Loading...
Loading...
Found 5,519 Skills
Create and operate durable, source-backed Researcher runs. Use when a user wants cited research, a live watch URL, reusable source records, YouTube/video transcript extraction, website/domain extraction, run continuation, forked report versions, or run-scoped Q&A over a completed Researcher run.
Builds, runs, debugs, and operates applications on AWS Lambda MicroVMs — Firecracker-isolated, snapshot-resumable serverless compute environments running inside a container with up to 8 hr lifetimes. Applicable when workloads need strong isolation between tenants, isolated serverless compute, sandbox compute, or secure multi-tenant execution. Also suited for AI/agent code-execution sandboxes, interactive code playgrounds and notebooks (Jupyter, REPLs, dev environments running user-supplied code), reinforcement-learning environments, multi-tenant CI executors and build runners, sessionful game or simulation servers, or isolated security scanners. Also applicable when the workload needs long-lived sessions, a real port-listening server (gRPC, WebSocket, custom TCP protocols), state preserved across periods of inactivity (suspend/resume), container-level access (FUSE, eBPF, custom syscalls), or session-affine routing.
Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers. Use when deploying GKE inference servers, configuring GKE GPU resources for inference, or deploying LLMs on GKE. Don't use for generic batch jobs or HPC task queues (use gke-batch-hpc instead).
亚马逊店铺文件上传（与 linkfox-amazon-store-auth 等同系列），经 /spApi/developerProxy 调用 Uploads API v2020-11-01 的 createUploadDestinationForResource，再向返回 URL 上传文件，供 A+ Content、Messaging 等 API 使用。当用户提到上传文件、createUploadDestinationForResource、upload destination、contentMD5、预签名上传、SP-API 上传、A+ 图片上传、Messaging 附件上传 时触发。
Convert evidence gaps, conflicts, and anomalies into traceable candidate innovation points, and screen them based on contribution, feasibility, and falsifiability criteria. Use when the user asks for "finding research innovation points", "generating research directions from literature gaps", "screening candidate innovation points", "brainstorming research directions", or requests the rw-research-novelty workflow. Runs without a private local workspace or preset research-lab; use user-provided material and bundled public-source methods.
Organize scientific research text based on user-provided research materials and verifiable sources, determine the writing functions of chapters, sections, and paragraphs, and fill in the gaps between evidence, explanations, significance, and research questions. Use when the user asks for “write PhD chapters”, “revise paper arguments”, “write academic paragraphs based on sources”, “revise scientific writing according to supervisor feedback”, or requests the rw-phd-write workflow. Runs without a private local workspace or preset research-lab; use user-provided material and bundled public-source methods.
Validate an implemented React Doctor rule before merge. Use after focused tests pass to review detector correctness, inspect open-source hits, run pull request parity, add regression coverage, prepare a changeset, write pull request copy, or address review findings.
Retrieve, query, and identify relevant Google Cloud Monitoring metric descriptors for a GCP service or resource (such as Compute Engine, Spanner, BigQuery, Cloud Run, Cloud SQL, Pub/Sub, Cloud Storage, etc.). Use when asked to find, list, search, or discover GCP metric types, names, kind/value schemas, or descriptors.
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.
Apifox Import/Export and Quality Gate: Import OpenAPI/Postman/Apifox native formats, export OpenAPI/HTML/Markdown/Postman/Apifox native formats; Validate spec completeness, tags grouping, schema/body coverage before import, verify count, module and resource visibility after import.
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
Overview of Tavus, the AI research lab pioneering human computing. Use when you need context about what Tavus is, their mission, core concepts like CVI and Human Computing, the model stack (Phoenix, Raven, Sparrow), or links to docs/platform/resources.