Loading...
Loading...
Found 1,666 Skills
Build Docker images for Python services following team conventions. Use this skill when writing Dockerfiles, authoring CI image build pipelines, or adding a new service — covers mitodl image naming, git short-ref tags, relocatable uv venvs, and shared library handling.
Diagnose and fix broken Goldsky Compose apps interactively. Triggers on: compose app in error state, crashlooping, not running, not processing tasks, cron not firing, HTTP trigger returning 500, onchain event listener missing events, wallet errors, gas sponsorship failures, 'No bundler provider available', manifest validation errors, bundling/esbuild failures, secret missing, 'You cannot use a smart wallet in local dev', 'Transaction Receipt failed with status'. Also use when the user mentions a Compose app name alongside a problem, even if they don't say 'compose' explicitly, if they're referring to `goldsky compose` commands (not `goldsky turbo` or `goldsky pipeline`). Runs `status`/`logs`/`secret list`/`wallet list` to identify root cause, and offers fixes. For building a new app from scratch, use /compose instead. For manifest field / CLI flag / API lookups without an active problem, use /compose-reference instead. Do NOT trigger on Turbo or Mirror pipeline problems.
Use this skill when the user wants to convert a Wang Jianshuo-style WeChat article (article.md) into a narrated short MP4 video — featuring TTS voiceover via Volcano Engine Volcano TTS, scene-specific HyperFrames CSS/GSAP animations, subtle sound effects (SFX), abstract watercolor backgrounds, and end-to-end pipeline rendering to a 1080×1920 portrait MP4 (30-90 seconds). Triggers — "把这篇文章做成视频", "做一个解说视频", "讲解视频", "/wjs-converting-text-to-video".
End-to-end data engineering pipeline using MinIO, Airbyte, PostgreSQL, DBT, and Airflow with medallion architecture (Bronze/Silver/Gold layers)
Build end-to-end real-time data pipelines with Kafka, PostgreSQL, Airflow, and Streamlit using Medallion Architecture for streaming analytics.
Conveyor integration. Manage Organizations, Projects, Pipelines, Users, Goals, Filters. Use when the user wants to interact with Conveyor data.
Create, run, and maintain API test collections using Bruno (OpenCollection YAML format and legacy Bru format). Use when the user wants to: (1) create a Bruno API test collection from scratch or from OpenAPI/Swagger specs, (2) write API request files with tests and assertions, (3) run API tests using bru CLI, (4) generate test reports (HTML, JUnit, JSON), (5) set up CI/CD pipelines (GitHub Actions) for automated API testing, (6) debug or fix failing Bruno API tests, (7) add environment configurations for API testing, (8) chain API requests with data extraction, or (9) work with any .yml/.bru Bruno collection files. Triggers on mentions of 'Bruno', 'bru CLI', 'API testing collection', 'OpenCollection', or requests to automate API testing with file-based collections.
Run an autonomous Humanize-governed SGLang SOTA performance loop for one LLM model: first perform the fixed fair SGLang/vLLM/TensorRT-LLM deployment search and benchmark, then start one RLCR loop that repeatedly decides the gap, profiles the current bottleneck, runs layer/kernel pipeline analysis, patches SGLang code, optionally uses ncu-report-skill for kernel evidence, and revalidates until SGLang matches or beats the best observed framework under the same workload and SLA.
Scaffold the test framework and CI/CD pipeline for the project's engine. Creates the tests/ directory structure, engine-specific test runner configuration, and GitHub Actions workflow. Run once during Technical Setup phase before the first sprint begins.
Orchestrate the UI team through the full UX pipeline: from UX spec authoring through visual design, implementation, review, and polish. Integrates with /ux-design, /ux-review, and studio UX templates.
Build ETL pipelines and analytics dashboards for Harvard Art Museums API data with MySQL storage and Streamlit visualization
Structured data research: search sources, extract structured data, archive raw sources, maintain canonical tracker pages, deduplicate. Parameterized via YAML recipes for investor updates, donations, company updates, or any email-to-structured-data pipeline.