Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when deciding which documents a software or product project needs to produce — classifies across 10 dimensions, identifies product capability areas (4-signal algorithm), and produces a proportional, capability-scoped manifest with all five sections populated (documents, roles, skills, tools, capabilities). Re-tailors when the project changes (amend). Covers the full SDLC universe (seven lifecycle bands + four domain overlays). Returns a three-key JSON payload; caller writes two files from it (capability-map.yaml + manifest.yaml) — never assumes scope_root. Discovery only: decides which documents and what it takes to produce them, not how to author them. Keywords: document discovery, documentation plan, SDLC documents, document manifest, capability map, proportional docs, manifest completeness.
Use this skill when the user asks to "review a prompt", "analyze conversation history" or "diagnose understanding", or when it is invoked with /prompt-review. It reads past AI agent conversation history (Claude Code, GitHub Copilot Chat, Cursor, Cline, Roo Code, Windsurf, Antigravity, Gemini CLI, OpenAI Codex, OpenCode), estimates technical understanding, prompting patterns and AI dependence, and generates a report.
Python design patterns for CLI scripts and utilities — type-first development, deep modules, complexity management, and red flags. Use when reading, writing, reviewing, or refactoring Python files, especially in .trellis/scripts/ or any CLI/scripting context. Also activate when planning module structure, deciding where to put new code, or doing code review.
Set up and run a documented QA process for a project: initialize tests/docs/ with test-case documents, execution-tracking and bug-tracking CSVs, baseline/weekly metrics templates, P0-P4 bug severity, OWASP Top 10 security test coverage, and a master prompt for autonomous LLM-driven test execution or third-party QA handoff. Use when asked to 「QA プロセス立ち上げ」「テストケース文書化」「QA 引き継ぎ資料」「バグ管理表」, when starting structured QA from scratch, or when a QA team needs handoff documentation. Do NOT use for: writing ordinary pytest unit tests or deciding coverage policy (that lives in rules/testing.md, 75% target).
Search and download ebooks from LibGen.li. Use when the user wants to download ebooks via LibGen, search for books on LibGen, or mentions "从libgen下载", "libgen下载", "用libgen抓取". Triggers when qiao-epub-bot fails or the user explicitly asks for LibGen.
Discover and install related skills from inference.sh skill registry. Helps find complementary skills for your AI workflow. Use for: skill discovery, workflow expansion, capability exploration. Triggers: related skills, find skills, skill discovery, complementary skills, expand workflow, more capabilities, similar skills, skill suggestions
Handle replies to your cold outreach end to end — classify each response, draft the right answer from the full conversation, and send it through La Growth Machine after you approve. Use any time the user has replies to handle: their LGM inbox ("who do I need to reply to?"), a campaign's replies, or a pasted thread. When a conversation is pasted and the user asks what to reply, this is the right tool — don't improvise a reply without it. Triggers on: 'reply to my inbox', 'who do I need to answer', 'handle my campaign replies', 'what do I reply to this', 'help me reply to this prospect', and the French 'à qui je dois répondre', 'réponds à mon inbox', 'réponds aux leads de ma campagne', 'aide-moi à répondre'. Reads the whole thread, classifies the reply, drafts one calibrated answer in the thread's language, shows them for review, and on approval sends via LinkedIn or email natively. Nothing is sent without your OK. For SDR, BDR, RevOps, Growth and founders. Maintained by La Growth Machine.
Plan Fireworks post-training from a task-shaped goal — recommend a method, cookbook entry, data plan, and eval from what the user already said, ask only decision-critical questions, and hand off to configure when ready to train. Use when the user describes a problem in plain language, is unsure which method or dataset fits, needs public dataset ideas, or wants to explore before committing. Read-only — does not create jobs or upload data. For explicit train requests with known model and data, use configure; for failures use debug.
Check PRD coverage after development is complete. Not for PRD quality, plan design, or reviewing a single diff. Compare completed plans, records and implementation, distinguish omissions from changes, adjudicate differences interactively, and generate a gaps plan if needed
Use when reviewing/judging a finished (or amended) wireframes document — an acceptance gate: can the downstream hi-fi + UI engineering build the screen structure from it. Judges a TEXTUAL markdown wireframe against a single-sourced buildability + coverage + composition bar: every flow-named screen/state covered with quality states; layout unambiguous on a grid + shared app-shell meeting an objective layout-quality bar; real + consistent components; affordances + data-display annotated; microcopy intent (no data-model leak in labels); screen-composition a11y (landmarks/focus-order/target-size) — pixel contrast/focus-appearance are the design-system's, not judged here; responsive; gaps surfaced; structural not hi-fi; an amend reviewed as a scoped versioned delta. Emits `VERDICT: approve|revise` + actionable findings; approves a doc meeting the bar (no false-revise on a thin screen), revises only on a named gap. Not for authoring, the navigation graph (user-flows), the visual tokens (design-system), or hi-fi.
Validates locally (`robomotion validate`) then executes a Robomotion flow on a robot (`robomotion run <flow-dir>`), tailing the agent-mode JSONL session log to drive a validate → run → observe → fix loop with bounded retries. Use when the user says "run the flow", "start on robot X", "trigger this on the robot", "test on a robot", or "deploy and run".
Use this skill whenever the user wants to download academic papers, search for research literature, get citations (BibTeX/RIS/EndNote), manage WebVPN institutional proxy for paper access, import .bib files, or batch-download papers. This skill orchestrates the scansci-pdf MCP server which exposes 18 high-level tools covering download (OA/grey/institutional channels), discovery, queue preparation, diagnostics, and login. TRIGGER when: user mentions downloading papers, DOI, arXiv ID, Sci-Hub, paper search, literature review, citation export, WebVPN, institutional access, "帮我下载论文", "搜索文献", "批量下载", "论文下载", "文献检索", or provides a list of DOIs/arXiv IDs. SKIP: user is only discussing papers conceptually without intent to download/search/cite, or user asks about non-academic PDFs (invoices, reports, etc.).
The industry standard library for machine learning in Python. Provides simple and efficient tools for predictive data analysis, covering classification, regression, clustering, dimensionality reduction, model selection, and preprocessing.
Comprehensive guide for SciPy - the fundamental library for scientific and technical computing in Python. Use for integration, optimization, interpolation, linear algebra, signal processing, statistics, ODEs, Fourier transforms, and advanced scientific algorithms. Built on NumPy and essential for research and engineering.
Best-practices reference for the ScraperAPI Python SDK (scraperapi-sdk package). Consult whenever the user is writing, debugging, or reviewing Python code that calls ScraperAPI. Use when user asks: "scrape a website with Python and ScraperAPI", "how do I use ScraperAPIClient", "ScraperAPI Python render example", "Python ScraperAPI async", "batch scraping Python ScraperAPI", "ScraperAPI premium Python", "how to handle ScraperAPI errors in Python", "ScraperAPI structured data Python". Covers client setup, all request parameters, the escalation ladder (standard → render → premium → ultra_premium), async jobs for batches, structured data endpoints, error handling, and credit budgeting. Note: Transmits user-supplied queries, URLs, and content to ScraperAPI.
Finds Robomotion packages, nodes, and templates via the `robomotion` CLI, which is backed by Bleve full-text search with fuzzy matching and semantic expansion. Use when the user asks to find a package, explore templates, discover what nodes exist for a task, or check exact property names before writing a flow.
SEO architecture and content strategy for search visibility. Covers entity-first optimization, structured data, E-E-A-T signals, AI Overviews optimization, and content auditing. Use when optimizing search rankings, implementing JSON-LD schema, improving E-E-A-T signals, auditing site performance, planning topical authority, or structuring content for AI Overviews and featured snippets.
Procedural noise functions in GLSL—Perlin, simplex, Worley/cellular, value noise, FBM (Fractal Brownian Motion), turbulence, and domain warping. Use when creating organic textures, terrain, clouds, water, fire, or any natural-looking procedural patterns.
Follow-up Signals scout for recently merged pull requests. Works out whether each one has deployed, then checks the project's telemetry for whether it did what it claimed, had the impact it expected, or caused a side effect that needs a look.
Sends and receives SMS text messages via the SMS channel of the Sinch Conversation API. Covers sender ID types (long code, short code, alphanumeric, toll-free, 10DLC), GSM 7-bit vs UCS-2 character encoding, concatenated multi-part messages, opt-out (STOP) handling, and SMS channel properties. Use when sending an SMS or text message, handling inbound SMS or STOP keywords, choosing or configuring an SMS sender ID, or debugging encoding and message-part issues.
Design, create, validate, review, and package a Claude Code skill (SKILL.md plus references/scripts/assets). Use when asked to 「スキル作って」「スキル設計」「SKILL.md 作成」「スキルレビュー」, when a new reusable workflow or domain knowledge should become a skill, when an existing skill's description fails to trigger or its SKILL.md has grown past progressive-disclosure limits, or when a skill needs a sanitization/security review before distribution. Do NOT use for: running or invoking an existing skill, or editing CLAUDE.md / rules (those are not skills).
Audit agent skills, plugins, prompts, manifests, scripts, dependencies, and bundled assets for provenance, prompt-injection, permission, execution, exfiltration, persistence, and update risk. Use when evaluating a third-party skill before installing, enabling, updating, publishing, or distributing it; reviewing an untrusted SKILL.md, agent configuration, MCP integration, archive, or repository; comparing a package with a known-good version; or investigating unexpected tool, network, credential, or filesystem behavior.
This skill should be used when the user asks to "perform SMTP penetration testing", "enumerate email users", "test for open mail relays", "grab SMTP banners", "brute force email credentials", or "assess mail server security". It provides comprehensive techniques for testing SMTP server security.
Transcribe audio to text with ElevenLabs Scribe and Whisper models via inference.sh CLI. Models: ElevenLabs Scribe v2 (98%+ accuracy, diarization), Fast Whisper Large V3, Whisper V3 Large. Capabilities: transcription, translation, multi-language, timestamps, speaker diarization, audio event tagging. Use for: meeting transcription, subtitles, podcast transcripts, voice notes. Triggers: speech to text, transcription, whisper, audio to text, transcribe audio, voice to text, stt, automatic transcription, subtitles generation, transcribe meeting, audio transcription, whisper ai, elevenlabs stt, scribe, eleven labs transcribe
Use when standing up a relational data layer with SQLAlchemy 2.x (2.0/2.1) ORM that must run on more than one dialect — SQLite, PostgreSQL, and MySQL — from a single codebase. Covers the typed 2.x ORM (DeclarativeBase / Mapped[...] / mapped_column), engine + connection-string + pooling, short-lived sessions and transaction scope, the sync-first / async (AsyncSession / await) split with a per-dialect driver matrix, and the cross-dialect gotchas that bite when one schema runs on all three engines: row locking (with_for_update / SKIP LOCKED), JSON columns, upsert (ON CONFLICT vs ON DUPLICATE KEY UPDATE), autoincrement / identity, and transaction isolation. Multi-dialect, portable, ORM-first. Not migrations (see alembic), not job-queue/lease patterns (see sql-job-queue), not a full API reference.
Hands-on SRC / crowdsourced testing / bug bounty vulnerability hunting workflow skill. Includes: a 5-phase methodology (intake → recon → enum → hunt → report), 19 attack playbooks (SQLi/XSS/RCE/SSRF/IDOR/CSRF/Path Traversal/File Upload/SSTI/XXE/Race/HTTP Smuggling/OAuth/JWT/SAML/GraphQL/Mobile/LLM/DoS), 305 structured payloads, 263 WAF/EDR bypass variants, 2,887 disclosed real HackerOne High/Critical cases, statistics from 77,000+ WooYun cases, a fingerprint library of domestic OA / middleware, and vertical playbooks for the banking / telecom industries. Triggers when the user mentions "src 挖洞 / src 漏洞挖掘 / bug bounty / 众测 / hackerone / 漏洞赏金 / SRC / 任意 X 漏洞 / 渗透测试" or asks "how to hunt a certain target / how to test a certain API / how to bypass a WAF".
End-to-end AI video production skill for agentic frameworks. Use when the user asks to make, edit, repurpose, caption, soundtrack, or export videos using HeyGen avatars, Seedance or ByteDance b-roll, OpenAI image generation and editing, AI UGC ads, Remotion, HyperFrames, screen recordings, FFmpeg, captions, ElevenLabs music, Suno, or social-video variants.
Digest of what your Superset agents did — sweeps workspaces, tasks, and agent terminals, then reports what finished, what needs review, and what's blocked. Use when the user asks what their agents did, wants a standup or summary of agent work, or returns after being away.
Use this skill when reviewing Swift code for runtime-level performance costs, including heap allocation, ARC traffic, stack vs heap storage, closure capture contexts, method dispatch, protocol witness dispatch, existentials vs generics, opaque types, copy-on-write, SIL optimizer output, unsafe memory boundaries, or module-boundary optimizer visibility. Do not use it for Swift Concurrency scheduling, SwiftUI rendering, app launch, or profiling workflows unless the question is specifically about Swift runtime costs.
TanStack DevTools for debugging Query, Router, and Form state in React apps. Use when setting up devtools, debugging cache state, or inspecting route trees. Use for devtools, react-query-devtools, router-devtools, form-devtools, debug, inspect, cache-viewer.
TanStack Query v5 performance optimization for data fetching, caching, mutations, and query patterns. This skill should be used when using useQuery, useMutation, queryClient, prefetch patterns, or TanStack Query caching. This skill does NOT cover generating query hooks from OpenAPI (use orval skill) or mocking API responses in tests (use test-msw skill).
Technical blog post writing with structure, code examples, and developer audience conventions. Covers post types, code formatting, explanation depth, and developer-specific engagement patterns. Use for: engineering blogs, dev tutorials, technical writing, developer content, documentation posts. Triggers: technical blog, dev blog, engineering blog, technical writing, developer tutorial, tech post, code tutorial, programming blog, developer content, technical article, engineering post, coding tutorial, technical content
Runs and authors behavioral tests for Robomotion flows using @robomotion/sdk/testing. Use when the user says "test the flow", "write tests for main.ts", "mock this service", "check branch coverage", or when a flow needs regression tests before a change. For pspec schema validation, use validating-flow instead.
Build apps with the TomTom Maps SDK for JavaScript (@tomtom-org/maps-sdk). Use when working with TomTomMap setup (including the map attribution — its TomTom and OpenStreetMap logos, which the license keeps on screen, their corner and padding, and the soft backdrop behind them with attribution.backdrop — and adding your own credits with attribution.credits, transformRequest to hold or rewrite map requests, the MapLibre web worker it registers for Vite builds, registerMapLibreWorker, and a map that stays blank under webpack, Next.js with Turbopack, or a re-bundling CDN because the worker doesn't load), MapLibre integration (map.mapLibreMap, and when to prefer SDK features over raw MapLibre), custom layers drawing a three.js or raw WebGL scene in metres around a place, aligned with the map through localFrameMatrix, placed under the 3D buildings and kept through style switches with map.addCustomLayer and the lowest3D anchor, and their objects made clickable and hoverable with a hitTest, instancing many moving objects (the three-buffer ring for ANGLE on Direct3D 11), BaseMapModule (showing or hiding layer groups such as 3D buildings and road shields, and road markings such as arrows and exit numbers, and its own 3D buildings hovered, clicked and coloured by id with buildings3D.hover, buildings3D.click and setBuildingColors, and buildings highlighted by place with getBuildingIdAt) and its settings as data with baseMapKnobCatalogue, setting, reading and resetting any module knob by id with setKnob, setKnobs, getKnob and resetKnob (StylingFoundationsModule and MapEffects too) and when to use them rather than applyConfig and updateConfig and checking a value with validateKnobValue, TerrainModule (hillshade and its look, 3D terrain elevation and exaggeration, every setting as data with terrainKnobCatalogue), and viewport utilities; geopolitical views of disputed territories and borders (the global `geopoliticalView`, `geopoliticalViews`, setGeopoliticalView, and which views each API serves with servesGeopoliticalView and GeopoliticalViewAPI); map styles, standard style IDs (standardStyleIDs, streetLight, streetDark, streetLightDriving, streetDarkDriving, monoLight, monoDark, streetSatellite), setStyle and StyleChangeHandler, style switcher; semantic map styling with StylingFoundationsModule (label/icon/road size knobs, the typeface of every map label from the style's serif and italic faces or your own font files with labels.customTypeface, globe projection and sky, the light on 3D buildings and reading it with getMapLight, rounded building corners, the stylingFoundationsKnobCatalogue, raw style-layer edits through layers.query and LayerSelection (exact layer ids, paint and layout derived from the style's or a knob's value, addFilterClause to narrow a layer's filter), while the POI, traffic and hillshade looks sit on POIsModule, the traffic modules and TerrainModule; map presets with applyMapPreset and mapPresetCatalogue; reading any style colour by its map-wide id with getStyleColor and styleColorKnobIds; theming the map from a website's colours, a CSS stylesheet, an image, a palette description or an artist's style with the map-theme plugin's deriveMapColors, mapColorsLightDark, deriveMapColorsFromCss and deriveMapColorsFromImage, and the accent colour routes, geometries and places follow — colors.accent, map.mapColors), recolouring the base map with setMapColors, switching it between day and night looks, and exporting the result with exportStyle, and the map-effects plugin (bloom and its bloom.only colour scope, glare that makes lights cast streaks like street lamps through a lens with glare.only, tint, grade, vignette, fog and the colour of its air with fog.color, depth of field, capture, your own GLSL passes with addPass, their vec3 and vec4 uniforms, textures and mipmapped, and your own 2D canvas layers between the overlays with addLayer and removeLayer, for paper, film grain or a watermark); flying a camera along a route with the flyover plugin (RouteFlyover, aim ahead, junction framing, terrain clearance, where the followed position sits on screen with anchorForPitch, the marker that follows the route with setMarker, flying it once to the destination with loop: false and onArrive, and seeking it by time or distance); editing a route by dragging with the route-dragging plugin (RouteDragging, an editable route whose stops move by their pins and gain new ones pulled off the route line, re-planned live while you drag every planIntervalMS with the answers in order, and handed to your own state with showOnMap: false, onWaypointsChange and onRoutes); 3D landmarks and buildings with the landmarks-3d plugin (Landmarks3D models of recognizable buildings, its KTX2 transcoder and transcoderPath, in their own textured colours with the texture knob, and Buildings3D, the base map's buildings in 3D with windows, lit windows at night, reflective glass, a sun and shadows, road names or POIs hidden behind them, their walls, roofs and the landmarks coloured from palettes of your own colours, picked or blended, each a shade of its own with variation, and single buildings and landmarks hovered, clicked and coloured by id with buildings.events, landmarks.events, setBuildingColors and setLandmarkColors, and their knob catalogues read from landmarks-3d/knobs without loading three.js); textures on the map's water, land cover and roads with the Landmarks 3D plugin's GLSurfaces (gl-surfaces, waves that mirror the sky, tree crowns, 3D trees, grass, field parcels, dunes, glaciers, scrub, mud flats, shingle, rock, paving, built-up ground and asphalt, all following 3D terrain, coloured for a season with surfaceSeasons, the light and wind they follow, sharing the map's light and the buildings' shadows with Buildings3D, every look as data with glSurfacesKnobCatalogue); user interaction events (click, hover, contextmenu, recently-hovered, dragging a feature with dragstart, drag and dragend, such as a waypoint, a place pin or a route line to pull a new stop onto, the pointer leaving a feature with no leave event, clicks and hovers on the rest of the map with BaseMapModule, changing their timings with updateEventsConfig), selecting and highlighting features yourself and reading which are selected with setEventState, clearEventStates and getEventStates on every data-owned module and module lifecycle events, and saving and replaying a module's display configuration as JSON (the *SerializableConfig types); search, geocoding, reverse geocoding (ReverseGeocodingResponse, which has no properties where nothing matches), autocomplete, search-box suggestions of places, brands and categories with getSearchSuggestions(), discovering places with discoverPlaces() (categories in words with filters.poiCategoryQuery, or resolved first with resolvePOICategories) and place details with getPlaceDetails(), area outlines with geometryData (PlaceGeometryProps), places and POIs (PlacesModule and its markerType, color, label and icon.opacity, where its pins and connections sit in the layer stack with PlacesBeforeLayerConfig, every places setting as data with placesKnobCatalogue, POIsModule and poisKnobCatalogue, hiding single POIs by id with filters.ids, custom icons and pins per POI category on the map's own POIs and on shown places with categoryIcons), clustering them with the pin-clustered marker type, drawing their entry points, which results PlacesModule.show() takes and what it adds to them (preparePlacesForDisplay), and a popup or result card on a clicked place, fuzzy search (FuzzyLevel), geometry and along-route search, all through discoverPlaces (route, maxDetourTimeSeconds, sortBy, each result's detourTimeInSeconds and detourDistanceInMeters), search filters and cursor pagination, geographic bias with geoBias, and EV charging stations (charging stations, charging points and connectors on search results); routing and calculateRoute (RoutingModule), a departure or arrival time with when (departAt, arriveBy), at a local wall-clock time with localDateTime, the route's color, widthPreset, widthFactor, opacity, waypoints.sizePreset and waypoints.sizeFactor, waypoint pins per role (start, stop, finish), stop numbering in numbers or letters, waypoint labels and hover growth, waypoint icons of your own or a POI category pin per stop, waypoints versus places (who draws a route's stops), every routing setting as data with routingKnobCatalogue, route alternatives and what sets each apart (the distinct sections no other route drives, getDistinctSections, DistinctSectionProps, DistinctSectionsOptions, and the roads each takes by road number, getImportantRoads, ImportantRoad, ImportantRoadsOptions, and the ferries, tolls and traffic on them or what an alternative adds and avoids against another route, getSectionsWithin, SectionsWithin, SectionsWithinOfType, SectionsWithinOptions, getSectionOverlap, RouteSpan, and why the live route avoids the usual one's jams and closures, compareRoutes, RouteComparison, CompareRoutesOptions), the route summary bubbles (what they say, the time against the selected route, which routes carry one and where they sit, their colour, typeface and zooms), which vehicle and truck parameters routing accepts, turn-by-turn guidance instructions and the lanes to take at each (getInstructionLanes), route sections including toll and charged roads (the default ones as defaultSectionTypes, to add to), the curves and curvy stretches of a route with their turn radius, heading change and severity, for keeping clear of winding roads (motion sickness) or seeking them (motorbiking), with getCurveSections, getCurvyStretchSections and isHairpin (hairpinCount), the tight ones drawn with a kerb (sections.curve.kerb), their thresholds set with calculateRoute's curveDetection or tried again on routes already calculated with withCurveSections, ringing a leg or any section from your UI with setSectionFocus, speed limits and the tunnel and closed-to-vehicles signs, border crossings between country sections, and reachable ranges (isochrones) with ReachableRangesModule, its bands coloured from the map's accent and land or your own palette, faded band by band with fill.outermostOpacityFactor, every setting as data with reachableRangesKnobCatalogue; GeometriesModule (color, your own fill colours with fill.palette, cycled or ramped with fill.paletteMode, dashed or dotted borders with line.pattern, fill.style, label, lineLabel, every setting as data with geometriesKnobCatalogue); traffic flow and incidents faded with opacityFactor, incidents in a bbox or a polygon and their icons (isIconsVisible), planned incidents (timeValidity) and the highlight of a focused or hovered incident (IncidentHighlightConfig), the other incidents dimmed while one is focused (highlight.unfocusedOpacityFactor) and its lines faded with line.opacity (IncidentLineConfig), and area analytics, and their settings as data with trafficAreaAnalyticsKnobCatalogue and the other traffic knob catalogues; custom GeoJSON layers and bring-your-own-data (CustomGeoJSONModule, BYOD, its settings as data with customGeoJSONKnobCatalogue, and colouring areas by the median or mean of your points per hexagon, square or district with aggregateIntoCells); and the agent-toolkit plugin for conversational map agents (createMapAgent, LLM tools, custom tools with locatePlace and getViewportBias, the user's location precision with createGetCurrentLocationTool, the opt-in executeMaplibreCode tool with createExecuteMaplibreCodeTool, the generated-code sandbox and the page CSP it needs with getCodeExecutionMode and allowMainThreadFallback, Vercel AI SDK). Also covers core Place/Route types and importing GeoJSON types such as Position from geojson (@types/geojson under pnpm), service config and a per-call retry, cancelling in-flight service calls with an AbortSignal and keeping only the latest one with createLatestRequest (search-as-you-type, refetch on map move, stale responses, race conditions, debounced input, and showing each answer of requests that start faster than they answer with supersede: 'on-answer') and the SDKError/SDKServiceError/SDKAbortError classes, their SDKErrorCode codes and the ServiceName in error.service (a 401 rejected key versus a 403 key not allowed an API or domain, and the Private Preview access such as Calculate Reachable Range or the 3D Landmarks tiles that a key lacks, read from apiErrorCode and privatePreviewAccess on services and the map alike), map failures (TomTomMapError, addErrorHandler, WebGL unsupported or context lost, rejected API key, a refused style or tile, Landmarks 3D tile errors), ViewportPlaces onError, and utilities such as bboxFromGeoJSON, bboxFromCoordsArray, isBBoxWithArea, getPosition, formatDistance, and formatDuration. Before integrating any SDK feature in Public Preview or Private Preview, plugins included (every plugin below 1.0.0 is in Public Preview, or in Private Preview where its doc says so), it shows the developer a preview notice and asks them to confirm. At the start of SDK work, it offers the developer the tomtom-maps-sdk-js-feedback skill, which reports what the SDK got wrong to TomTom with the developer's consent.
Generate transparent-background raster assets with Codex image generation plus deterministic cleanup. Use when the user wants a PNG sticker, icon, mascot, sprite, UI asset, or web-ready visual element with transparent background, or asks to remove/avoid a generated image background while preserving the subject.
Drive the tty7 terminal workbench from the shell with the `tty7` binary — list workspaces/tabs/panes, split a pane, send text or keystrokes into one, capture what is on a pane's screen, run a command in a real PTY and pass its exit code through, run a command in a shell pane you already have and get back its output and exit code, block until a pane finishes or needs input, see which coding agents are running and which ports a pane is listening on. Use this whenever tty7, panes, workspaces, or `%42`/`@7`/"the other pane"/"the other agent" come up; whenever you want to hand work to another agent and collect the result ("get Claude/Codex to do X", "派个活", "let another agent handle this", running several agents in parallel and merging what they produce); whenever you need to start something long-running or interactive (dev server, REPL, ssh session, `tail -f`, a TUI) that should not sit blocking your Bash tool; whenever a program needs a real terminal to behave the way the user sees it; and whenever you need to look at or report on what is running in some *other* terminal on this machine. Cheap to check: if `$TTY7_PANE` is set you are already inside tty7 and every command here works with no setup.
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.
