 (environment concept), and Seedance 2.0 i2v.
Run Claude Code or Codex CLI on Muapi (api.muapi.ai) using Muapi credits instead of a separate vendor account. Use when the user wants a local coding agent to use Muapi as its model provider, asks which Muapi models work with Claude Code or Codex, or needs the base URL, API key variable, provider block or model name for either agent. Covers Claude Code (Anthropic Messages) and Codex CLI (OpenAI Responses), model discovery, verification and troubleshooting.
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.
