Data analysis, machine learning, LLM apps, and prompt design (9K skills)
Apply statistical power in reproducible local data workflows with version-aware APIs, explicit assumptions, and validation. Use when the user chooses statistical power or its strengths fit the task.
The English summary is being prepared. Showing the original description.
Design production-ready music prompts and optionally generate music through SandBase. Use for songs, instrumentals, soundtracks, jingles, loops, or multi-part music; use a speech or sound-effect workflow when music is not the main deliverable.
The English summary is being prepared. Showing the original description.
Plan, implement, or review ml pipeline work in an existing codebase with compatibility, security, and verification controls. Use when the user explicitly requests ml pipeline work.
The English summary is being prepared. Showing the original description.
Apply hugging face datasets in reproducible local data workflows with version-aware APIs, explicit assumptions, and validation. Use when the user chooses hugging face datasets or its strengths fit the task.
The English summary is being prepared. Showing the original description.
Apply data context extractor in reproducible local data workflows with version-aware APIs, explicit assumptions, and validation. Use when the user chooses data context extractor or its strengths fit the task.
The English summary is being prepared. Showing the original description.
Apply data visualization in reproducible local data workflows with version-aware APIs, explicit assumptions, and validation. Use when the user chooses data visualization or its strengths fit the task.
The English summary is being prepared. Showing the original description.
Use when designing, refactoring, or debugging Formax system prompt assembly, system-reminder injection, or skills/deferred-tool prompt exposure semantics; mandatory for any change involving FORMAX_DEFERRED_TOOL_EXPOSURE and request-payload parity checks.
The English summary is being prepared. Showing the original description.
Structured persuasion for tech leads, PMs, and founders—not activity logs. Five scenarios (kickoff, status update, wrap-up, investor pitch, solution selling) on one 5-part framework (Hook→Context→Proposal→Evidence→Ask). AI prompts for missing materials and audience context; pre-submit checklist. Claude Code plugin; Cursor, Codex, and chat via prompts.
The English summary is being prepared. Showing the original description.
Use when a city is setting up its devopsdays event for a new year and needs its data file, pages, redirect, and asset directories created from scratch.
The English summary is being prepared. Showing the original description.
Use when a devopsdays event has sold or confirmed a sponsorship and the sponsor needs to appear on the event's site - covers both sponsors already in the shared directory and brand-new ones needing a logo and data file.
The English summary is being prepared. Showing the original description.
Internal — for Boundless team members only. Query Boundless broker telemetry tables on Redshift for prod/staging operational data. Use when the user asks about broker health, request evaluations, request completions, proving times, skip rates, telemetry data, or wants to run SQL against the telemetry database on live networks. Also covers historical telemetry through 2026-04-24 stored as Parquet archives in S3 (queried via DuckDB). Do NOT use for debugging local code changes, reviewing PRs, or investigating issues in the codebase itself.
The English summary is being prepared. Showing the original description.
Create evidence-aware, interactive visual explainers as self-contained offline HTML. Use when a user asks to explain a concept, repository module, engineering tradeoff, or incident with a diagram, walkthrough, ELI5 treatment, data/request trace, failure view, or teach-back. Do not use for a plain short answer, ordinary prose rewrite, generic website implementation, or unsupported claims presented as facts.
The English summary is being prepared. Showing the original description.
CesiumJS time, properties, and animation - Clock, JulianDate, TimeInterval, Property, SampledProperty, CallbackProperty, PathMode, interval and sampled path materials, interpolation, splines, CZML temporal data. Use when making entity attributes or path materials time-dynamic, configuring the simulation clock, interpolating positions, or working with sampled, interval, or callback properties.
The English summary is being prepared. Showing the original description.
CesiumJS core utilities and networking - Resource, Color, Event, Request, RequestScheduler, error handling, helper functions, feature detection. Use when fetching remote data, managing HTTP requests, working with colors, handling events, debugging errors, or using utility functions like defined, clone, or buildModuleUrl.
The English summary is being prepared. Showing the original description.
CesiumJS entities and data sources - Entity, EntityCollection, DataSource, GeoJsonDataSource, KmlDataSource, CzmlDataSource, Graphics types, PathGraphics, PathMode, Visualizers. Use when adding points, labels, models, polygons, polylines, or time-segmented paths, loading GeoJSON/KML/CZML/GPX data, or working with the high-level Entity API.
The English summary is being prepared. Showing the original description.
Design and debug Elixir persistence with Ecto. Use for schemas, changesets, queries, preloads, transactions, migrations, multi-tenancy, and data access through application contexts. Covers database query performance and connection pools.
The English summary is being prepared. Showing the original description.
Build and debug Phoenix web interfaces and HTTP endpoints. Use for LiveView lifecycle and data loading, components, forms, routes, controllers, Plug, channels, and PubSub. Use ecto for changesets, queries, and persistence behind those interfaces.
The English summary is being prepared. Showing the original description.
Write and refactor idiomatic Elixir functions, modules, and data structures. Use for pattern matching, control flow, error handling, protocols, behaviours, and deciding whether a process is needed. Use otp for process design and supervision.
The English summary is being prepared. Showing the original description.
Use when prompting a learner to complete hands-on MATLAB coding exercises, guided practice, debugging drills, code tracing, small MATLAB projects, or MATLAB-script assessment during tutoring. Use when the tutor should create a complete runnable MATLAB script, execute it through MATLAB tools, compare the produced outputs with expected outputs, and evaluate MATLAB programming style.
The English summary is being prepared. Showing the original description.
Use when an instructor asks for a setup guide, adoption guide, planning guide, implementation checklist, prerequisite check, MATLAB Course Designer course structure plan, Common Cartridge workflow, Simulink starter and solution model planning, LMS import plan, or starter prompt for creating a MATLAB and Simulink enabled course with the matlab-generate-course skill.
The English summary is being prepared. Showing the original description.
Add fast, local, typed decisions to any project with Laya, an open-source non-generative decision model (pip install laya). It classifies, routes, scores and answers yes/no questions about a piece of text, returning calibrated probabilities in roughly 20-35 ms on a laptop GPU, with no LLM call and no data leaving the machine. Use this skill whenever the user wants to classify or route text, triage tickets or emails, detect spam, phishing, toxicity or intent, put a guardrail in front of an agent or LLM, score something against a rubric, or replace an LLM-based classifier to cut latency or cost. Also use it when they mention Laya, Jev, a "System 1 model", "typed decisions" or a "decision model", even if they never name Laya.
The English summary is being prepared. Showing the original description.
Craft verifiable, tight goal prompts for AI coding agents (Claude Code /goal, Codex Automations, Pi), either from a standalone task interview or from an already-approved to-goal handoff. Use when the user says "给我一个 goal 提示词", "帮我写个 goal", "设置一个自动化任务", "我想让 agent 自动做 X", or asks to turn a task into a self-running loop. Ensures every goal has a checkable completion criterion so the agent knows when it's done.
The English summary is being prepared. Showing the original description.
Run a one-shot or flat parallel batch of provider LLM subagents (headless `cc-fleet subagent`) that return a result. Use when fanning out N independent tasks, doing bulk per-file work, or calling a specialized provider model (DeepSeek / GLM / Kimi / Qwen / MiniMax). NOT a long-lived collaborator you message back and forth (that is /cc-fleet:team); NOT a multi-phase pipeline with dependencies or resume (that is /cc-fleet:workflow); NOT trivial work the main session should just do.
The English summary is being prepared. Showing the original description.
Start long-lived provider LLM teammates as native Claude Code agent-team members (the native Agent tool with a ccf-<provider> type) that you message with SendMessage — multi-turn, collaborative, watchable in tmux panes. Use for sustained parallel build/work ("start 3 glm teammates", N teammates on N files), or when you need a collaborator you message across turns, from a terminal `claude` session. NOT a fire-and-forget one-shot or a flat batch of independent prompts — that is /cc-fleet:subagent. NOT a scripted multi-phase run — that is /cc-fleet:workflow.
The English summary is being prepared. Showing the original description.